Verification & Evidence

I built MaRN (Mapping Networks) , a PyTorch library that lets you optimize a compact latent representation instead of directly training every model parameter. Some results from my current benchmarks: MNIST CNN: Reduced a 537,748-parameter CNN to 4,080 trainable parameters ( 131.8× reduction ), with accuracy decreasing from 99.07% → 98.10% ( −0.97 pp ). A smaller 107,998-parameter CNN was reduced to 1,872 trainable pa

View original ↗

Nature Computational Science, Published online: 09 October 2026; doi:10.1038/s43588-026-01063-0 Researchers pair active learning with geometric deep learning to predict the outcome and site selectivity of chemical reactions from scarce data, guiding experiments that accelerate drug discovery and expand accessible chemical space.

View original ↗

Abstract With the growing use of Artificial Intelligence (AI) in remote sensing of mass movements, open and suitable datasets for model training and validation are increasingly needed. Although Differential Synthetic Aperture Radar Interferometry (DInSAR) is a widely used technique for studying mass movements, wrapped interferograms remain less exploited, and the importance of geomorphological expertise in their inte

View original ↗

It’s hard to believe that Periodic was only launched last September : One year later, it is considered one of the pre-eminent AI scientist labs, with dizzying talent density and astonishing progress in the autonomous lab buildout: Most people are familiar with the standard credentials of Liam and Dogus , but we found an incredible “talent slope” while learning more about Periodic, where each successive employee seems

View original ↗

Why is Anthropic running a biology lab? Anthropic is best known for Claude, the artificial intelligence chatbot that competes with OpenAI’s ChatGPT and Google’s Gemini. But the AI company now employs molecular biologists, studies DNA, and operates a laboratory where scientists conduct physical experiments. The San Francisco Bay Area facility is what researchers call a “wet lab”: a laboratory where scientists work dir

View original ↗

image credit- shutterstock China's XtalPi Holdings, an AI and robotics-driven drug and materials discovery company, has debuted Kodexia™, the industry's first closed-loop small interfering RNA (siRNA) discovery platform combining generative AI, first-principles-driven biological modeling, and automated experimentation. Validating the rapid execution capabilities of this new infrastructure, the company simultaneously

View original ↗

Large language model agents can improve across tasks by retaining reusable skills distilled from prior interactions. Recent work jointly optimizes task execution and skill extraction, enabling the policy and skillbank to co-evolve. However, as the actor continues learning, rewarding skill proposals through their reuse in subsequent training steps may conflate skill benefits with actor improvement, while directly test

View original ↗

This work examines the transfer of a co-evolved communication mechanism between two robotic agents from a discrete two-dimensional (2D) simulator to a three-dimensional simulator with real physics (3D). The study focuses on whether a communication mechanism co-evolved in a 2D environment retains its functional role after transfer to a 3D physics-based simulator. To support this analysis, the effects of the episode ti

View original ↗

Multi-teacher on-policy distillation (MOPD) is used in two settings. In common-domain composition, several teachers score each student rollout from one prompt domain and their signals form a single target; in routed-domain distillation, prompts from different domains are assigned to the corresponding specialist. Both settings usually transfer each teacher's endpoint policy, which mixes what post-training changed with

View original ↗

Share SOUTH SAN FRANCISCO, Calif. – October 6, 2026 – insitro, the AI company unlocking causal human biology to systematically generate high-impact therapeutics, today announced that the advanced machine learning models that insitro built with Eli Lilly and Company (Lilly) to predict in vitro and, critically, in vivo properties of small molecules can now be used by certain biotech companies in Lilly TuneLab™. Trained

View original ↗

Large language models (LLMs) and vision-language models (VLMs) are usually frozen after deployment, so they do not learn from the cases they solve. This is especially concerning in medicine, where new clinical evidence, updated guidelines, and new therapies can change established practice. Fine-tuning can update the model, but it requires access to model weights and additional training. Parameter-free methods avoid t

View original ↗

Large language models (LLMs) are increasingly relied upon to support ambient documentation and clinical reasoning. Here we examine the impact of a failure mode shared between these two applications by assessing their sensitivity to information incidental to the patient encounter. In 576 patient-clinician dialogues, we found that frontier models inserted small-talk exchanges into 35% of notes, while mean quality score

View original ↗

On 13 September, leading luminaries and up-and-coming talents in mathematics and computer science congregated at the annual Heidelberg Laureate Forum in Germany for a week of discussion, networking, and—naturally—wurst. Having attended several of these events in the past, the mathematicians normally focus their chatter on which famed researchers are present, or what interesting problems they have been working on. But

View original ↗

Site-specific fertilizer recommendation systems adapt nutrient advice to location, soil properties, crop type, and production targets, but scientific reuse is constrained when recommendation functions remain accessible mainly through interactive interfaces, outputs are not versioned, and trained approximations cannot be independently loaded or benchmarked. This technical report presents the Turba fertilizer machine l

View original ↗

At the International Conference on Machine Learning (ICML 2026) , Dezhi Luo, Yijiang Li, Maijunxian Wang, Tianwei Zhao, Bingyang Wang, Siheng Wang, Pinyuan Feng, Pooyan Rahmanzadehgervi, Ziqiao Ma , and Hokin Deng presented their work Vision Language Models Cannot Reason About Physical Transformation . In this interview, William Yijiang Li tells us more about the research, the method the team used, and the controlled

View original ↗

Real-world users often exhibit highly heterogeneous preferences over multiple objectives for LLM responses. A lightweight aligner can tailor these responses to individual preferences, but scarce user-specific feedback makes personalized training difficult. Learning shared initializations across users can support few-shot adaptation. However, heterogeneous preferences and competing objectives cause gradient conflicts

View original ↗

Physics-based neuromorphic computing promises major gains in performance and energy efficiency, but training remains largely in silico, requiring costly physical modeling and suffering from fabrication-induced errors. Here we introduce on-chip, in situ physical gradient descent (INSPIRE), a general training method for photonic integrated circuits. INSPIRE uses on-chip synthetic time-reversal holography to measure the

View original ↗

Continuous asynchronous replanning is essential for real-time generative robot policies, but independent stochastic initialization can cause mode switching and inconsistent continuation across action chunks. We propose Execution-Aligned Progressive Noise (EAPN), which introduces structured stochasticity at both inter-chunk and intra-chunk levels. Across replanning steps, EAPN propagates a shared noise trajectory and

View original ↗

Enterprise AI agents that share a memory store face two unaddressed risks: sensitive data can leak through legitimately computed results the requester could not derive, and departments can silently compute a same-named key performance indicator (KPI) through conflicting logic. Existing agent-memory systems (e.g., MemGPT, Zep, A-MEM) gate retrieval by content, ownership, and role, not derivation, missing a cached insi

View original ↗

Modern information systems, including many agentic workflows, use dense retrieval to explore large amounts of unstructured data. However, dense retrieval relies on surface-level semantic similarity, which is insufficient for increasingly complex search applications. Here, we investigate agentic retrieval that combines the reasoning capabilities of Large Language Models (LLMs) with the efficient corpus exploration of

View original ↗

Google DeepMind watermarks AI-designed proteins, and the first binders still bind Google DeepMind has taken its SynthID watermark into biology, and says the first watermarked protein binders still bind. In wet-lab testing against three target proteins, VEGF-A, the SARS-CoV-2 spike protein RBD and PD-L1, the watermarked designs “matched the hit rate, binding affinity, and natural sequence diversity of unwatermarked ve

View original ↗

Language models can already help researchers search the literature, synthesize evidence, and work through complex questions. But scientific work places particular demands on these models—answers need to stay grounded in evidence, the models need to preserve what the evidence actually supports rather than quietly broadening a study’s conclusions, and researchers need to be able to verify the final outputs. We see that

View original ↗

The development of machine olfaction (digitization of odor) is currently hindered by data scarcity and the lack of standardization in descriptive labels. Datasets integration faces the challenges of descriptor-level conflicts, including cross-source labeling inconsistencies, synonym redundancy, skewed distributions, etc. To address the semantic confusion inherent in multi-source data, we developed a SEA (Statistical

View original ↗

Reasoning traces improve large language models (LLMs), but current models are trained to reason mostly in English. It has been shown that forcing a model to reason in another language degrades accuracy, even when the reasoning language matches the language of the prompt -- but only for a setting where the model reasons over a short prompt. Here, we ask whether the same holds for retrieval-augmented generation (RAG),

View original ↗

Existing streaming vision-language models (VLMs) continuously perceive and reason over visual streams, but their computational pathways remain fixed throughout inference. Consequently, they cannot adapt computation to evolving scene dynamics, where different future events demand different levels and forms of perception. We show that streaming VLMs inherently possess the ability to anticipate the immediate future, and

View original ↗

Vision-Language-Action (VLA) foundation models have scaled rapidly to enhance manipulation performance and generalizability, but this scaling incurs high computational costs that render real-world deployment increasingly challenging. Existing approaches typically mitigate this issue by designing smaller architectures or reducing the iterative denoising steps in flow-based policies. In this work, we propose FastOPD, a

View original ↗

World action models integrate future visual dynamics with robot action prediction, but their scalability remains limited by the need for action-annotated robot trajectories. Observation-only videos contain rich evidence about interaction dynamics, but existing approaches typically use them either to pretrain visual representations that must later be adapted for control, or to infer latent actions that are subsequentl

View original ↗

Introducing SynthID Bio: Google DeepMind Puts Watermarks Inside AI-Designed Proteins Google DeepMind is introducing SynthID Bio after laboratory tests produced the first watermarked protein binders that retained their intended biological function. The September 30 announcement moves AI watermarking beyond images, text, audio, and video. Its signature can remain detectable in a synthesized physical protein, not merely

View original ↗

October 1, 2026 report Google DeepMind develops invisible watermarks for AI-designed proteins Paul Arnold Author Gaby Clark Scientific Editor Robert Egan Senior Editor Watermarks have long protected everything from bank notes and fine art to digital photographs and software, helping prove authenticity and trace an object's origin. Their main function is to protect copyright and verify authenticity. That same traceabi

View original ↗

World action models (WAMs) have emerged as a promising paradigm for robotic control by jointly predicting future visual dynamics and actions from an initial observation and instruction. However, existing WAMs struggle with long-horizon prediction, as generating dense video rollouts is highly inefficient. Some recent WAMs address this by predicting a single future frame without generating the full video, but this appr

View original ↗

Reinforcement learning based post training of diffusion models, such as Denoising Diffusion Policy Optimization (DDPO), optimizes a reverse diffusion process under a reward function. However, current approaches to reward optimizations do so at the cost of diversity and quality. In this paper, we provide better tradeoffs through careful theoretical considerations and method design. We analyze the theoretical framework

View original ↗

Scientific progress emerges from a longitudinal ecosystem in which researchers, institutions, funding agencies, collaboration networks, and the scientific literature co-evolve. As AI becomes increasingly involved throughout the scientific research cycle, understanding these interconnected and evolving processes becomes increasingly important. We introduce SciUtopia, a persistent, closed-loop LLM-agent simulation fram

