AI.info
Bing Wang
Explore Bing Wang on AI.info.
- PhysInOne: Visual Physics Learning and Reasoning in One Suite
- VILTA: A VLM-in-the-Loop Adversary for Enhancing Driving Policy Robustness
- Distribution-Aligned Sequence Distillation for Superior Long-CoT Reasoning
- Pixel-Perfect Visual Geometry Estimation
- ParkGaussian: Surround-view 3D Gaussian Splatting for Autonomous Parking
- DriveLaW:Unifying Planning and Video Generation in a Latent Driving World
- MindDrive: A Vision-Language-Action Model for Autonomous Driving via Online Reinforcement Learning
- MiMo-Embodied: X-Embodied Foundation Model Technical Report
- Enhancing Multimodal Misinformation Detection by Replaying the Whole Story from Image Modality Perspective
- LiveStar: Live Streaming Assistant for Real-World Online Video Understanding
- Rethinking Driving World Model as Synthetic Data Generator for Perception Tasks
- Pixel-Perfect Depth with Semantics-Prompted Diffusion Transformers