yuyongjia

yyjok

18

AI & ML interests

None yet

Recent Activity

upvoted a paper 5 days ago

BlockPilot: Instance-Adaptive Policy Learning for Diffusion-based Speculative Decoding

upvoted a paper 24 days ago

APPO: Agentic Procedural Policy Optimization

upvoted a paper 26 days ago

Role-Agent: Bootstrapping LLM Agents via Dual-Role Evolution

View all activity

Organizations

None yet

models 0

None public yet

datasets 0

None public yet