What’s new

MoRSE accepted at NeurIPS 2026

Peiwen Li, Harry Zhang, Yangtian Zhang, and Sizhuang He introduce a mixture of role and subtask experts that lets teams of LLM agents split up hard problems.

The AI Neuroscientist

Aakash Patel and colleagues release an agent that runs neuroimaging analyses through conversation, with the Saxena and Krishnaswamy labs.

Teaching language models to simulate biology, not just reason about it

David speaks at the EMBL-EBI Industry Programme workshop on AI reasoning with LLMs, Cambridge, MA.

STRIDE presented at ICML 2026

Syed Rizvi presents STRIDE, which post-trains LLMs to reason about and refine biological sequences through edit trajectories.

Aakash Patel named a Salovey–Moret Data Science Fellow

Aakash joins the inaugural cohort of Yale’s Peter Salovey and Marta Moret Data Science Fellows Program.

TANTE accepted in the Journal of Computational Physics

Time-adaptive operator learning via neural Taylor expansion, with Lu Lu’s group.

AI at Yale Seed Grant: a Rosetta Stone for aging

With the Higgins-Chen lab, we will build language models that translate omics data into measures of healthspan.

Three papers accepted at ICML 2026

Permutation diffusion on ranks, STRIDE for bio-sequence reasoning, and variational insertion-based generation.

Building the virtual human for drug discovery

David gives the Boehringer Ingelheim Future of Science Seminar.

SciDesignBench

A benchmark for scientific inverse design, and methods that make language models better at it.

CaDDi at NeurIPS 2025

Yangtian Zhang presents non-Markovian discrete diffusion with causal language models in San Diego.

David van Dijk promoted to Associate Professor

Syed Rizvi receives a Google PhD Fellowship

C2S-Scale generates a new cancer hypothesis, confirmed in living cells

Our 27B model, built with Google Research and Google DeepMind, predicted that the CK2 inhibitor silmitasertib boosts antigen presentation only in an immune-active context. Experiments at Yale confirmed it.

NSF CAREER Award

Language models and neural operator learning for spatiotemporal biomedical discovery.

Intelligence at the Edge of Chaos at ICLR 2025

C2S-Scale preprint released