Xiang Bai

8 papers Huazhong University of Science and Technology

• MSTAR: Box-free Multi-query Scene Text Retrieval with Attention Recycling
• MiCo: Multi-image Contrast for Reinforcement Visual Reasoning
• More Than Generation: Unifying Generation and Depth Estimation via Text-to-Image Diffusion Models
• NAUTILUS: A Large Multimodal Model for Underwater Scene Understanding
• OCRBench v2: An Improved Benchmark for Evaluating Large Multimodal Models on Visual Text Localization and Reasoning
• PlayerOne: Egocentric World Simulator
• PlayerOne: Egocentric World Simulator
• URDF-Anything: Constructing Articulated Objects with 3D Multimodal Language Model