STAPO: Stabilizing Reinforcement Learning for LLMs by Silencing Rare Spurious Tokens
Paper • 2602.15620 • Published • 3
Keqiang Li
UestcJay
AI & ML interests
None yet
Recent Activity
upvoted a paper about 7 hours ago
EVA: Efficient Reinforcement Learning for End-to-End Video Agent authored a paper about 1 month ago
STAPO: Stabilizing Reinforcement Learning for LLMs by Silencing Rare Spurious Tokens upvoted a paper 5 months ago
InteractiveOmni: A Unified Omni-modal Model for Audio-Visual Multi-turn
DialogueOrganizations
None yet
authored a
paper about 1 month ago