← authors · overview

• Separate The Wheat From The Chaff: Model Deficiency Unlearning Via Parameter-efficient Module Operation
  2023 · 43 citations
• Stabilizing Long-term Multi-turn Reinforcement Learning with Gated Rewards
  2025 · 2 citations
• LycheeDecode: Accelerating Long-Context LLM Inference via Hybrid-Head Sparse Decoding
  2026
• Dynamic Long Context Reasoning over Compressed Memory via End-to-End Reinforcement Learning
  2026
• Dynamic Long Context Reasoning over Compressed Memory via End-to-End Reinforcement Learning
  2026
• FusionFormer: Fusing Operations in Transformer for Efficient Streaming Speech Recognition
  2022