Jiawei Liu

AgentSentry stops indirect prompt injection attacks in LLM agents by pinpointing when the attack takes hold using causality, then surgically removing the malicious influence.

Code-generating LLMs may ace static benchmarks, but developers are actually *slower* when using them because they disrupt mental flow, highlighting the need for benchmarks that capture the temporal dynamics of coding.

Forget clunky skeletons: this new model lets you prompt your way to accurate 3D human meshes from single images, even in the wildest poses.

LLM-powered test generation can finally achieve meaningful coverage in deep learning libraries, thanks to a novel agent-driven framework that iteratively refines tests based on constraint validation.