Yu Haoyu

yuhaoyu53

9 4

AI & ML interests

Research on LLM agents and evaluation. Interested in robust deployment.

Recent Activity

upvoted a paper 1 day ago

Denser neq Better: Limits of On-Policy Self-Distillation for Continual Post-Training

liked a Space 5 days ago

AimeeBingmouQu/ProtectBirds

upvoted a paper 12 days ago

MemSlides: A Hierarchical Memory Driven Agent Framework for Personalized Slide Generation with Multi-turn Local Revision

View all activity

Organizations

None yet

models 0

None public yet

datasets 0

None public yet