arxiv:2605.24830
Xiaoteng Ma
xtma
AI & ML interests
Agent, RL
Recent Activity
upvoted a paper about 3 hours ago
On the Scaling of PEFT: Towards Million Personal Models of Trillion Parameters authored a paper 7 days ago
From Word to World: Can Large Language Models be Implicit Text-based World Models? authored a paper 7 days ago
Thickening-to-Thinning: Reward Shaping via Human-Inspired Learning Dynamics for LLM ReasoningOrganizations
