Ning Ding

12

Papers

536

Total Citations

1

Affiliations

Affiliations

Tsinghua University

Papers (12)

Advancing LLM Reasoning Generalists with Preference Trees

TTRL: Test-Time Reinforcement Learning

NeurIPS 2025arXiv

MedXpertQA: Benchmarking Expert-Level Medical Reasoning and Understanding

KoLA: Carefully Benchmarking World Knowledge of Large Language Models

Predicting Emergent Abilities with Infinite Resolution Evaluation

How to Synthesize Text Data without Model Collapse?

Scaling Physical Reasoning with the PHYSICS Dataset

The Overthinker's DIET: Cutting Token Calories with DIfficulty-AwarE Training

NeurIPS 2025arXiv

Learning to Focus: Causal Attention Distillation via Gradient‐Guided Token Pruning

Towards Large-Scale In-Context Reinforcement Learning by Meta-Training in Randomized Worlds

ULTRAFEEDBACK: Boosting Language Models with Scaled AI Feedback

Memory-Space Visual Prompting for Efficient Vision-Language Fine-Tuning