AI.info

Xiang Bai

Explore Xiang Bai on AI.info.

• SimWAM: A Simple World Action Model for End-to-End Autonomous Driving
• TurboVLA: Real-Time Vision-Language-Action Model at 32 Hz on an RTX 4090 with <1 GB VRAM
• AlphaOracle: Oracle bone script decipherment via human-workflow-inspired deep learning
• When Numbers Speak: Aligning Textual Numerals and Visual Instances in Text-to-Video Diffusion Models
• ThinkOmni: Lifting Textual Reasoning to Omni-modal Scenarios via Guidance Decoding
• MindDrive: A Vision-Language-Action Model for Autonomous Driving via Online Reinforcement Learning
• Cook and Clean Together: Teaching Embodied Agents for Parallel Task Execution
• URDF-Anything: Constructing Articulated Objects with 3D Multimodal Language Model
• NAUTILUS: A Large Multimodal Model for Underwater Scene Understanding
• More Than Generation: Unifying Generation and Depth Estimation via Text-to-Image Diffusion Models