arxiv:2606.09426
Wanli Li
wanlilll
AI & ML interests
NLP、CV、RL、Agent
Recent Activity
authored a paper about 3 hours ago
TempFlow-GRPO: When Timing Matters for GRPO in Flow Models authored a paper about 3 hours ago
LiteResearcher: A Scalable Agentic RL Training Framework for Deep Research Agent authored a paper about 3 hours ago
SAIL: Self-Amplified Iterative Learning for Diffusion Model Alignment with Minimal Human Feedback