← 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
• SLO-Aware Compute Resource Allocation for Prefill-Decode Disaggregated LLM Inference
  2026
• LycheeCluster: Efficient Long-Context Inference with Structure-Aware Chunking and Hierarchical KV Indexing
  2026
• 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
• Is On-Policy Data always the Best Choice for Direct Preference Optimization-based LM Alignment?
  2025
• KaLM-Embedding-V2: Superior Training Techniques and Data Inspire A Versatile Embedding Model
  2025
• CMT: A Memory Compression Method for Continual Knowledge Learning of Large Language Models
  2024