PPaperPicks

Xinshuo Hu

9 papers at tracked venues · 6 at CORE A* · active 20242026

Venues

Frequent coauthors

Papers

  1. Learning to Extract Rational Evidence via Reinforcement Learning for Retrieval-Augmented Generation
  2. CMT: A Memory Compression Method for Continual Knowledge Learning of Large Language Models
  3. DAST: Context-Aware Compression in LLMs via Dynamic Allocation of Soft Tokens
  4. FunnelRAG: A Coarse-to-Fine Progressive Retrieval Paradigm for RAG
  5. Improving Attributed Text Generation of Large Language Models via Preference Learning
  6. In-Context Learning State Vector with Inner and Momentum Optimization
  7. Separate the Wheat from the Chaff: Model Deficiency Unlearning via Parameter-Efficient Module Operation
    AAAI 2024 · Xinshuo Hu
  8. Take Off the Training Wheels! Progressive In-Context Learning for Effective Alignment
  9. TruthReader: Towards Trustworthy Document Assistant Chatbot with Reliable Attribution