Guanhua
eric18
AI & ML interests
NLP/ML
Recent Activity
upvoted a paper about 7 hours ago
LoopCoder-v2: Only Loop Once for Efficient Test-Time Computation Scaling upvoted a paper 8 days ago
Bridging the Agent-World Gap: Text World Models for LLM-based Agents upvoted a paper 2 months ago
SPPO: Sequence-Level PPO for Long-Horizon Reasoning Tasks