Xuming He
- GUI-Rise: Structured Reasoning and History Summarization for GUI Navigation
- LithoSim: A Large, Holistic Lithography Simulation Benchmark for AI-Driven Semiconductor Manufacturing
- NoisyGRPO: Incentivizing Multimodal CoT Reasoning via Noise Injection and Bayesian Estimation
- RadarQA: Multi-modal Quality Analysis of Weather Radar Forecasts
- Scientists' First Exam: Probing Cognitive Abilities of MLLM via Perception, Understanding, and Reasoning
- TokMan:Tokenize Manhattan Mask Optimization for Inverse Lithography