At CoRL 2026, Tsinghua University Assistant Professor Xu Mengdi presented her research on building adaptable generalist robots for human-centered environments. Her work emphasizes the necessity for robots to learn during deployment, rather than solely relying on pre-training. Key projects include CoVer-VLA, which uses a validator to refine robot actions based on user instructions, and Dex-X, which learns dexterous manipulation from human demonstrations by leveraging simulation to bridge the gap in tactile information. AI
IMPACT Highlights the need for robots to learn adaptively in real-world scenarios, moving beyond static pre-training.
RANK_REASON Research presentation at an academic conference. [lever_c_demoted from research: ic=1 ai=1.0]
- Carnegie Mellon University
- .codex
- CoRL 2026
- CoVer-VLA
- Dex-X
- Fei-Fei Li
- Leiphone
- Rosetta
- Safe AI Lab
- Stanford University
- Tsinghua University
- Wu Jiajun
- Xu Mengdi
- Zhao Ding
AI-generated summary · Google Gemini · from 1 sources. How we write summaries →