Lei Bai

Exploring the quotient space of equivalent GEM repairs unlocks a more efficient path to discovering distinct biological mechanisms, outperforming standard exploration under verifier-induced equivalence.

Enzymatic reactions are more than just molecular transformations; a unified model now captures both molecular structure and catalytic function, bridging a critical domain gap.

SciReasoner achieves a remarkable 31% improvement in Cellular Component annotation for low-homology proteins, showcasing the power of structural reasoning in AI.

Achieving trillion-parameter performance with just 35 billion parameters by scaling agent horizons reveals a new frontier in model efficiency.

LLMs can slash the search space for physical laws by 100,000x, yielding simpler and more accurate formulas for materials properties.

Forget RLHF, self-play, or chain-of-thought: geometric consensus with sparse supervision unlocks scientific reasoning in LLMs.