View original ↗

As LLM agents undertake increasingly complex, long-horizon tasks, verifying their outputs becomes increasingly challenging. We study how verification capability can be strengthened with a fixed base model, without access to reference answers or grading rubrics at test time. Repeated sampling yields multiple rollouts that can contain complementary correct claims, but we need a reliable verification mechanism to determ

View original ↗

Introducing SynthID Bio Proof of concept for watermarking AI-generated proteins while preserving biological function. Today, we’re introducing SynthID Bio to bring watermarking technology to synthetic biology. SynthID Bio embeds an imperceptible signature directly into the biological code, ensuring the watermark is verifiable not just on a digital model but on the synthesized, physical protein itself – all while pres

View original ↗

Inflammation is widely considered a hallmark of animal immune responses. In mammals, this process is mediated in part by pro-inflammatory cytokines of the interleukin 1 (IL-1) superfamily, which establish and support microenvironments that regulate immune cell activity. However, the evolutionary origins of IL-1 cytokines remain elusive, as homologous proteins have been difficult to confidently identify outside verteb

View original ↗

Legal language models require reward signals that capture not only answer correctness but also the multidimensional quality of legal responses. Existing reward methods, however, often rely on coarse-grained holistic judgments, providing limited domain specificity and interpretability. We introduce LexReward, a taxonomy-driven framework for legal reward modeling. LexReward characterizes legal response quality along th

View original ↗

A transformer language model performs a bounded amount of computation per token, and recent work by Vishal Sikka, former CEO of Infosys, argues that this bound limits which tasks a model can carry out or verify (arXiv:2507.07505). We ask how much of the budget beneath that ceiling is spent on work the model has already done. Serving is stateless across requests: a model that answers a second question about a document

View original ↗

Modern multimodal models bring generation and understanding into a single unified system, which enables them to provide and learn from their own feedback. Motivated by this unified capacity, we introduce UniEvo-VL, a self-evolving framework for multimodal models to learn from this constructive self-correction feedback during test-time compute. Instead of relying on a separate, often larger, teacher, we leverage their

View original ↗

Biology doesn't operate in silos, and neither should the AI representation of it. Quine is an early-stage research effort to create a multimodal world model of biology. By connecting insights across biological scales and modalities, Quine helps scientists computationally search a space far larger than intuition allows and prioritize hypotheses before they reach the lab. Experimental results provide important feedback

View original ↗

Welcome to our monthly digest, where you can catch up with any AIhub stories you may have missed, peruse the latest news, recap recent events, and more. This month, we meet AI pioneer Ken Goldberg, use AI techniques to track animal populations, investigate how to improve recommender systems, and find out how external knowledge is used in AI systems. Combining cultures, from code to canvas: an interview with Ken Goldb

View original ↗

AI Models & Platforms Microsoft Research Debuts Quine, a Multimodal World Model of Biology Add Unite.AI to your preferred sources on Google Microsoft Research on September 29, 2026, introduced Quine, a research effort built around a multimodal world model of biology and an interactive harness that links the model to orchestration and reasoning models, scientific tools, the research literature, the wet lab, and the te

View original ↗

Listen: Solving all disease is one of the most monumentally complex challenges in science. Today, for the first time, AI provides the foundation to make it achievable. Tackling the frontier of human health is our mission, and it means identifying exactly where modern AI can make the greatest difference. We see drug discovery as the critical wedge in solving all disease, and therefore our initial focal point where AI

View original ↗

This work evaluates the direct transfer of a co-evolved communication protocol from a 2D simulation to a 3D physical environment, without retraining the network weights. Two e-puck-type robots, controlled by a GRU network with residual connection, were evaluated in a food-seeking task with social signaling. The sensory and motor translation layer required three corrections for stable physical operation, including the

View original ↗

A small trainable advisor can steer a frozen language-model executor using natural-language advice. In addition to learning from task rewards, the advisor can use feedback from completed interactions to improve its advice. However, a plausible correction need not change execution, yet learning from such corrections can still affect the advisor's future decisions in other contexts. In a shared-parameter model, we prov

View original ↗

From left: Dr Liang Qiyu, research fellow at the Institute for Digital Molecular Analytics and Science at NTU, and Professor Miao Yansong. Credit: NTU Singapore. Scientists at Nanyang Technological University, Singapore (NTU Singapore) have developed two artificial intelligence (AI)-powered platforms that could enable researchers to more accurately predict proteins that undergo phase separation – a process through wh

View original ↗

On-policy learning has been argued to reduce catastrophic forgetting, produce sparser parameter updates, and improve generalisation. However, existing comparisons between supervised fine-tuning and reinforcement learning vary many factors simultaneously, making the contribution of rollout policy difficult to isolate. We study the effect of rollout policy in a controlled strong-to-weak distillation setting, by indepen

View original ↗

In response to the growing demand for long sequences in agentic and reasoning use cases, many state-of-the-art LLMs combine multiple variants of attention to mitigate the quadratic complexity of traditional softmax attention. These hybrid attention LLMs aim to balance the strengths and limitations of full attention and alternatives based on recurrence. This work presents a first study of how hybrid attention impacts

View original ↗

In this review, Hasib et al. introduce EXHYTE a process centric survey to unify research on AI-assisted scientific discovery. Mapping recent studies reveals rapid advances in evidence retrieval, knowledge assembly, and idea generation, but it also reveals a persistent bottleneck in translating hypotheses into executable tests and using results to refine subsequent steps. The survey underscores the need for human over

View original ↗

Masked diffusion language models (MDMs) admit flexible generation orders, making the unmasking strategy an inference decision. Existing methods vary in how they prioritize positions, control parallelism, restrict selection regions, revise predictions, or plan future denoising, yet it remains unclear when these choices should change during generation. We study this question through strategy reversals, where an alterna

View original ↗

AI Models & Platforms Anthropic Says Claude Computed a Nine-Loop Particle Physics Amplitude Add Unite.AI to your preferred sources on Google Anthropic on September 25, 2026 published a guest post on its research site reporting that two of its physicists used the company’s Claude model to compute the six-particle scattering amplitude in planar N=4 super Yang-Mills at nine loops, answering a public challenge issued to

View original ↗

Anthropic touts AI-led biology discovery Andrew Zinin Chief Editor U.S. artificial intelligence startup Anthropic on Wednesday unveiled the first discovery from its molecular biology lab, a previously unknown enzyme system spotted by its Claude model and touted by the company as proof that AI can speed up basic research. Enzyme systems found in nature have led to some of biology's biggest breakthroughs, from the tool

View original ↗

Anthropic touts AI-led biology discovery - Anthropic's AI model Claude discovered a new enzyme system called ART by analysing DNA sequences, potentially revealing a new gene-editing mechanism similar to CRISPR. - The AI autonomously analysed over 200,000 genes in 21 hours, accelerating research that usually takes weeks or months. - The discovery, still preliminary and unreviewed, could lead to advances in gene therap

View original ↗

Retrieval-based factuality evaluation, where LLM-generated claims are verified against evidence from authoritative medical corpora, has become the dominant paradigm for scalable hallucination detection in high-stakes clinical settings. Despite the urgency of reliable and transparent medical fact verification, most systems measure performance with aggregate metrics like F1, which obscure where and why failures occur.

View original ↗

Science Sep 23, 2026 We’re introducing a new life sciences research group and laboratory at Anthropic. Our focus is on fundamental biology research using Claude: exploring datasets of DNA to identify uncharacterized protein families, generating hypotheses at scale, and testing them through experiments in the lab. This post introduces the team behind this work and shares early results in which Claude discovered a nove

View original ↗

Radical Numerics co-founder Eric Nguyen discusses genomic language models and biosecurity. He helped develop Evo and Evo 2; a separate Arc/Stanford team later used those models to generate and synthesize functional bacteriophage genomes. The interview distinguishes three sequence scales: an average human gene is about 60K, long genes can reach 2.3M, and the whole human genome is around 3B. Nguyen argues that models w

View original ↗

How often do you get to talk to a guest who has both an Academy Award and who invented textbook machine learning algorithms? John Platt has an Oscar , two textbook algorithms , two named asteroids, and an Erdos-Bacon number of 6. This was easily the most fun bio of all the guests we’ve read to date. And the result was an epic and fun chat covering Google’s Empirical Research Assistance (ERA), how AI can help battle c

View original ↗

**media[1229066]**Viva-Thera makes its public debut with four modalities pursuing HIV prevention, treatment and cure, supported by XtalPi's platform capabilities.Viva-Thera combines its first atomic-resolution MPER-TMD-CT structure with XtalPi's AI and automation platform to advance a small-molecule PCC.MPER vaccine immunogens elicit antibody levels approximately five times those of the study comparator in rhesus mac

View original ↗

This September 22 secondary report describes Anthropic’s Bay Area biology laboratory and reports plans for Claude-directed robotic experiments. In its September 23 announcement, Anthropic explicitly states that all lab work in the laboratory it describes is performed by human scientists. Claude searches genomic data, proposes candidate systems and assists analysis. The two sources differ in date and claim; the earlie

View original ↗

Rapid Oral presentation will report initial Phase I data for ISM6331 in patients with advanced solid tumors FDA Fast Track- and Orphan Drug-designated program reflects Insilico’s strategy to advance AI-designed medicines against difficult-to-treat, age-associated diseases CAMBRIDGE, Mass. — September 22, 2026 — Insilico Medicine ("Insilico"; HKEX: 3696), a clinical-stage generative artificial intelligence (AI)-driven

View original ↗

LLM agents are increasingly deployed in collaborative settings, yet long-term interaction may give rise to undesirable coordination. We study the emergence of collusion in a long-horizon multi-agent environment: two agents repeatedly complete individual tasks, share task logs, verify each other's work, and receive rewards. We introduce realistic constraints that make compliance with the verification protocol incompat

View original ↗

Alex Zhavoronkov, co-CEO of the AI drug discovery startup Insilico Medicine, dresses the same way at all his public engagements: a black padded vest with a small white badge that keeps count of the company’s clinical pipeline. When Fortune sat down with him in Hong Kong in July, he made sure to point out the badge’s latest revision: a small circle beside “Phase 3.” The badge is a provocation as much as a point of pri

View original ↗

Abstract Accurate meteorological forecasting is fundamental to public safety and economic stability, but it heavily relies on numerical weather prediction (NWP) models, whose complex outputs are often inaccessible to non-experts. Although large language models (LLMs) show potential in translating structured data into natural language to automate forecast reporting, progress has been constrained by a critical scarcity

View original ↗

Large Reasoning Models (LRMs) achieve strong performance on complex tasks but exhibit systematic inefficiency: they often overthink easy problems and underthink hard ones. Existing approaches based on uniform length penalties or rigid routing incur an efficiency tax, trading reduced computation on easy instances for accuracy loss on hard instances. We formulate efficient reasoning as an instance-adaptive computation

