Jingrui He

4 papers University of Illinois at Urbana-Champaign

• CLIMB: Class-imbalanced Learning Benchmark on Tabular Data
• Mint: A Simple Test-Time Adaptation of Vision-Language Models against Common Corruptions
• ReasonFlux-PRM: Trajectory-Aware PRMs for Long Chain-of-Thought Reasoning in LLMs
• Transformer Copilot: Learning from The Mistake Log in LLM Fine-tuning