Xiaotong Chen

发表论文 13 篇 · 总被引 272 次 · h-index 7

代表论文

• VLMbench: A Compositional Benchmark for Vision-and-Language Manipulation (2022 · Neural Information Processing Systems · 被引 97)
• ClearPose: Large-scale Transparent Object Dataset and Benchmark (2022 · European Conference on Computer Vision · 被引 77)
• Cosmos 3: Omnimodal World Models for Physical AI (2026 · arXiv.org · 被引 47)
• LIT: Light-Field Inference of Transparency for Refractive Object Localization (2019 · IEEE Robotics and Automation Letters · 被引 26)
• GRIP: Generative Robust Inference and Perception for Semantic Robot Manipulation in Adversarial Environments (2019 · IEEE/RJS International Conference on Intelligent RObots and Systems · 被引 26)
• TransNet: Category-Level Transparent Object Pose Estimation (2022 · ECCV Workshops · 被引 23)