View original ↗

JEPA-Anything: Learning Predictive Models across Different Worlds 摘要 World modeling enables intelligence to anticipate consequences, guide interventions, and learn from interaction. Yet predictive models remain domain-specific: can a common learning principle support world modeling across radically different systems? We introduce JEPA-Anything, a domain-agnostic framework based on orthogonal predictive factorization

View original ↗

On-policy self-distillation (OPSD) lets a language model learn from a frozen copy of itself that sees an answer or a worked solution. Giving the teacher this extra information seems to offer the student more to learn, but how much does it add beyond distillation itself? To isolate that contribution, we construct AMPLE-Math, a reusable suite of 5,319 mathematical problems with six reasoning views that share the same a

View original ↗

Artificial intelligence (AI) is changing the way biomedical research is conducted by making it possible to integrate diverse types of biological data and tackle questions that were previously difficult to address. At the same time, its growing use also raises important questions about data quality, reliability, interpretability, and how computational predictions should be combined with biological knowledge and experi

View original ↗

It’s a pharmaceutical-company executive’s dream: tens of thousands of employees working day and night, uninterrupted by meals, sleep or distraction, to find the next blockbuster drug. A sophisticated artificial-intelligence system called the Virtual Biotech, which is described today in the journal Science1, is a step towards this vision. The Virtual Biotech comprises as many as 37,000 agents — AI systems that autonom

View original ↗

Spatial intelligence requires more than describing object locations. Under incomplete observation, models must identify and acquire missing evidence, interpret it in a common spatial frame, and act on it. We introduce VA-Bench to evaluate the complete observe-reason-act-revise loop. General-purpose MLLMs learn procedural context from RGB-only demonstrations, actively select camera viewpoints, issue metric Cartesian c

View original ↗

Recent Omni-Modal Generative Models (Omni-Models) have advanced content generation toward unified modeling of text, images, video, and audio. MiniMax-H3 exemplifies this transition by combining multimodal context understanding with joint audio-visual generation in a shared latent framework. Its unified architecture raises a fundamental question: Can multimodal alignment improve the model's world reasoning, and what n

View original ↗

ScienceBuddy: Recursive-in-Recursive Self-Improvement for Interactive Scientific Agents 摘要 ScienceBuddy is an interactive scientific research workspace that brings continually improving agents into a researcher's everyday work. It supports researchers in carrying out scientific tasks while turning their requests, feedback and execution evidence into tasks and evaluation rubrics for continual learning. At its core is

View original ↗

On September 8, OpenAI said 10,000 of its agents, running for 88 hours, had produced a 166-page proof regarding the Navier-Stokes equations — which describe fluid movement and have remained an open question since 1934. It's one of the seven Millennium Prize Problems established by the Clay Mathematics Institute in 2000, each carrying a $1 million prize; only one has ever been awarded. OpenAI has said it won't be clai

View original ↗

In a new series of interviews, we’re meeting some of the PhD students that were selected to take part in the Doctoral Consortium at the International Joint Conference on Artificial Intelligence and the 29th European Conference on Artificial Intelligence (IJACI-ECAI 2026) . In this first article of the series, we caught up with Yash Saxena to find out how he is trying to make it easier to understand how external knowl

View original ↗

Single-cell foundation models (scFMs) are transforming computational biology by enabling generalizable, task-agnostic representations for versatile single-cell analysis. Despite their progress in facilitating rapid deployment for downstream tasks, off-the-shelf scFMs still have some overlooked concerns: (I) (Pretraining Cost.) Pretrain-based scFMs necessitate pretraining on a vast volume of cells, rendering it draini

View original ↗

Discovery Foundation Models: Toward Open-Ended Discovery Intelligence 摘要 Foundation models have progressed from learning and reasoning over existing knowledge, to increasingly learning through action, tool use, and outcome feedback. We argue that the next frontier is a further transition: from solving and acting within problems specified by humans to participating in the process by which new problems, representations

View original ↗

PhAI Labs opened a scientist collaboration program focused first on life science and biomedicine, inviting collaborators with scientific questions, data, computational or experimental environments, and real validation conditions.

View original ↗

AutoDiscovery, our AI agent for scientific research, analyzes datasets, proposes hypotheses, runs experiments to test them, and ranks the results by Bayesian surprise—the gap between what the model predicted and what the data showed. In a University of Washington classroom this spring, it surfaced a possible flaw in how battery aging is measured, an unexpected pattern in silicon polymers, and a recurring feature in p

View original ↗

Large language models (LLMs) can generate biomedical hypotheses, but it remains unclear whether they truly reason from scientific evidence or simply produce convincing-sounding ideas. To study this, we combine three major biological databases: the Kyoto Encyclopedia of Genes and Genomes (KEGG), Rhea, and UniProt, into a unified biochemical knowledge graph and construct a benchmark of 550 paths connecting enzyme sourc

View original ↗

For drug discovery, protein-folding models such as AlphaFold have a data problem: there isn’t enough of it in public databases. Improving the performance of these artificial-intelligence-based tools will require extra data that provide examples of how proteins and drugs interact, some scientists argue. Protein structures— locked away by the thousands in drug company vaults— offer one promising source. Today, a consor

View original ↗

Digital agents must often adapt to new environments whose interfaces, tools, and failure modes are not fully captured by pretrained models. We introduce RSIAgent, a training-free multi-agent framework for recursive self-improvement through autonomous memory construction. RSIAgent coordinates curriculum, actor, and verifier agents to continually explore the environment, validate outcomes, and retain environment-specif

View original ↗

Background: Histopathological diagnoses in kidney transplant biopsies, as described by the Banff classification, suffer from substantial inter-observer variability and misinterpretation, making them prone to diagnostic errors. Continuous indices based on BanffNET automated lesion scores are proposed to quantify the continuous phenotypic spectrum of kidney transplant biopsies, complementary to pathologist assessment o

View original ↗

Can financial vision-language models (VLMs) turn chart evidence into reliable action recommendations? Existing hallucination evaluations are mostly claim-centric; they assess whether generated statements are supported, but not whether evidence remains traceable through rationale, confidence, and final action. We introduce E2A-Bench, a 969-query benchmark for financial chart reasoning, constructed from 323 HS300 const

View original ↗

When people engage in spontaneous thought under low external constraint, thought content changes continuously and can shift across topics. However, the cognitive computational principles governing these transitions remain unclear, as does whether similar dynamics emerge in artificial language generation. Here, we formalized spontaneous narrative dynamics using a foraging-inspired framework, constructing an agent base

View original ↗

I often say that I think that antibody design is one of the better use cases for AI drug discovery at present, because you start with a lot of inherent advantages: antibodies as a class are evolutionarily optimized for long plasma half-lives, and the long list of approved antibody drugs shows you that success is out there to be had. But this is a relative scale! I still believe that antibodies are one of the more rea

View original ↗

Reinforcement learning (RL) has become central to post-training of large language models. Recent advances in RL for Mixture-of-Experts (MoE) models have primarily focused on improving optimization stability and training efficiency, while treating the expert selection as a fixed component. Since routing determines the sparse computation paths that induce output distributions, expert selection offers an additional sour

View original ↗

We demonstrate that a general-purpose agent can directly drive a physical robot throughout task execution without any task-specific or environment-specific training. We introduce Agent as Policy (AGP), which places task planning and execution under the agent's control. Given a task and a robot interface, the agent interprets visual evidence, writes executable programs, issues motion commands, and revises its actions

View original ↗

Nature Computational Science, Published online: 10 September 2026; doi:10.1038/s43588-026-01049-y MutexaGPT turns plain-language enzyme-engineering intuitions into lead mutation designs through AI agent-orchestrated high-throughput molecular modeling, yielding experimentally validated improvements in enzyme specificity and cold activity.

View original ↗

Google DeepMind has created an AI-powered map of about 9 billion possible single-letter changes in human DNA, giving scientists a new way to search for genetic mutations that could matter for disease and biology. Called AlphaGenome Atlas, the platform contains precomputed predictions for every possible single-nucleotide variant in the human genome. DeepMind says testing billions of possible changes individually in la

View original ↗

Today was a tough news cycle to launch anything; we ordinarily promise to cover any new decacorn fundraises so Cognition’s $48B round and Mistral’s $24B round would normally have made it; we love imagegen so GPT Image 2.5 would have been its own headline; we covered the Dreamer story closely so their relaunch as Meta’s Muse agent should have made it; but.. yknow… the bar is higher these days. The summaries below capt

View original ↗

AlphaGenome Atlas: A predictive map of every possible DNA letter change in the human genome How predicting the molecular impact of every possible single-letter DNA variant in the human genome will help accelerate our understanding of biology. Today, we are introducing AlphaGenome Atlas: a platform (detailed in our paper) containing predictions for the effects of 9 billion single-nucleotide variants — every single-let

View original ↗

Physical equations in protein modeling appear to have been replaced by generative models trained directly on structure data. By learning a mapping from noise to data, sampling de novo protein structures has become much more efficient. However, such models can also learn non-physical features and break down with out-of-distribution settings which are typical in protein design campaigns. In this review, we highlight wh

View original ↗

Self-driving laboratories (SDLs) combine automated experimentation with adaptive decision-making to accelerate scientific discovery. Their operation nevertheless often depends on human specialists who translate scientific objectives into executable closed-loop campaigns. Specialists adjust them as data and operating conditions change. Here, we present La Agente \'Optima, an agentic framework that constructs and super

View original ↗

We investigate the best $L_2$ approximation of mixed Sobolev spaces by shallow neural networks with $n$ neurons and general activation functions. We first establish an activation-independent Fourier-block principle: if an activation has univariate approximation order $\rho$ in the sense of the Fourier-block property, then the global approximation rate has algebraic order $\min\{\alpha,\rho\}$ for target functions of

View original ↗

Across application domains, predictive signals often sit in unstructured free text rather than structured fields, yet turning that text into useful and interpretable features is difficult. Running large language models (LLMs) over an entire corpus is costly and hard to reproduce, while end-to-end text representations can rely on surface cues that are difficult to inspect. We present an agentic workflow that takes a p

View original ↗

Checking that a major mathematical proof is correct can take years. Formalization—converting the mathematical reasoning into a form computer proof assistants like Lean can verify—can help. Last month, Claude completed the first formalized proof of Fermat’s Last Theorem, one of… pic.twitter.com/pdT8zwlV4A

View original ↗

Science Sep 4, 2026 We are sharing the first complete computer-checked proof of Fermat’s Last Theorem. Claude worked largely autonomously over 11 days to write the proof in the Lean programming language. Below, we describe how the formalization was done and share some thoughts about what this work could mean for research mathematics. Around 1637, Pierre de Fermat jotted down a claim in the margin of his copy of Dioph

View original ↗

The geometric morphology of deposited filaments can significantly influence the structural performance and stability of 3D concrete-printed (3DCP) structures. However, most finite element (FEM)-based approaches for buildability assessment represent printed layers as simplified rectangles, potentially limiting predictive accuracy. This study proposes a geometry-informed modelling framework that integrates the deep-lea

