Junzhe Wang

AbICL reveals that contextual demonstrations can dramatically improve antibody affinity ranking, especially in challenging scenarios where traditional methods fall short.

Even state-of-the-art language models struggle significantly in real-world tasks, exposing critical shortcomings in their deployment readiness.

Today's best language models can barely make sense of your messy group chats and fragmented digital life, achieving only 19% accuracy on a new benchmark of real-world reasoning.

RAG models struggle to ignore their pre-trained knowledge, even when it contradicts the provided context, but a new dataset can help them learn to be more faithful.

Multi-turn reinforcement learning gets a boost: weighting trajectories by semantic similarity dramatically improves baseline estimation and agent performance in long-document visual QA.