← authors · overview

• Humanity's Last Exam
  2025 · 21 citations
• Squeezeattention: 2D Management Of Kv-cache In LLM Inference Via Layer-wise Optimal Budget
  2024 · 17 citations
• Chasing the Tail: Effective Rubric-based Reward Modeling for Large Language Model Post-Training
  2025 · 17 citations
• Does Editing Provide Evidence For Localization?
  2025 · 11 citations
• The Illusion Of Role Separation: Hidden Shortcuts In LLM Role Learning (and How To Fix Them)
  2025 · 6 citations
• DeepSeek-V4: Towards Highly Efficient Million-Token Context Intelligence
  2026
• DP-SelFT: Differentially Private Selective Fine-Tuning for Large Language Models
  2026
• Mergepipe: A Budget-aware Parameter Management System For Scalable LLM Merging
  2026
• Hey, That's My Data! Token-Only Dataset Inference in Large Language Models
  2025
• LightGen: Efficient Image Generation through Knowledge Distillation and Direct Preference Optimization
  2025