View original ↗

We propose an unsupervised learning framework for calibrating a physics-augmented neural network (PANN) for small-strain viscoelasticity via full-field data. It only requires quantities that are directly accessible in real experiments for training, namely global reaction forces and surface displacements. The underlying PANN is embedded in the generalized standard materials theory, in which two scalar-valued potential

View original ↗

Artificial intelligence (AI) increasingly treats scientific literature as a data source for building databases, training predictive models, and guiding discovery. Yet literature-derived datasets often assume that reported experimental values are internally consistent and directly reusable. Here, we analyze this assumption using solid electrolyte (SE) conductivity data as a representative materials-science case. By tr

View original ↗

Classical constitutive modeling of path-dependent inelastic materials relies on internal state variables whose evolution equations must be postulated based on domain knowledge and calibrated against experimental data. However, in many practical settings, the relevant internal variables are typically not measurable in experiments, and the constitutive response must be inferred entirely from measured strain-stress data

View original ↗

Digital twin technologies could transform neuroscience and biomedicine by creating predictive computational representations of living organisms. However, most animal digital twins model neural circuits, anatomy, or biomechanics separately rather than integrating the processes that generate behavior. We argue that animal digital twins should instead be conceived as embodied dynamical systems that unify neural activity

View original ↗

Polymeric materials are central to modern technologies, with applications ranging from energy to health and transportation. Although AI has made significant advances in materials discovery, the hierarchical structure of polymers across multiple length scales makes them inherently difficult to represent in a unified and physically meaningful way. Here we introduce HiPoly, a polymer-native AI framework that processes c

View original ↗

Black-box optimization problems remain challenging because of large, weakly structured, and high-dimensional search spaces. Existing methods often suffer from poor sample efficiency because they rely on direct candidate generation or trial-and-error refinement. A natural way to improve search efficiency is to use world modeling, which can help identify promising optimization directions before costly evaluation. Large

View original ↗

Equimolar NaCa(BH$_4$)$_3$ offers a theoretical hydrogen capacity of 11.24 wt.% and a decomposition enthalpy expected to fall between those of NaBH$_4$ and Ca(BH$_4$)$_2$, but it has never been prepared and no crystal structure has been reported. Predictions for it have so far been built within the perovskite family that its heavier homologues adopt. Here that assumption is removed. Six candidate frameworks were asse

View original ↗

Accurate identification of drug-target interactions is consequential for novel drug discovery and development. Deep learning methods for drug-target affinity (DTA) prediction have shown great promise in accelerating drug discovery and reducing development costs. Although graph neural networks have improved drug representation learning for DTA prediction tasks, many models still struggle to effectively and efficiently

View original ↗

Machine learning interatomic potentials bridge the gap between quantum chemical precision and classical computational speed, enabling molecular dynamics simulations with first-principles accuracy. Their reliability is often improved through active learning, which iteratively expands the training set by identifying uncertain, out-of-distribution configurations. Existing uncertainty-quantification methods often involve

View original ↗

Powder X-ray diffraction (XRD) is central to materials characterization, yet reliable end-to-end automation remains challenging. An XRD agent must interpret diffraction evidence, operate refinement software, manage coupled parameters in a defensible order, and distinguish numerical improvement from physical validity. In this paper, we propose AutoXRD, an autonomous large language model (LLM) agent framework that orga

View original ↗

Malaria remains a significant global health burden, necessitating continuous research efforts to understand its complex molecular mechanisms, epidemiology, and potential therapeutic interventions. Extracting essential biomedical information from the vast and constantly growing malaria literature is a challenging task that demands innovative approaches. Recently, pre-trained language models have revolutionized natural

View original ↗

Computer science papers rely heavily on diagrams: architecture drawings, system flowcharts, and pipeline schematics that often carry more information than the text around them. There is currently no public dataset that pairs this specific kind of figure with captions, context, questions, answers, and step-by-step reasoning, which is exactly what is needed to train a vision-language model to understand them. We presen

View original ↗

Progress in physics has long been driven by ingenious experiments conceived by human experts. Recently, design methods driven by artificial intelligence (AI) have begun to move beyond tuning a handful of parameters to proposing entirely new experimental layouts. The discovered configurations often challenge established design conventions while matching or even exceeding the performance of human-designed set-ups. We f

View original ↗

AI can already assist with a surprising amount of scientific work: search literature, analyze datasets, write code, and generate and test hypotheses. The harder problem is building systems scientists can steer as a research project unfolds, especially when new evidence changes which hypotheses to pursue, experiments to run, or questions to investigate next. That challenge was the focus of an August 27 event at Ai2 ma

View original ↗

Scientific progress depends not only on finding solutions, but on learning the rules that explain why they work and using that understanding to design better experiments. We introduce science sandboxes, a framework for studying this capability in AI agents through repeated cycles of experimentation, feedback, and hypothesis revision. Science sandboxes invite an agent to query the natural world in different ways, rang

View original ↗

Protein co-abundance clusters preserved across tissues can reveal shared disease mechanisms and candidate therapeutic targets, particularly when proteins implicated in organ-confined diseases converge in peripheral or accessible tissues. However, previous cross-tissue studies have focused on biologically pre-selected tissue pairs, leaving most possible combinations and non-obvious relationships unexplored. We present

View original ↗

Large language model (LLM) agents are increasingly embedded in scientific workflows for literature analysis, drafting, and review. Existing systems advance autonomous discovery and manuscript generation, but do not resolve the governance problem that arises when ideas, methods, results, and claims propagate through AI-assisted workflows without mandatory human approval or artifact-level traceability. This paper propo

View original ↗

This work provides an overview of the different strategies that can be used to evaluate the performance of AI models and agents based on large language models (LLMs) for materials synthesis. After providing a brief overview of the key technologies behind the current generation of AI agents based on LLMs, we summarize the different approaches to evaluating these models in the context of materials science and in partic

View original ↗

Phage tail-like elements (PTEs) -- tailocins, bacterial type VI secretion systems (T6SS), and extracellular contractile injection systems (eCIS) -- are contractile nanomachines that bacteria use to kill their neighbors and compete within their micro-ecosystems. PTEs help shape microbial community composition. Most PTE detection tools only detect a single PTE class. Moreover, most tailocin detection methods are largel

View original ↗

At a glance - The Flash family extends GigaPath and GigaTIME with dramatically improved efficiency, making large-scale pathology research more accessible and practical. - A distilled pathology foundation model backbone reduces computational requirements without sacrificing performance, enabling repeated analyses across larger patient cohorts. - These open models support population-scale discovery, helping researchers

View original ↗

Multi-label graph learning intends to capture the intrinsic complexity of real-world applications, where one sample is often related to multiple groups or consists of multiple objects. To date, a handful of multi-label graph learning methods exist, but none of them integrate training-time interpretation capability. While post-hoc graph explainers have been developed, they do not explicitly model label-dependent evide

View original ↗

Post-training quantization is often treated as a semantically neutral optimization for edge deployment of Large Language Models. When a full-precision source checkpoint is evaluated and quantization is applied downstream without equivalent re-evaluation, this workflow creates a structural validation--deployment gap: because quantization is a many-to-one mapping over parameter space, source-precision certification doe

View original ↗

Objective To measure the accuracy of clinical coding, clinician review, and a locally deployed large language model (LLM) in identifying alcohol, drug, and self-harm involvement in emergency department (ED) attendances, and quantify prevalence. Design Two-phase diagnostic accuracy study. In a validation week, the identification strategies were assessed against a conflict-adjudicated reference standard (n=2,256); the

View original ↗

The widespread adoption of clinical large language models (LLMs) introduces significant risks of automation bias, premature closure, and clinician deskilling. Current interpretability paradigms, including latent space trajectories, Concept Activation Vectors, and Concept Bottleneck Models, suffer from topological stagnation, metric distortion, and epistemic occlusion, frequently masking intermediate diagnostic uncert

View original ↗

In this tutorial, we build an ensemble weather forecasting workflow with NVIDIA Earth2Studio. We install the required Earth2Studio components while preserving Colab’s existing CUDA-enabled PyTorch environment, load the FCN prognostic model, and retrieve atmospheric initial conditions from GFS. We then implement a custom wind-power diagnostic that converts 10-meter wind components into turbine capacity factors, along

View original ↗

As AI begins to build itself, automating alignment research becomes increasingly important to let safety research keep pace. Although measuring the success of alignment research is enormously challenging, researchers (at Anthropic and elsewhere) have developed benchmarks and automated auditing tools, such as Petri, that quantify common alignment failures, like deception, sycophancy, and jailbreaks. In one of our earl

View original ↗

Physics-Informed Neural Networks (PINNs) have recently gained considerable attention as a mesh-free framework for solving partial differential equations. Nevertheless, their performance deteriorates when applied to strongly coupled multiphysics systems, such as Biot's consolidation model, due to severely ill-conditioned optimization landscapes. In this work, we propose a robust PINN-based solver, termed FS-ENGD-PINN,

View original ↗

Scientific computing is undergoing rapid transformation as advances in artificial intelligence, heterogeneous computing, automation, and data-intensive research reshape not only computational tools but also the institutions, workforce models, and collaborative practices that support scientific discovery. This report synthesizes insights from the 2026 Workshop on Next-Generation Ecosystems for Scientific Computing, th

View original ↗

Machine learning interatomic potentials (MLIPs) have emerged as a powerful alternative to density functional theory (DFT) for molecular dynamics simulations, offering near-DFT accuracy at a fraction of the computational cost. However, many state-of-the-art MLIPs remain computationally demanding and act as black boxes, limiting physical interpretability. In this work, we evaluate the ultra-fast force field (UF$^3$) po

View original ↗

Protein language models (pLMs) encode information about protein sequences which enable downstream tasks such as structure prediction, but their internal representations are not well understood. Sparse autoencoders (SAEs) provide a promising tool to disentangle latent pLM representations into interpretable features, but existing annotation pipelines largely rely on protein-level annotations derived from database label

View original ↗

While Physics-Informed Neural Networks (PINNs) have emerged as a transformative paradigm for solving complex differential equations, their reliance on backpropagation-based gradient descent and automatic differentiation (AD) imposes significant computational bottlenecks and severe non-convex optimization challenges. To overcome these fundamental limitations, we propose the Physics-Informed Stochastic Configuration Ma

View original ↗

Nature Computational Science, Published online: 28 August 2026; doi:10.1038/s43588-026-01046-1 A large-scale experiment at a major machine learning conference shows that when researchers privately rank their own submissions, those rankings forecast future citations more reliably than peer-review scores.

View original ↗

Nature Machine Intelligence, Published online: 28 August 2026; doi:10.1038/s42256-026-01283-z Although language models can be helpful in molecular design, they are not typically calibrated for uncertainty. Rankovic and colleagues present a method to train language models while taking into account the uncertainty of the data.

