← authors · overview

• Leave No Document Behind: Benchmarking Long-context Llms With Extended Multi-doc QA
  2024 · 126 citations
• How Alignment And Jailbreak Work: Explain LLM Safety Through Intermediate Hidden States
  2024 · 92 citations
• Structrag: Boosting Knowledge Intensive Reasoning Of Llms Via Inference-time Hybrid Information Structurization
  2024 · 67 citations
• Chinesevideobench: Benchmarking Multi-modal Large Models For Chinese Video Question Answering
  2025
• Creft-cad: Boosting Orthographic Projection Reasoning For CAD Via Reinforcement Fine-tuning
  2025