Ning Ding

6 papers Tsinghua University, Tsinghua University

• DePass: Unified Feature Attributing by Simple Decomposed Forward Pass
• Learning to Focus: Causal Attention Distillation via Gradient‐Guided Token Pruning
• Scaling Physical Reasoning with the PHYSICS Dataset
• TTRL: Test-Time Reinforcement Learning
• The Overthinker's DIET: Cutting Token Calories with DIfficulty-AwarE Training
• Towards Large-Scale In-Context Reinforcement Learning by Meta-Training in Randomized Worlds