View original ↗

PhysicsNeMo General Release v2.2.0 Added Adds ShardTensor support for GeoTransolver and FLARE models. Adds zarr save/load for Mesh and DomainMesh via tensordict's zarr storage backend: physicsnemo.mesh.io.to_zarr / from_zarr , with training-appropriate chunking and zstd compression. MeshReader and DomainMeshReader transparently read zarr stores alongside .pmsh / .pdmsh (opt in via pattern ). Requires optional zarr >=

View original ↗

Physics-Informed Neural Networks (PINNs) have emerged as an important class of numerical methods for solving partial differential equations (PDEs). However, during the late-stage optimization process, further parameter updates often yield diminishing accuracy improvements while increasing computational costs. To address this issue, this paper proposes a Physics-Informed Error Field Learning (PIEFL) framework for PINN

View original ↗

Synthesis planning for inorganic materials requires predicting both synthesizability and viable routes by linking microscopic thermodynamic stability with macroscopic synthesis methods, precursors, and processing conditions. Here, we develop an interpretable Physics-Informed Retrieval-Augmented Generation Language Model (PIRAG-LM) for end-to-end inorganic crystal synthesis planning. We construct a material-centered S

View original ↗

When a large language model (LLM) is asked to write a person's life, how much of what it writes actually happened? We present a scene-level case-study audit - the first quantified audit of LLM-generated autobiography against a subject-specific ground-truth corpus that we are aware of, based on an unsystematic literature search. The subject and the author of this paper are the same person: a 366-day "page-a-day" book

View original ↗

Large language models (LLMs) have shown strong capabilities in reasoning, planning, and tool use, but many scientific and engineering tasks require more than plausible text and code generation. They require understanding how a system responds to intervention, which in practice depends on controlled experimentation. In this work, we propose a multi-agent framework that enables LLM agents to conduct controlled experime

View original ↗

Messenger RNA (mRNA)-based therapeutics have emerged as a powerful platform for vaccines, protein replacement therapies, and cancer immunotherapy. A critical bottleneck in mRNA development is manufacturing large quantities of RNA economically, as measured by RNA yield emerging from an in vitro transcription (IVT) reaction. However, how promoter-adjacent DNA sequences influence RNA yield remains poorly characterized.

View original ↗

Abstract Knowledge of RNA sequences, expression, splicing, isoforms, structure and modifications is central for understanding and targeting cellular processes. Revolutionary single-cell and spatial transcriptomics technologies—for example, as deployed by consortia such as the Human Cell Atlas—partially capture this diversity and generate cellular profiles that expand at petabyte scale each year 1–5 . Yet researchers

View original ↗

On-policy distillation trains a language model on its own generations while a teacher scores them token by token. It combines the dense supervision of imitation learning with the on-policy sampling of reinforcement learning. But it requires a second, larger model to act as teacher. On-Policy Self-Distillation (OPSD) removes that cost. The teacher is the model itself, conditioned on privileged information the student

View original ↗

AI systems increasingly generate alternatives, inspect evidence, and deploy a selected output. Validation is therefore target-relative: evidence certifies deployment only in directions resolved by the interventions that produced it. We represent validation and deployment rules as kernels over a reliability surface. Their span geometry separates replication, which reduces sampling noise, from new intervention directio

View original ↗

Polyethylene (PE) is one of the most commonly used synthetic polymers. While the synthesis and processing protocols for PE are well established, precise experimental assignment of microscopic structures at atomistic resolution (i.e., the position of each atom) remains largely limited to highly crystalline systems. This gap is often addressed via computer simulations using empirical interatomic potentials, which use a

View original ↗

Developing physical neural network (PNN) hardwares is important to next generation artificial intelligence systems. Phononic devices-using heat current to encode and process information-is one of the solutions to neuromorphic computing. In this work, we back map an artificial neural network (ANN) into a PNN simulation model using polymer networked nanoparticles (PNNPs). Our atomistic simulation results demonstrate th

View original ↗

We demonstrate an iterative approach to modeling a sparsely measured magnetic field in a large-bore solenoid. This approach uses a hybrid of traditional and machine learning techniques. The traditional technique is a linear least-squares fit using a series solution to Laplace's equation, while the machine learning technique involves the training of a physics-informed neural network (PINN) on the least-squares fit res

View original ↗

High-quality molecular datasets are essential for reliable machine learning in cheminformatics and bioinformatics, yet dataset quality is rarely assessed systematically and its relationship with downstream model performance remains poorly understood. Here, we present MolJam, an open-source framework for quantitative assessment of molecular dataset quality across five dimensions-structural integrity, data quality, exp

View original ↗

Bacteriophage lytic enzymes and depolymerases are relevant to phage biology, antimicrobial development, and protein engineering, but their sequence and annotation data remain dispersed across general databases, specialized resources, genome-centred collections, and prediction-oriented datasets. We present PhageLysData, an evidence-aware and AI-ready resource constructed through reproducible multisource integration, p

View original ↗

Transport resilience work is often split across separate data preparation scripts, network models, simulation tools, image inspection systems and reports. This fragmentation makes it difficult to move from an observation to a tested and reviewable decision. We introduce ResiliFlow, an open transport world model concept and an implemented platform for infrastructure resilience, response and recovery. The platform conn

View original ↗

Neural PDE operators are increasingly trained on reusable solver archives, yet validation often relies on clean prediction error and parameter-agnostic plausibility checks. We introduce cross-parameter relinking, a data-poisoning primitive that makes a triggered input select a valid solution from the same PDE family under an incorrect physical parameter. We term this a wrong-physics backdoor: the output remains physi

View original ↗

Early thinking in the field of high entropy oxides (HEOs) emphasized their likely abundance, with combinatorial arguments hinting at a myriad of new materials. The experimental reality has proven more challenging: the stability of HEOs cannot be straightforwardly predicted based on ionic radii, lattice geometry, and charge-balancing considerations alone. In this work, we employ machine learning interatomic potentials

View original ↗

Abstract Peer review in academic research aims to ensure factual correctness and identify work of high scientific potential, but rapid submission growth has made this increasingly difficult. Here we investigate an additional measure for identifying high-impact research: authors’ rankings of their own submissions to the same artificial intelligence (AI) conference. Grounded in game-theoretic reasoning, we hypothesize

View original ↗

Scientific data acquisition continues to outpace storage and analysis capabilities, making voxel-based representations increasingly intractable. Implicit neural representations (INRs) offer a promising solution by encoding signals through coordinate-based neural networks, serving as surrogates of data, with computational and storage requirements scaling with network complexity rather than data dimensionality. However

View original ↗

Off-target cleavage is a central safety concern for CRISPR-Cas9 genome editing, particularly in therapeutic applications where unintended double-strand breaks carry clinical risk. We benchmarked five machine learning classifiers: logistic regression on mismatch-count summary features, a random forest and a gradient boosting model on one-hot-encoded sgRNA/candidate-site sequence pairs, a one-dimensional convolutional

View original ↗

Objective Translating free-text clinical trial criteria into computable code sets is a valuable standardization practice that is necessary for producing reproducible real-world evidence studies but requires standardized interpretation across multiple clinical vocabularies. Methods We developed TrialCode Agent, a hybrid-large language model (LLM)-terminology verification agent that generates, formats, verifies, and ex

View original ↗

Accurate computational prediction of enzyme function, standardized by Enzyme Commission (EC) numbers, is essential for large-scale genome annotation and generative enzyme design. However, it remains unclear whether state-of-the-art predictors learn the intrinsic structural determinants of catalytic activity or merely rely on global sequence similarity to annotated homologues. To address this gap, we introduce EnzymAR

View original ↗

The 35th International Joint Conference on Artificial Intelligence and the 29th European Conference on Artificial Intelligence (IJCAI-ECAI 2026) named three distinguished papers. One paper, titled "Approximate Strategyproofness in Approval-Based Budget Division" by Haris Aziz et al., proves that the Nash product rule (NASH) has an incentive ratio of 2, thereby circumventing the impossibility theorem by Brandl et al.

View original ↗

The high photon flux at synchrotron beamlines allows for the measurement of fast dynamical processes. However, beamline radiation-safety protocols prohibit human intervention during X-ray experiments, limiting the ability to perform versatile real-time sample manipulations during continuous data acquisition. Here we present a robotic platform at an X-ray scattering beamline to enable real-time sample handling and pro

View original ↗

This survey proposes viewing agent evolution as dynamic graph transformation, modeling agent state as a dynamic graph where memories, tools, skills, workflows, and inter-agent relations are represented as typed nodes, edges, and subgraphs updated through schema-constrained rewrites. The authors organize existing dynamic-graph-based methods for self-evolving agents into four taxonomies: node/feature evolution, edge/to

View original ↗

Microsoft Research's Skala 1.1 demonstrates the continuous improvement of their deep-learning DFT approach. Trained on 2.5× more data than its predecessor, it delivers substantially higher accuracy across key molecular simulation challenges, including thermochemistry, reaction kinetics, and molecular structure prediction. Skala is now available in CP2K and is being integrated into Psi4, FHI-aims, ORCA, and VASP, brin

View original ↗

Nature Computational Science, Published online: 20 August 2026; doi:10.1038/s43588-026-01035-4 As large language models begin to plan and run experiments on their own, the reflex is to demand that they be interpretable before they are trusted. We argue that what grounds trust in autonomous science is not a view inside the model; it is provenance: a complete, re-openable record of what was reasoned, done and measured

View original ↗

MemTrapBench is a new benchmark for evaluating cognitive traps in large language model (LLM) memory use. Existing memory benchmarks mainly assess whether information is correctly extracted, stored, and retrieved, but overlook how retrieved memories reshape model reasoning and affect current task performance. MemTrapBench covers two forms of cognitive traps: Reasoning Fixation and Belief Distortion. Experiments across

View original ↗

Missense mutations and post-translational modifications (PTMs) are major molecular perturbations that reshape protein function but are traditionally studied independently. Current computational approaches largely rely on sequence conservation or static structural features, limiting our understanding of how perturbations alter intrinsic protein dynamics. We present DynGeo-Pheno, a unified geometric deep learning frame

View original ↗

In this episode of AI Pioneers, Cynthia Rudin, a pioneer in interpretable machine learning and winner of the 2022 Squirrel AI Award, discusses her work on black boxes and Rashomon sets. She recounts her early project with Con Edison on the NYC power grid, where black-box models failed and simple interpretable models outperformed them. Rudin argues that for high-stakes problems like loan decisions or crime prediction,

View original ↗

This work proposes a new interpretable neural operator framework, termed the Physics Informed Kernel Function Neural Operator (PIKFNO), which explicitly incorporates physics informed kernel functions derived from governing equations into the neural operator architecture. Unlike traditional neural operators such as DeepONet, which rely on deep networks to implicitly learn basis functions, PIKFNO constrains the trunk n

View original ↗

This article investigates physics-informed and hybrid machine learning strategies that incorporate physics knowledge into experimental data-driven deep-learning models for predicting bond quality and porosity of fused filament fabrication (FFF) parts. Three strategies are explored: incorporating physics constraints into the loss function, using physics model outputs as additional inputs, and pre-training with physics

View original ↗

We address the inverse problem of reactive transport in heterogeneous porous media, where unknown model parameters must be inferred from sparse experimental observations. The problem is complicated by strong nonlinearities, spatial heterogeneity, and limited data availability. We propose a Conditioned-on-Design Bayesian Physics-Informed Neural Network (CoDe-BPINN), which combines a domain-decomposed PINN solver with

View original ↗

This paper investigates physics-informed machine learning strategies for global sensitivity analysis (GSA) when both a physics-based model and experimental observations are available. Two machine learning techniques, deep neural networks (DNN) and Gaussian process (GP) modeling, are considered, and two strategies for incorporating physics knowledge are explored: enforcing physics constraints via loss functions, and p

View original ↗

Reward modeling for joint video-audio generation typically combines metrics for audio quality, visual fidelity, and synchronization, which evaluate perceptual dimensions separately and fail to capture the overall semantic and temporal coherence among text, video, and audio, encouraging reward hacking. To address this, the authors construct a large-scale human-preference dataset VAPref-10K with 9K prompts and 10.3K fi

View original ↗

Training terminal agents requires scalable executable supervision, yet synthesizing high-quality terminal tasks is challenging. Each task couples an instruction, an initialized environment, a reference solution, and an executable verifier; inconsistent assumptions can make tasks unsolvable or mis-evaluated. Multi-stage synthesis may discard original goals, dependencies, state transitions, and procedural constraints.

