Scholar
Xiaotong Chen
Google Scholar ID: UPIcVtUAAAAJ
Research Scientist, ProtagoLabs | Ph.D., University of Michigan
Citations & Impact
Citations
655
H-index
11
i10-index
12
Publications
20
Co-authors
16
list available
Publications
Browse publications on Google Scholar (top-right) ↗
Resume (English only)
Academic Achievements
- Published multiple papers, such as 'T-Recs: Transparency Reconstruction from Single-view Fusion' (Humanoids 2023), 'TransNet: Transparent Object Manipulation Through Category-Level Pose Estimation' (ECCV workshop 2022), 'VLMbench: A Compositional Benchmark for Vision-and-Language Manipulation' (NeuIPS 2022), 'ClearPose: Large-scale Transparent Object Dataset and Benchmark' (ECCV 2022), 'ProgressLabeller: Visual Data Stream Annotation for Training Object-Centric 3D Perception' (IROS 2022).
Research Experience
- Worked as a research engineer on self-driving truck localization at TuSimple (summer 2020); interned as an applied scientist at Amazon Lab 126 (summer 2022). Main research areas include transparent object reconstruction, transparent object manipulation, and benchmarks for vision-and-language manipulation tasks.
Education
- PhD in Robotics from the University of Michigan, Ann Arbor, under the supervision of Prof. Chad Jenkins; previously conducted research in the soft robotics group led by Prof. Xiaoping Chen at the University of Science and Technology of China.
Background
- Research Interests: Combining robotics and NLP to realize more intelligent general-purpose AI systems. Currently working as a research scientist at ProtagoLabs.AI.
Miscellany
- Personal interests and hobbies not mentioned
