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
authored
a paper
5 days ago
STAPO: Stabilizing Reinforcement Learning for LLMs by Silencing Rare Spurious Tokens upvoted a paper 4 months ago
InteractiveOmni: A Unified Omni-modal Model for Audio-Visual Multi-turn
Dialogue upvoted a paper 6 months ago
ELV-Halluc: Benchmarking Semantic Aggregation Hallucinations in Long
Video Understanding Organizations
None yet
authored a paper 5 days ago