View original ↗

Abstract Background: Cardiovascular-kidney-metabolic (CKM) syndrome is an increasingly prevalent multisystem condition associated with morbidity, fragmented care, recurrent hospitalization, and rising healthcare costs. While cardiovascular risk models estimate future disease risk, fewer frameworks support multidisciplinary CKM care, clinician decision-making, and population health management. Synthetic data environme

View original ↗

This work presents a machine learning-symbolic regression (ML-SR) strategy to develop a physically interpretable formula for predicting low pressure CO2 adsorption capacity in hypothetical metal-organic frameworks (hMOFs). Four ML models were trained on a small dataset of 1,000 samples, and five key descriptors—largest cavity diameter, pore limiting diameter, void fraction, gravimetric surface area, and number of hyd

View original ↗

Automated structure elucidation from routine spectroscopy remains a major challenge. Researchers introduce MACROS, a multi-agent system that emulates expert iterative hypothesis testing. Trained on 100 million simulated and 1.6 million experimental spectra-molecule pairs, it natively supports arbitrary combinations of routine spectroscopic techniques and achieves unprecedented zero-shot generalization to diverse real

View original ↗

Large language models (LLMs) are increasingly evaluated and used in medicine, but clinical usefulness depends on answer accuracy and whether confidence tracks evidence quality and uncertainty. We developed a controlled, psychophysics-inspired clinical benchmark to test diagnostic choice and confidence behavior in a medical LLM. The benchmark focused on probable Alzheimer-type neurocognitive disorder (AT-NCD) versus d

View original ↗

AI efficiency has recently taken the spotlight in both academy and industry due to massive model scales, high energy demands, and environmental costs. While reporting Floating Point Operations (FLOPs) is a traditional approach for assessing computational costs, the relationship between FLOPs and execution time is not straightforward, as layers with the same number of FLOPs may not have the same execution time because

View original ↗

We introduce Semantic Task Completion Video Generation, an outcome-oriented task requiring both the achievement of the intended outcome and semantic grounding, which characterizes the correspondence between the reference image and the generated outcome in terms of high-level task-relevant semantics. Evaluation focuses on the generated outcome and does not require a complete sequence of intermediate steps or appearanc

View original ↗

Florent Delgrange won the Best Blue Sky Paper Award at AAMAS 2026 for his work 'Foundation World Models for Agents that Learn, Verify, and Adapt Reliably Beyond Static Environments.' The paper proposes a research agenda that merges reinforcement learning and reactive synthesis into a single loop: a foundation world model is learned from experience but structured for a verifier to reason about. As the agent learns a p

View original ↗

In offline reinforcement learning, estimating the optimal action-value function Q* can be formulated as solving the optimal Bellman equation based solely on offline observations. A fundamental challenge is that the reward function and transition kernel are unknown, so the optimal Bellman operator is not directly observable. To address this, we propose a novel framework that decouples operator estimation from value fu

View original ↗

Machine learning is rapidly reshaping constitutive modeling, offers new ways to learn material behavior directly from experimental data, and challenges long-established modeling paradigms. But with a growing number of machine-learning-based approaches available, how do they compare in practice? In this paper, we use the classic experimental data of Treloar to benchmark popular frameworks for hyperelasticity: (General

View original ↗

Natural language offers robots a flexible task interface, but target ambiguity in embodied environments arises not only from user intent; it can also result from missing task-relevant physical evidence in the current observation. Existing interactive disambiguation methods primarily obtain additional information by asking the user, whereas occlusion, restricted viewpoints, unreadable text, and unobserved targets requ

View original ↗

We present RapidLiDAR, a LiDAR scene completion method that treats initialization as a learned, data-driven component. An adaptive initialization module predicts spatially varying displacement for each partial input point, avoiding manual noise tuning. A multi-scale reconstruction module refines point positions using voxel and BEV feature maps. On SemanticKITTI and KITTI-360, our method achieves state-of-the-art comp

View original ↗

AlphaFold3 (AF3) predicts protein-complex structures from sequence with near-experimental accuracy on many targets, substantially lowering the cost of mechanistic and therapeutic discovery. However, application to antibody epitope prediction is hampered by an approximately 63% failure rate. Comparing successful and failed AF3 predictions across antibody-antigen and nanobody-antigen complexes, we found that failed pre

View original ↗

Reliable uncertainty quantification (UQ) is essential for deploying large language model (LLM) agents in complex interactive environments. Existing UQ methods often rely on local signals, such as token probabilities or predictive entropy, overlooking long-range dependencies where errors accumulate across an execution trajectory. We propose RUPA, a trajectory-level UQ framework that represents an execution history as

View original ↗

Objective: Erythropoietic protoporphyria (EPP) is a rare photodermatosis marked by multi-year diagnostic delays. We developed and externally validated machine learning models to identify patients with EPP earlier from longitudinal electronic health record (EHR) data and estimate undiagnosed disease burden. Materials and Methods: In a retrospective case-control study at two San Francisco health systems, an academic re

View original ↗

Embodied agents are increasingly used to close the gap left by end-to-end policy models, but existing harnesses remain largely open-loop, reflecting only after episodes, which cannot govern real-time physical interaction. We present Zetta, a closed-loop embodied harness that evolves code-based runtime critics and recovery skills online while keeping the base policy frozen. Through three timescale-separated loops, Zet

View original ↗

Generative artificial intelligence is accelerating molecular design, yet the relative suitability of available models for different targets and stages of preclinical drug discovery remains unclear. Here we benchmarked 12 molecular generation and optimization methods across 176 curated protein ligand systems spanning diverse therapeutic target classes, with experimentally validated ligands providing reference chemical

View original ↗

Looped language models have shown promising results on reasoning benchmarks, yet their potential for agentic tool use remains largely unexplored. We study this question in compositional tool-calling settings, where models must coordinate multiple API calls, maintain intermediate state, and preserve dependencies across tool interactions. We evaluate native and retrofitted looped language models on API-Bank, BFCL, and

View original ↗

MathCode converts natural-language mathematics problems into Lean 4 theorem statements and attempts formal proofs. Its public project combines a persistent Lean REPL, reusable theorem and axiom libraries, agentic proving, parallel subgoal trees and an Obsidian theorem graph.

View original ↗

Synaptic vesicle glycoprotein 2C (SV2C) is a vesicular protein enriched in dopaminergic neurons of the basal ganglia that modulates dopamine storage and release, and its disruption is implicated in Parkinson's disease (PD). Despite strong genetic and pathological links to PD, there are no selective small-molecule probes for SV2C. Here, we describe an AI-enhanced virtual screening (VS) and experimental campaign that i

View original ↗

Prime Intellect ran 153 internet-isolated autonomous runs across 18 frontier models on the nanoGPT optimizer speedrun, releasing the traces, monitor reports, per-run ledger and harness.

View original ↗

Scientific discovery often involves optimizing expensive-to-evaluate objectives over vast, structured, and open-ended hypothesis spaces, such as molecules, protein sequences, and computer programs. Generative models like large language models (LLMs) provide expressive priors, but their likelihoods and self-assessments are unreliable for objectives and calibrated epistemic uncertainty, especially for novel candidates.

View original ↗

Codon optimization uses synonymous sequence changes to improve the expression and therapeutic performance of nucleic acid-based medicines. Masked language models (MLMs) have recently been proposed as alternatives to traditional, frequency-based codon optimization approaches, yet whether they offer a meaningful advantage over such simpler methods remains unclear. Here we benchmark three prominent MLMs --- CaLM, EnCodo

View original ↗

Drug discovery (DD) is a complex, time-consuming, and resource-intensive process that involves the identification of therapeutic targets, selection of bioactive compounds, and extensive experimental validation. The discovery of promising therapeutic compounds from large libraries of phytochemicals and synthetic molecules remains a major challenge in modern drug development. Screening millions of compounds through con

View original ↗

The rapid advancement of artificial intelligence has substantially increased the demand for large-scale datasets; however, available datasets remain insufficient for data-intensive tasks, particularly in nuclear medicine. While large-scale datasets exist for computed tomography (CT), few provide paired projection-domain and image-domain data across diverse lesion types. This issue is more pronounced for positron emis

View original ↗

Arc Institute’s Patrick Hsu on Building an App Store for Biology with AI Patrick Hsu, co-founder of Arc Institute, discusses the opportunities for AI in biology beyond just drug development, and how Evo 2, their new biology foundation model, is enabling a broad ecosystem of applications. Evo 2 was trained on a vast dataset of genomic data to learn evolutionary patterns that would have taken years to find; as a result

View original ↗

Nature Methods, Published online: 14 August 2026; doi:10.1038/s41592-026-03138-2 Direct preference optimization (DPO) aligns a pretrained protein language model with experimental stability data, yielding ProteinDPO, a model that scores and generates thermostable protein sequences. Applied to H5N1 influenza hemagglutinin, it achieved large improvements in thermal stability of hemagglutinin while preserving antibody re

View original ↗

Open-weight language models are often fine-tuned, quantized, pruned, or merged without documented provenance. We propose a data-free, white-box method for lineage verification: by removing the identity-aligned component that residual training imparts to branch products, we isolate checkpoint-specific structure across residual blocks and compute a symmetric lineage score. On residual-MLP and GPT-2 benchmarks, the scor

View original ↗

Nature Methods, Published online: 14 August 2026; doi:10.1038/s41592-026-03137-3 This Article demonstrates that direct preference optimization (DPO) can be used to effectively align an unsupervised structure-conditioned language model with biophysical information. The aligned model, ProteinDPO, achieves stability prediction competitive with that of task-specific models and consistently outperforms unsupervised and fi

