Ming Li
- CPO: Condition Preference Optimization for Controllable Image Generation
- ColorBench: Can VLMs See and Understand the Colorful World? A Comprehensive Benchmark for Color Perception, Reasoning, and Robustness
- CrossAD: Time Series Anomaly Detection with Cross-scale Associations and Cross-window Modeling
- HyperMixup: Hypergraph-Augmented with Higher-order Information Mixup
- MultiNet: Adaptive Multi-Viewed Subgraph Convolutional Networks for Graph Classification
- Safe-Sora: Safe Text-to-Video Generation via Graphical Watermarking
- Sekai: A Video Dataset towards World Exploration
- To Think or Not To Think: A Study of Thinking in Rule-Based Visual Reinforcement Fine-Tuning
- ViCrit: A Verifiable Reinforcement Learning Proxy Task for Visual Perception in VLMs