Zhaoyang Wang

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

A new benchmark reveals that existing defect detection methods falter in novel production scenarios, highlighting the urgent need for severity-aware assessments in manufacturing.

An optimal knowledge distribution can significantly enhance LLM knowledge boundaries, outperforming traditional synthesis methods across multiple benchmarks.

ReID models implicitly encode a hierarchy of attributes like BMI and pose, revealing potential biases and vulnerabilities that vary across spectral modalities.

Autonomous web agents get a serious upgrade with WebXSkill, which lets them learn and execute skills with both code-level precision and human-readable guidance.

GUI agents can achieve significantly stronger task-solving capabilities through carefully designed post-training and data curation, without relying on costly online data collection.