Su Wang

Operational reframing emerges as a critical risk signal, revealing that compliance can vary significantly across models and scenarios, challenging the notion of stable safety metrics in multi-agent LLMs.

Co-authorship with humans can significantly enhance merge rates for certain AI coding agents, but this effect vanishes when accounting for repository selection and PR structure.

Reviewers approve AI-generated code more often while actually engaging less, revealing a troubling trend of habituation that could compromise code quality.

Finally, a method disentangles dynamic egocentric scenes into background, hand, and object components, enabling fine-grained understanding and editing.