Tianyu Chen

MT-EditFlow bridges the gap between local planning and global success in multi-turn image editing, achieving a significant performance boost over leading models.

SIRI allows LLM agents to autonomously develop and internalize skills, achieving up to a 2.2% performance boost without external dependencies.

Reference patches, typically discarded in software-engineering agent training, can be distilled into latent process graphs to guide trajectory curation, leading to more effective and efficient learning.

Finally, a gradually typed metaprogramming language with mutable references that *doesn't* let your variables escape scope, thanks to clever dynamic enforcement of environment classifiers.

Tool-using agents like Clawdbot are surprisingly vulnerable to seemingly harmless prompts, where minor misinterpretations can quickly escalate into high-stakes tool actions.