View original ↗

High-quality creative writing data for LLMs is dominated by story-centric data, limiting models' adherence to diverse creative formats. The authors propose an attribute-guided genre expansion framework that uses human-authored story prompts as creative seeds and manually curated genre attributes to enforce structural, stylistic, and formatting conventions. This produces genre-faithful query-response pairs, which are

View original ↗

UNIVERSITY PARK, Pa. — Artificial intelligence could dramatically accelerate the search for technologies that transform carbon dioxide into useful fuels, but a new multi-laboratory study shows that even the most advanced model can be undermined by something as simple as inconsistent stirring. Researchers from four U.S. laboratories have demonstrated that experimental variability can substantially alter measurements o

View original ↗

V-RAE is a video representation autoencoder that builds compact generative latents on top of frozen vision foundation model representations. A lightweight temporal pooling module removes temporal redundancy while preserving semantic structure, and a video decoder reconstructs continuous motion from compressed features. On K600, V-RAE achieves an rFVD of 2.13, outperforming all evaluated large-scale pretrained video V

View original ↗

For the sake of anyone who might read this blog post in the distant future (a month from now, say), let me mention that I am writing it a few days after OpenAI announced that it had solved ten major problems in mathematics and theoretical computer science, including the first construction of a non-sofic group, and a proof that the multicolour Ramsey number (where there are 3’s) grows superexponentially in . The first

View original ↗

Microsoft Research introduces CARE-X, a unified chest X-ray vision-language model (VLM) designed for diverse clinical interpretation tasks. It combines free-text generation with structured prediction to provide both narrative reports and deterministic outputs. The model uses reinforcement learning (DAPO) to reward clinical correctness in a multi-task setting. In a separate research experiment, the team paired Qwen3-V

View original ↗

By 2050, antibiotic-resistant infections could be associated with over eight million deaths annually worldwide. Developing new antibiotics is slow and costly, but generative AI models, guided by scientists, can propose novel molecules, and physics-based simulations can quickly assess their potential as drugs. Peptides like insulin and vancomycin serve as important starting points. A good AI model includes a generator

View original ↗

An important article by field experts points out that despite widespread AI application in drug discovery, evidence of clinically relevant impact remains 'disappointingly limited'. They conclude we are at a stage of 'absence of evidence', not necessarily 'evidence of absence'. Desired outcomes like better decision-making in selecting disease areas, targets, lead molecules, and trial designs are among areas current AI

View original ↗

Nature Computational Science, Published online: 10 August 2026; doi:10.1038/s43588-026-01018-5 A newly generated high-throughput experimentation (HTE) dataset is integrated with open-source data to produce a large and high-quality Buchwald–Hartwig reaction dataset for training machine learning models. The combination of HTE and active learning enabled the development of a robust machine-learning model with reliable o

View original ↗

A joint study by Insilico Medicine, the University of Copenhagen, and academic partners identifies NDRG1 as a key regulator of DNA damage repair, demonstrating that targeting this pathway via the antimalarial drug quinacrine triggers synthetic lethality in specific cancer subtypes. Insilico Medicine (HKEX:3696, "Insilico"), a clinical-stage biotechnology company pioneering generative artificial intelligence (AI) for

View original ↗

Terence Tao discusses the Heil-Ramanathan-Topiwala (HRT) conjecture, which asserts that a nonzero function with reasonable decay cannot satisfy a finite linear relation among its time-frequency shifts. He notes that the conjecture holds when all shifts are frequency shifts or collinear. For the lattice case, commutativity allows a diagonalization that reduces the relation to a pointwise equation, using restrictions t

View original ↗

Artificial intelligence has significantly expanded candidate generation in drug discovery, but selecting optimal compounds under real-world experimental constraints remains a major bottleneck. This review examines quantum annealing as a potential downstream optimization layer within hybrid computational workflows. By focusing on constraint-dominated decision tasks formulated as quadratic unconstrained binary optimiza

View original ↗

In healthcare settings, LLM performance differs between evaluation and deployment, with a recent study finding a 61 percentage point gap. The authors argue this gap arises not from poorly designed benchmarks but from implicit assumptions in evaluation protocols that fail at deployment. They propose a taxonomy categorizing assumptions into task and outcome types to diagnose where the gap arises and what is needed to c

View original ↗

OpenAI released ten results on long-standing problems together with human-prepared manuscripts and Lean certificates.

View original ↗

Image credit: José Neiva Mesquita-Neto Understanding Pollination Through Ecological Function Pollination is one of the most important ecological processes on Earth, but understanding how different insects contribute to it remains surprisingly difficult. While many bee species visit flowers, they do not all transfer pollen. Distinguishing between different ecological functions has traditionally required labor-intensiv

View original ↗

Tao, 51, an Australian and American mathematician recognized for his contributions to partial differential equations, combinatorics, harmonic analysis, and additive number theory, made the remarks in his lecture, "Mathematics in the Age of AI," delivered at the International Congress of Mathematicians (ICM) last weekend. His speech drew widespread attention from the global mathematics community. He began by reflectin

View original ↗

The OlmoEarth Platform: Geospatial inference at planetary scale July 28, 2026 Ai2 The OlmoEarth models are our family of Earth observation foundation models, pretrained on roughly 10 terabytes of multimodal satellite data. Governments, NGOs, and other mission-driven organizations are already adapting OlmoEarth for applications including deforestation monitoring, food security, and wildfire risk. At Ai2, we know how t

View original ↗

Researchers at ISTA and international collaborators have developed a method to guide AlphaFold with experimental data, enabling the modeling of protein structure ensembles that better reflect physical and biological reality. Although AlphaFold predicts protein 3D structures with remarkable accuracy, it tends to reduce heterogeneous structures to a single dominant conformation and overlooks experimental conditions aff

View original ↗

As AI becomes critical infrastructure for science, medicine, industry, and government, one question matters more than ever: who gets to understand how these systems work? At Ai2, that question is central to our work, and it’s what motivates our commitment to open science and open models. For us, openness is more than a licensing choice—it shapes how we build, release, and evaluate our work. Open-weight models let peo

View original ↗

Accelerating the frontiers of scientific discovery: Google’s $40M commitment to the Genesis Mission Pushmeet Kohli VP for Science and Strategic Initiatives, Google DeepMind, and Chief Scientist, Google Cloud Karthik Narain Chief Product and Business Officer, Google Cloud Google AI for Public Sector Empowering an Adaptive, Responsible, Secure, and Intelligent way forward Learn more Scientists today face challenges of

View original ↗

In April 2026, a NASA Artemis II photo of Earth caught public attention, but AI can fabricate similar images in seconds, raising trust issues. The author, a visual science communication researcher, notes that AI-generated images infiltrate science: used for illustrations, synthetic data, editing lab images, and outreach, blurring lines between illustration, enhancement, and fabrication. In 2024, two papers were retra

View original ↗

The notorious Jacobian conjecture can be formulated concretely over the complex numbers as follows. Conjecture 1 (Jacobian Conjecture) Let be a polynomial map in complex variables, whose Jacobian is a non-zero constant. Then is invertible (with polynomial inverse). The condition that the Jacobian is non-zero is equivalent to being locally invertible. (The implication of local invertibility from non-vanishing Jacobian

View original ↗

AI-guided protein design was experimentally tested as a way to improve the efficiency and targeting range of compact base editors.

View original ↗

The work audits AI protein structures at the level of electrostatic interactions, beyond aggregate structure scores.

View original ↗

AI-assisted fragment prioritization was connected to NMR and X-ray evidence rather than evaluated only in silico.

View original ↗

Abstract Elucidating reaction mechanisms requires efficient generation of transition states (TSs) and products. Existing diffusion and sequence-based models accelerate parts of this process over traditional string-based methods, but typically still require manual enumeration of either TSs or products, and stochastic diffusion dynamics can be inefficient and hard to control. We introduce MolGEN, a conditional flow-mat

View original ↗

AlphaGEM uses structural information and deep learning to fill gaps in genome-scale metabolic models.

View original ↗

Fluorescent proteins and small-molecule dyes offer complementary advantages for biological imaging: Proteins are amenable to genetic tagging, whereas dyes provide superior brightness and photostability. To combine these strengths, we used de novo protein design to generate small, nanomolar-affinity, high-selectivity binders (NovoTags) for three cell-permeable dyes spanning the visible spectrum. We show that the NovoT

View original ↗

Conjecture Machines: AI agents and the new validation bottleneck in science Over the past year, agents have transformed what it means to code. Scientific research may be next — from proposing novel hypotheses, to designing experiments, to discovering algorithms that improve on the best that humans have designed. This raises urgent questions for policymakers and science funders, the biggest being how to validate the c

View original ↗

SemiEpi connects a physics model, in-situ sensing and immediate feedback to control molecular-beam epitaxy.

View original ↗

Machine learning (ML) is rapidly moving from the margins of research into the centre of weather forecasting. Only a few years ago, ML models were largely experimental tools, tested alongside traditional numerical weather prediction (NWP) systems. Today, ML is becoming an increasingly important component of operational forecasting systems, complementing established numerical weather prediction. The potential is signif

View original ↗

“I have this idea of a communal brain.” David Baker, PhD, told me as I sat in his office at the University of Washington (UW) surrounded by colorful and complex figurines of protein structures. It was the one-year anniversary of his Nobel Prize in Chemistry win. Just outside his doors, a lab of more than 100 researchers was united by the shared ambition to design proteins from scratch (or de novo) for powerful applic

View original ↗

A generative system performs inverse design for information metamaterials, linking learned representations to physical objects.

View original ↗

Universal machine learning force fields (UMLFFs) promise to revolutionize materials science by enabling rapid atomistic simulations across the periodic table. However, their evaluation has been limited to computational benchmarks that may not reflect real-world performance. Here we introduce UniFFBench, a comprehensive evaluation framework featuring the MinX dataset-a diverse collection of 1,500+ mineral systems span

View original ↗

How Rust, Lean, Aeneas, and AI agents are helping scale formal verification for production cryptographic algorithms At a glance SymCrypt develops new verified cryptography using Rust, Aeneas, and Lean to provide higher security assurance. We prove that their code safely and correctly implements standard algorithms, notably for post-quantum cryptography. We are releasing verified code, specs, properties, and proofs in

View original ↗

Stanford GSB professor Douglas Guilbeault argues that human decision-making often relies on 'satisficing'—gathering just enough information to make a satisfactory prediction, rather than seeking optimal solutions. Experimental games show this strategy also applies to learning social rules, offering new insights into social learning and highlighting a key difference between humans and large language models (LLMs). LLM

View original ↗

In a 25-dimensional, 528-run closed-loop experiment, expert chemists and LLMs were compared directly, producing a useful mixed result for AI-scientist claims.

