Ge Zhang

8 papers University of Michigan - Ann Arbor

• FlexWorld: Progressively Expanding 3D Scenes for Flexible-View Exploration
• General-Reasoner: Advancing LLM Reasoning Across All Domains
• Is Grokking a Computational Glass Relaxation?
• KORGym: A Dynamic Game Platform for LLM Reasoning Evaluation
• LIFEBENCH: Evaluating Length Instruction Following in Large Language Models
• MVU-Eval: Towards Multi-Video Understanding Evaluation for Multimodal LLMs
• OmniBench: Towards The Future of Universal Omni-Language Models
• SuperGPQA: Scaling LLM Evaluation across 285 Graduate Disciplines