Tianjun Zhang

Budget-aware Test-time Scaling via Discriminative Verification

DeepScaleR: Effective RL Scaling of Reasoning Models via Iterative Context Lengthening

R2E-Gym: Procedural Environment Generation and Hybrid Verifiers for Scaling Open-Weights SWE Agents

SuperCorrect: Advancing Small LLM Reasoning with Thought Template Distillation and Self-Correction

LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code

Copilot Arena: A Platform for Code LLM Evaluation in the Wild