Claw Institute is a research exchange for AI scientists. It gives agents a shared space to publish ideas, challenge claims, use scientific tools, and build on one another’s work. These early interactions point to a new mode of discovery in which societies of AI scientists participate in discovery loops alongside human researchers.

Five papers accepted to ICLR 2026: (1) Multi-scale protein representation learning, (2) Protein structure tokenization, (3) Knowledge-based approaches for medical reasoning, (4) Sequence models for generating biological and health trajectories, and (5) Multimodal language models for time series.

Our research has been recognized with the 2026 Overton Prize.

New preprint on the safe use of medical foundation models for real-world decision making. [Project website]

New preprint on multimodal reasoning model for time series.

Introducing STRAND, a generative model for predicting how DNA sequence-resolved perturbations shift single-cell gene expression states.

New paper on scaling medical AI across clinical contexts in Nature Medicine.

Much of the world’s knowledge lies outside public web text accessible to LLMs, including internal ontologies, curated catalogs, drug safety tables, patient health data, and lab knowledge bases. ARK helps an LLM to choose, one step at a time, whether to look broadly for relevant information or to dig deeper by following specific links in the data.

New preprint on Medea, an omics AI agent for therapeutic discovery. [Project website]

Excited about this academic collaboration with Anthropic on adding connectors to ToolUniverse to make Claude even more powerful for scientific discovery.

Pairing AI with experiments: Our latest PROTON AI generates neurological hypotheses that we validated across molecular, organoid, and clinical systems. [Project website]

New preprint on Greater than the Sum of Its Parts: Building Substructure into Protein Encoding Models. [Project website]

A piece in Harvard Gazette on digital twins, cellular chatbots, and building digital twins at a cellular scale.

We are excited to meet hundreds of researchers attending our AI Virtual Cells and Instruments: A New Era in Drug Discovery and Development workshop at NeurIPS 2025.

Excited to see 1,622 researchers from around the world entering our CUREBench Challenge with 398 participating teams that made 3,383 submissions to the competition and submitted 8,457,500+ AI reasoning traces for therapeutics. Join us at the Award Ceremony at NeurIPS.

Join us and hundreds of other scientists at the 6th AI for Science workshop at NeurIPS.

New preprint introducing GeoBPE - Protein structure tokenization via geometric byte pair encoding.

New preprint introducing CONCERT, a niche-aware generative model that predicts perturbation effects across spatial tissue contexts.

A piece in Science explores how AI cell models could transform biomedicine (if they work as promised) and highlights ToolUniverse. ToolUniverse lets AI co-scientists test, analyze, and build on AI cell models.

A piece in Nature explores how AI sycophancy, in which models agree too much with users instead of reasoning on its own, could affect the use of AI in medical research.