SPPO: Sequence-Level PPO for Long-Horizon Reasoning Tasks
Paper • 2604.08865 • Published • 25
Qys77
Qys77
AI & ML interests
None yet
Recent Activity
upvoted a paper about 19 hours ago
SPPO: Sequence-Level PPO for Long-Horizon Reasoning Tasks upvoted a paper 4 months ago
From Word to World: Can Large Language Models be Implicit Text-based World Models? liked a dataset over 1 year ago
xinlai/Math-Step-DPO-10KOrganizations
None yet