View original ↗

I have been interested in machine-assisted ways to do and teach mathematics from as far back as 1999, when I started coding several applets in Java 1.0 , both for my complex analysis and linear algebra courses, as well as to visualize various mathematical objects I was interested in (such as honeycombs or Besicovitch sets). This was moderately successful; but the applets were time-consuming to program. Eventually, th

View original ↗

Herein, we combine Bayesian Optimization and mechanochemistry to develop a rapid, solvent-free protocol for the Johnson–Corey–Chaykovsky (JCC) cyclopropanation and epoxidation. By prioritizing efficiency and sustainability, Machine Learning quickly identified a new set of reaction conditions for this venerable reaction that diverge from established paradigms (explosive NaH/DMSO system), revealing that these transform

View original ↗

NicheTrans uses spatial context to translate between omics modalities and preserve tissue heterogeneity.

View original ↗

Biomni integrates tool retrieval, code execution and experimental protocols across biomedical tasks in a single agent environment.

View original ↗

Croonian Prize Lecture: Advances in computational protein design Join us for the Croonian Prize Lecture delivered by Dr David Baker. The Croonian Medal and Lecture 2026 is awarded to Dr David Baker for pioneering the design of completely new proteins as well as playing key roles in the development of protein structure prediction and protein engineering tools. Proteins mediate the critical processes of life and beauti

View original ↗

Image credit: Mantis Design / Adobe Stock The Growing Challenge of Biodiversity Data Citizen science projects are generating more data than ever before. Global biodiversity databases now contain millions of species observations , creating an incredible resource for ecological research. While collecting the data is not a problem, researchers still need to analyze the sounds hidden within thousands or even millions of

View original ↗

Token-level hallucination detectors that score each token independently often fail when the model is confidently wrong. This paper treats hallucination as a temporally extended span and frames detection as sequence labeling. Each token is scored from a 33-dimensional feature stream that fuses text statistics, Natural Language Inference (NLI) entailment, and language model surprisal, with no access to model internals.

View original ↗

LifeSciBench evaluates models on research tasks designed with life scientists rather than relying on generic knowledge questions.

View original ↗

Aviv Regev is a computational biologist who leads Genentech Research and Early Development. Previously a professor at the Massachusetts Institute of Technology and a leader at the Broad Institute of M.I.T. and Harvard University, her research has advanced single-cell genomics, systems biology and large-scale efforts to map human cells. [This interview was edited for length and clarity.] How would you describe the cur

View original ↗

In the journal Cell , a team of >80 researchers from 4 continents reported on the discovery of a 14-protein blood test which paved the way for predicting and preventing lung cancer more than 5 years before it would be diagnosed. Current efforts in cancer are largely directed to therapy and early detection, with only a very limited foray to prevention. In a recent Ground Truths , I reviewed the emerging potential for

View original ↗

Astrophysicist Chi-kwan Chan used Codex to derive, implement and test candidate algorithms for Event Horizon Telescope simulations.

View original ↗

Share - Findings from insitro’s lead therapeutic CTRO-1013 program demonstrate that liver-targeted silencing of IRS1 lowered circulatory biomarkers associated with fibrosis progression and hepatocyte injury in an industry-standard fibrogenic preclinical mouse model of MASH - Data presented today at ADA provide converging evidence from human genetics and preclinical models supporting IRS1’s effect on liver fat and liv

View original ↗

Science Jun 8, 2026 Written by Laura Luebbert. Based on research by Ferdous Nasri, Sarah Gurev, Patrick Varilly, Krithik Ramesh, Nuala A. O’Leary, Jonah Cool, Bernhard Y. Renard, Pardis Sabeti, and Laura Luebbert. In this post, Laura Luebbert argues that we need to make biological data infrastructure more agent-friendly. As a case study, she and her team tasked scientific research agents (Claude, Biomni Open Source (

View original ↗

REDWOOD CITY, Calif., May 27, 2026 – Biohub today announced the release of a world model of protein biology: a scientific engine for prediction, design, and discovery that can map proteins across the tree of life, predict their structures, and design new protein binders that function in laboratory experiments. Proteins are the machinery of life. Nearly every function of the human body depends on them. They are among

View original ↗

De novo Generation for Molecular Structure Elucidation from Mass Spectrometry - Runzhong Wang | MIT - Microsoft Research New England Generative Modeling & Sampling Seminar Recent advances in generative AI are enabling new approaches to scientific discovery in chemistry and biology. In this talk, we present DiffMS and FRIGID, two generative AI frameworks for de novo molecular structure elucidation from tandem mass spe

View original ↗

OpenAI scored a big result yesterday, with respect to an Erdos problem: Clearly impressive. But as with so much else, it should be viewed with skepticism. In an email to me this morning, Cal Newport made a number of good points that he said I could share, summarizing both what was found and some limitations: OpenAI used a new reasoning model (not yet released) to help identify a counterexample that disproved a conjec

View original ↗

I’m organizing a workshop in London on July 6th to 10th (2026) whose goal is to work on my EPSRC-funded project formalizing Fermat’s Last theorem in Lean. The initial aim of the project was to reduce FLT to theorems known in the 1980s, i.e. “formalize the Wiles/Taylor–Wiles papers” (although actually we are formalizing a more modern proof whose ideas go back to a strategy proposed by Khare). I have just finished givi

View original ↗

Machine learning (ML) models have become an increasingly important component of the global weather forecasting landscape. Over the past few years at ECMWF, several externally developed models have been run alongside the Integrated Forecasting System (IFS) in an experimental setting, allowing their performance to be assessed against established numerical methods. The upgrade of the IFS to Cycle 50r1 has provided a tes

View original ↗

Demis Hassabis, CEO of Google DeepMind and 2024 Nobel laureate in Chemistry, has spent the first months of 2026 articulating a specific and measurable thesis: AlphaFold, the protein-structure model that now serves more than three million researchers across 190 countries, is the first rung in an AI-powered scientific revolution, not the last. His clearest statement of this position came in a Semafor interview publishe

View original ↗

Google DeepMind presents an agentic system designed to collaborate with research mathematicians on open-ended problems.

View original ↗

Terence Tao argues that generating and verifying proofs is still incomplete until results are digested and connected to the field.

View original ↗

In a Nature interview, Tao separates current research usefulness from hype and explains the growing role of formal verification and human judgment.

View original ↗

Jùn Zhang and Carina Hong discuss translating mathematics into Lean, formal proof, mathematical intuition and building an AI-for-math company.

View original ↗

Image credit: Elianne Dipp / Pexels Over the last decade, work on animal communication has reached a convergence as the growing availability of large-scale behavioral and bioacoustic data merges with relatively recent advances in machine learning. As a result, we’re starting to see the study of animal communication shift from narrowly defined, species-specific, and hypothesis-limited analyses toward data-driven disco

View original ↗

Tanya Klowden and Terence Tao examine how AI and formalization may change the purpose, practice and social role of mathematics.

View original ↗

Share Amyotrophic Lateral Sclerosis (ALS) presents one of the most formidable challenges in medical science. For too long, the search for effective treatments has been hampered by a temptation to revisit familiar hypotheses and established biological pathways. While understandable given the slow progress and frequent setbacks, this approach rarely advances the science. At the heart of insitro’s collaboration with Bri

View original ↗

OpenAI’s GPT can summarize research papers and make predictions—but can it do science? Can it generate hypotheses, design experiments, interpret results and iterate? Last summer researchers at OpenAI and Ginkgo Bioworks, a company that designs and installs autonomous, robot-run labs, decided to find out. Though artificial intelligence systems have posted high scores in math, physics and computer science, biology is h

View original ↗

"AI Has Overwhelmed Human Exam Questions," A Conversation Between Terence Tao and Mark Chen: Large Language Models Are No Longer "Math Underachievers" Recently, at a seminar hosted by the Institute for Pure and Applied Mathematics (IPAM), Fields Medalist Terence Tao and Mark Chen, the Chief Researcher at OpenAI, participated in a "fireside chat." The two discussed the leap - forward progress of AI in the past year an

View original ↗

Climate scientist Zeke Hausfather documents a live AI-assisted modeling workflow, including a plausible wrong answer caught by domain expertise.

View original ↗

Optimizing molecules to achieve desired properties is a central bottleneck across the chemical sciences, particularly in the pharmaceutical industry, where it underlies the discovery of new drugs. Since molecular property evaluation often relies on costly and rate-limited oracles, such as experimental assays, molecular optimization must be highly sample-efficient. To address this, we introduce SEISMO, an LLM agent fo

View original ↗

Share AI-enabled brown adipose tissue (BAT) phenotype unlocks population-scale human genetic discovery BAT-01 knockdown drives 15% body-weight reduction in preclinical models through peripheral adipose beiging, preserving lean mass Key findings presented at the Keystone Symposia on Obesity Therapeutics SOUTH SAN FRANCISCO, Calif. – Feb 2, 2026 – insitro, the AI therapeutics company built on causal biology, today repo

View original ↗

Epoch AI released a pilot of 14 research-level open problems with programmatically checkable answers to test the frontier beyond existing benchmarks.

View original ↗

Share The primary driver of clinical attrition in drug discovery is often not insufficient scientific rigor, it is misalignment between the biological target and the therapeutic intervention. Discovery organizations have historically structured themselves around technological capabilities, operating as either small molecule, biologics, or oligonucleotide specialists. This specialization creates an underappreciated co

View original ↗

insitro announced it will acquire CombinAbleAI and, alongside the deal, has launched TherML (Therapeutic Machine Learning), a platform it describes as a single, modality-agnostic AI engine for drug discovery and design. The deal is expected to close in late January 2026 and is intended to expand insitro’s capabilities beyond its existing small-molecule and oligonucleotide work into antibodies and other complex biolog

View original ↗

Share New publication demonstrates that insitro’s POSH platform — integrating pooled CRISPR screening and self-supervised deep learning — successfully breaks the historic compromise between scale and depth to more rapidly identify novel therapeutic targets. SOUTH SAN FRANCISCO, Calif. — Dec. 16, 2025 — insitro, the AI therapeutics company built on causal biology, today announced the publication of research in Nature

View original ↗

Music editing is vital in modern production, yet many systems overlook preserving musical facets that should remain unchanged. The authors define this as Music Context Preservation (MuseCP) and introduce MuseCPEval, the first evaluation framework covering four categories of music facets with fine-grained metrics. Objective validation and human studies confirm effectiveness, while case studies demonstrate utility as a

View original ↗

Fourteen researchers report eleven case studies across mathematics, physics, astronomy, biology and materials, documenting both concrete advances and failure modes.

View original ↗

Sam Rodriques, an alum of the Synthetic Neurobiology research group, has been recognized in the Innovators category of the TIME100 AI 2025 list. Dr. Rodriques co-founded the nonprofit FutureHouse in 2023, with the aim of giving scientists new tools to break through bottlenecks and improve their workflows. To that end, FutureHouse is developing AI agents that can formulate hypotheses, conduct experiments, and analyze

View original ↗

A theoretical physicist by training, Sam Rodriques recognized the possible uses of AI for scientific discovery. In 2023 he co-founded the nonprofit FutureHouse, with a goal to build AI scientists that can formulate hypotheses, conduct experiments, and analyze data by themselves. While AI science is an increasingly crowded field, FutureHouse’s audacious vision and scientific bonafides have earned it the backing of Eri

View original ↗