Scholar
Carl Vondrick
Google Scholar ID: 3MzhkFIAAAAJ
Associate Professor, Columbia University
Computer Vision
Machine Learning
Follow
Homepage
↗
Google Scholar
↗
Citations & Impact
All-time
Citations
15,374
H-index
47
i10-index
81
Publications
20
Co-authors
62
list available
Contact
No contact links provided.
Publications
11 items
Few-Shot Design Optimization by Exploiting Auxiliary Information
2026
Cited
0
4D Gaussian Splatting as a Learned Dynamical System
2025
Cited
0
New York Smells: A Large Multimodal Dataset for Olfaction
2025
Cited
0
CAViAR: Critic-Augmented Video Agentic Reasoning
2025
Cited
0
Video Generators are Robot Policies
2025
Cited
0
MINERVA: Evaluating Complex Video Reasoning
2025
Cited
0
Towards LLM Agents for Earth Observation
2025
Cited
0
Can LLM feedback enhance review quality? A randomized study of 20K reviews at ICLR 2025
2025
Cited
0
Load more
Resume (English only)
Academic Achievements
Recipient of the 2024 PAMI Young Researcher Award
Recipient of the 2021 NSF CAREER Award
Senior Program Chair for ICLR 2025
General Chair for ICLR 2026
Mentored numerous PhD graduates now in academia and industry (e.g., Mistral, Meta, TRI, Rutgers, UMD, MBZUAI)
Published influential work in video learning, interpretability, audiovisual modeling, 3D reconstruction, robotics, and AI4Science
Research Experience
Currently YM Associate Professor of Computer Science at Columbia University
Researcher at Apple
Former research scientist at Google
Former visiting researcher at Cruise
Leads a lab that recruits 1–2 PhD students annually, focusing on multimodal learning, 3D vision, and robotic perception
Background
YM Associate Professor of Computer Science at Columbia University
Researcher at Apple
Research focuses on computer vision, machine learning, and their applications
Aims to build perception systems with spatial, physical, logical, and reasoning capabilities
Explores visual models leveraging large-scale unlabeled data for cross-task and cross-modal transfer
Additional interests include scene dynamics, audiovisual and language integration, interpretable models, and perception for robotics
Co-authors
62 total
Antonio Torralba
Professor of Computer Science, MIT
Hamed Pirsiavash
Associate Professor at University of California, Davis
Ruoshi Liu
Research Scientist, Meta FAIR
Chengzhi Mao
Assistant Professor, Rutgers University
Co-author 5
Junfeng Yang
Professor of Computer Science, Columbia University
Cordelia Schmid
Research director INRIA
Co-author 8
×
Welcome back
Sign in to Agora
Welcome back! Please sign in to continue.
Email address
Password
Forgot password?
Continue
Do not have an account?
Sign up