SII-zyj
SII-zyj
ยท
AI & ML interests
LLM, MLLM, AI4Science, RL
Recent Activity
upvoted a paper 2 days ago
The Past Is Not Past: Memory-Enhanced Dynamic Reward Shaping upvoted a paper 3 months ago
ArenaRL: Scaling RL for Open-Ended Agents via Tournament-based Relative Ranking commentedon a paper 4 months ago
Incentivizing Tool-augmented Thinking with Images for Medical Image AnalysisOrganizations
