arxiv:2409.02813
yuxuan sun
jamessyx
AI & ML interests
None yet
Recent Activity
upvoted a paper about 15 hours ago
ProAS: A Progress-Aware Advantage Shaping Framework for Multi-Turn Agentic Reinforcement Learning updated a model 10 months ago
jamessyx/PathGen-LLaVA upvoted a paper 11 months ago
Rethinking Expert Trajectory Utilization in LLM Post-training