Scholar
Zhiding Yu
Google Scholar ID: 1VI_oYUAAAAJ
Principal Research Scientist & Research Lead, NVIDIA Research
Computer Vsion
Deep Learning
Follow
Homepage
↗
Google Scholar
↗
Citations & Impact
All-time
Citations
24,839
H-index
56
i10-index
89
Publications
20
Co-authors
15
list available
Contact
CV
Open ↗
Twitter
Open ↗
GitHub
Open ↗
LinkedIn
Open ↗
Publications
34 items
Recova: Agent-Guided Failure Recovery for Autonomous Robotic Manipulation
2026
Cited
0
Vesta: A Generalist Embodied Reasoning Model
2026
Cited
0
LocateAnything: Fast and High-Quality Vision-Language Grounding with Parallel Box Decoding
2026
Cited
0
ProRL Agent: Rollout-as-a-Service for RL Training of Multi-Turn LLM Agents
2026
Cited
0
Towards Multimodal Lifelong Understanding: A Dataset and Agentic Baseline
2026
Cited
0
Stateful Token Reduction for Long-Video Hybrid VLMs
2026
Cited
0
PhyCritic: Multimodal Critic Models for Physical AI
2026
Cited
0
Nemotron ColEmbed V2: Top-Performing Late Interaction embedding models for Visual Document Retrieval
2026
Cited
0
Load more
Resume
Academic Achievements
Winner, CVPR24 Challenge on End-to-End Driving at Scale (Hydra-MDP).
2nd Place, CVPR24 Challenge on Driving with Language.
Winner, CVPR23 Challenge on 3D Occupancy Prediction (FB-BEV/FB-OCC).
Winner, ECCV22 Robust Vision Challenge (RVC) on Semantic Segmentation.
Winner, CVPR18 Autonomous Driving Challenge (WAD) on Domain Adaptation.
2nd Place, ICMI15 EmotiW Challenge on Static Facial Expression Recognition.
Best Paper Award, BMVC 2020.
Best Paper Award, WACV 2015.
Best Student Paper Award, ISCSLP 2014.
Most Influential NeurIPS Paper Award (SegFormer).
Numerous publications listed on Google Scholar.
Background
Principal Research Scientist & Research Lead at the Learning & Perception Research Group, NVIDIA Research.
Interested in building general autonomy and intelligence across virtual and physical domains.
Recent focus includes Vision Transformers, LLMs, multimodal LLMs, and vision-language-action (VLA) models.
Applications span open-world understanding, reasoning, AV/robot perception-planning, and agentic systems.
Works are characterized by state-of-the-art performance, scalable architectures, and data-centric strategies for real-world generalization.
Co-authors
13 total
Anima Anandkumar
California Institute of Technology and NVIDIA
Jose M. Alvarez
NVIDIA
Jan Kautz
Vice President of Research, NVIDIA Research
Weiyang Liu
CUHK | Max Planck Institute for Intelligent Systems
Shiyi Lan
NVIDIA
Xiaodong Yang
NVIDIA Research
Yang Zou
Senior Applied Scientist, Amazon
Chen Feng (冯晨)
New York University