6 papers
Auditable Claims about AI Agents
Yue Zhao, Jiate Li, Li Li +4
Organizations make claims about their AI agents: a person approves every external email, every action is logged, an evaluation shows the agent is safe to deploy. Article 12 of the…
Deciphering Fingerprints of 3D Molecular Surfaces for Accurate Epitope Prediction
Fang Wu, Weihao Xuan, Jure Leskovec +2
Molecular surfaces encode the geometric and physicochemical patterns that determine antibody-antigen recognition, central to epitope prediction. However, existing methods rely on s…
NoiseRater: Meta-Learned Noise Valuation for Diffusion Model Training
Fang Wu, Haokai Zhao, Da Xing +18
Training a diffusion model involves two sources of randomness for each data sample: the timestep and the Gaussian noise realization. The timestep has been studied extensively throu…
Proteo-R1: Reasoning Foundation Models for De Novo Protein Design
Fang Wu, Weihao Xuan, Heli Qi +26
Deep learning in de novo protein design has achieved atomic-level fidelity. However, existing models remain largely non-deliberative: they directly synthesize molecular geometries…
DeepSearch: Overcome the Bottleneck of Reinforcement Learning with Verifiable Rewards via Monte Carlo Tree Search
Fang Wu, Weihao Xuan, Heli Qi +4
Although RLVR has become an essential component for developing advanced reasoning skills in language models, contemporary studies have documented training plateaus after thousands…
Position: The Hidden Costs and Measurement Gaps of Reinforcement Learning with Verifiable Rewards
Fang Wu, Aaron Tu, Weihao Xuan +21
Reinforcement learning with verifiable rewards (RLVR) is a practical, scalable way to improve large language models on math, code, and other structured tasks. However, we argue tha…