I am a professor in the computer science department at Columbia, and my research studies computer vision, machine learning, and their applications.
I was previously a research scientist on the machine perception team at Google, and a visiting researcher at Cruise. I completed my PhD at MIT in 2017 advised by Antonio Torralba and my BS at UC Irvine in 2011, where I got my start working with Deva Ramanan.
I received the 2024 PAMI Young Researcher Award and the 2021 NSF CAREER Award. I am also the Senior Program Chair for ICLR 2025.
By training machines to observe and interact with their surroundings, our research aims to create robust and versatile models for perception. Our lab often investigates visual models that capitalize on large amounts of unlabeled data and transfer across tasks and modalities. Other interests include scene dynamics, sound and language and beyond, interpretable models, and perception for robotics.
Our lab recruits one or two PhD students each fall. Prospective PhD students should apply to the PhD program.
Sumit Sarin (2024), Ishaan Preetam Chandratreya (2023), Revant Teotia (2023), Scott Geng, (2023), Hui Lu, (2022), Jillian Ross (2021), Amogh Gupta (2020), Dave Epstein (2020)
Our research creates perception systems with diverse skills, including spatial, physical, logical, and reasoning abilities, for flexibly analyzing visual data. Our multimodal approach provides versatile representations for tasks like 3D reconstruction, visual question answering, and robot manipulation, while offering inherent explainability and excellent zero-shot generalization. The below papers highlight key examples of these capabilities.
We create interpretable machine learning methods for perception that allow people to audit decisions and reprogram representations. Unlike black-box neural networks, we develop methods that are explainable by construction while still offering excellent performance.
Machine perception is challenging because most knowledge about our world, such as physical commonsense, is not written down. Through large amounts of unlabeled video and interaction with the natural world, we create algorithms that learn perceptual skills without manual supervision.
Our research creates visual representations that learn the human behavior continuum, capturing the goals underlying human action. We aim to create computer vision systems that can assist people at their activities, thereby enabling new opportunities for human-computer interaction.
Critical applications require systems that are trustworthy and reliable. Our research demonstrates that predictive models have intrinsic empirical and theoretical advantages for improving robustness and generalization.
We develop multi-modal learning methods for robotics, integrating vision, sound, interaction, and other modalities together in order to learn representations for perception, design, and action.
We create new representations for spatial awareness, allowing vision systems to reconstruct scenes in 3D and anticipate object dynamics in the future. We often tightly integrate geometry, physics, and generative models in order to equip 3D vision systems with intuitive, and sometimes un-intuitive, physical skills.
We harness language to learn neuro-symbolic methods for computer vision, establishing methods that rapidly generalize to open world tasks while offering inherent explainability too.
Central to our research is forming an integrative perspective on perception to build accurate and robust models. Our research exploits the natural synchronization between vision, sound, and other modalities to learn cross-modal representations for tasks like recognition, source localization, and artistic correspondence.
The ubiquity of machine perception creates exciting possibilities for applications, but simultaneously exposes significant potential risks. Our research is exploring methods that prevent computer vision methods from solving potentially harmful problems.
Dreamitate: Real-World Visuomotor Policy Learning via Video Generation
Junbang Liang*, Ruoshi Liu*, Ege Ozguroglu, Sruthi Sudhakar, Achal Dave, Pavel
Tokmakov, Shuran Song, Carl Vondrick
CoRL 2024
Paper
Project Page
Whiteboard-of-Thought: Thinking Step-by-Step Across Modalities
Sachit Menon, Richard Zemel, Carl Vondrick
EMNLP 2024
Paper
Project Page
See It from My Perspective: Diagnosing the Western Cultural Bias of Large
Vision-Language Models in Image Understanding
Amith Ananthram, Elias Stengel-Eskin, Carl Vondrick, Mohit Bansal, Kathleen McKeown
arXiv 2024
Paper
Code
How Video Meetings Change Your Expression
Sumit Sarin, Utkarsh Mall, Purva Tendulkar, Carl Vondrick
ECCV 2024
Paper
Project Page
Controlling the World by Sleight of Hand
Sruthi Sudhakar, Ruoshi Liu, Basile Van Hoorick, Carl Vondrick, and Richard Zemel
ECCV 2024 (Oral)
Paper
Generative Camera Dolly: Extreme Monocular Dynamic Novel View Synthesis
Basile Van Hoorick, Rundi Wu, Ege Ozguroglu, Kyle Sargent, Ruoshi Liu, Pavel
Tokmakov, Achal Dave, Changxi Zheng, Carl Vondrick
ECCV 2024 (Oral)
Paper
Project Page
Evolving Interpretable Visual Classifiers with Large Language Models
Mia Chiquier, Utkarsh Mall, Carl Vondrick
ECCV 2024
Paper
Project Page
SelfIE: Self-Interpretation of Large Language Model Embeddings
Haozhe Chen, Carl Vondrick, Chengzhi Mao
ICML 2024
Paper
Project Page
PaperBot: Learning to Design Real-World Tools Using Paper
Ruoshi Liu, Junbang Liang, Sruthi Sudhakar, Huy Ha, Cheng Chi, Shuran Song, Carl
Vondrick
arXiv 2024
Paper
Project Page
pix2gestalt: Amodal Segmentation by Synthesizing Wholes
Ege Ozguroglu, Ruoshi Liu, Dídac Surís, Dian Chen, Achal Dave, Pavel Tokmakov, Carl
Vondrick
CVPR 2024
Paper
Project Page
Raidar: geneRative AI Detection viA Rewriting
Chengzhi Mao, Carl Vondrick, Hao Wang, Junfeng Yang
ICLR 2024
Paper
Interpreting and Controlling Vision Foundation Models via Text Explanations
Haozhe Chen, Junfeng Yang, Carl Vondrick, Chengzhi Mao
ICLR 2024
Paper
Sin3DM: Learning a Diffusion Model from a Single 3D Textured Shape
Rundi Wu, Ruoshi Liu, Carl Vondrick, Changxi Zheng
ICLR 2024
Paper
Project Page
Remote Sensing Vision-Language Foundation Models without Annotations via Ground
Remote Alignment
Utkarsh Mall, Cheng Perng Phoo, Meilin Liu, Carl Vondrick, Bharath Hariharan, Kavita
Bala
ICLR 2024
Paper
Objaverse-XL: A Universe of 10M+ 3D Objects
Matt Deitke, et al.
NeurIPS 2023
Paper
ViperGPT: Visual Inference via Python Execution for Reasoning
Dídac Surís*, Sachit Menon*, Carl Vondrick
ICCV 2023 (Oral)
Paper
Project Page
Code
Zero-1-to-3: Zero-shot One Image to 3D Object
Ruoshi Liu, Rundi Wu, Basile Van Hoorick, Pavel Tokmakov, Sergey Zakharov, Carl
Vondrick
ICCV 2023
Paper
Project Page
Code
Demo
Muscles in Action
Mia Chiquier, Carl Vondrick
ICCV 2023
Paper
Project Page
SurfsUp
: Learning Fluid Simulation for Novel Surfaces
Arjun Mani*, Ishaan Preetam Chandratreya*, Elliot Creager, Carl Vondrick, Richard
Zemel
ICCV 2023
Paper
Project Page
Landscape Learning for Neural Network Inversion
Ruoshi Liu, Chengzhi Mao, Purva Tendulkar, Hao Wang, Carl Vondrick
ICCV 2023
Paper
Blog Post
SHIFT3D: Synthesizing Hard Inputs For Tricking 3D Detectors
Hongge Chen, Zhao Chen, Greg Meyer, Dennis Park, Carl Vondrick, Ashish Shrivastava,
and Yuning Chai
ICCV 2023
Paper
Robust Perception through Equivariance
Chengzhi Mao, Lingyu Zhang, Abhishek Joshi, Junfeng Yang, Hao Wang, Carl Vondrick
ICML 2023
Paper
Project Page
Humans as Light Bulbs: 3D Human Reconstruction from Thermal Reflection
Ruoshi Liu, Carl Vondrick
CVPR 2023
Paper
Project Page
What You Can Reconstruct from a Shadow
Ruoshi Liu, Sachit Menon, Chengzhi Mao, Dennis Park, Simon Stent, Carl Vondrick
CVPR 2023
Paper
Blog Post
Tracking through Containers and Occluders in the Wild
Basile Van Hoorick, Pavel Tokmakov, Simon Stent, Jie Li, Carl Vondrick
CVPR 2023
Paper
Project Page
Datasets
Code
FLEX: Full-Body Grasping Without Full-Body Grasps
Purva Tendulkar, Dídac Surís, Carl Vondrick
CVPR 2023
Paper
Project Page
Doubly Right Object Recognition: A Why Prompt for Visual Rationales
Chengzhi Mao, Revant Teotia, Amrutha Sundar, Sachit Menon, Junfeng Yang, Xin Wang,
Carl Vondrick
CVPR 2023
Paper
Affective Faces for Goal-Driven Dyadic Communication
Scott Geng*, Revant Teotia*, Purva Tendulkar, Sachit Menon, Carl Vondrick
arXiv 2023
Paper
Project Page
Visual Classification via Description from Large Language Models
Sachit Menon, Carl Vondrick
ICLR 2023 (Oral)
Paper
Project Page
Code
Demo
Understanding Zero-Shot Adversarial Robustness for Large-Scale Models
Chengzhi Mao, Scott Geng, Junfeng Yang, Xin Wang, Carl Vondrick
ICLR 2023
Paper
Adversarially Robust Video Perception by Seeing Motion
Lingyu Zhang*, Chengzhi Mao*, Junfeng Yang, Carl Vondrick
arXiv 2022
Paper
Project Page
Task Bias in Vision-Language Models
Sachit Menon*, Ishaan Preetam Chandratreya*, Carl Vondrick
arXiv 2022
Paper
Private Multiparty Perception for Navigation
Hui Lu, Mia Chiquier, Carl Vondrick
NeurIPS 2022
Paper
Project Page
Code
Representing Spatial Trajectories as Distributions
Dídac Surís, Carl Vondrick
NeurIPS 2022
Paper
Project Page
Forget-me-not! Contrastive Critics for Mitigating Posterior Collapse
Sachit Menon, David Blei, Carl Vondrick
UAI 2022
Paper
Revealing Occlusions with 4D Neural Fields
Basile Van Hoorick, Purva Tendulkar, Dídac Surís, Dennis Park, Simon Stent, Carl
Vondrick
CVPR 2022 (Oral)
Paper
Project Page
Talk
Globetrotter: Connecting Languages by Connecting Images
Dídac Surís, Dave Epstein, Carl Vondrick
CVPR 2022 (Oral)
Paper
Project Page
Code
Causal Transportability for Visual Recognition
Chengzhi Mao*, Kevin Xia*, James Wang, Hao Wang, Junfeng Yang, Elias Bareinboim,
Carl Vondrick
CVPR 2022
Paper
It's Time for Artistic Correspondence in Music and Video
Dídac Surís, Carl Vondrick, Bryan Russell, Justin Salamon
CVPR 2022
Paper
Project Page
UnweaveNet: Unweaving Activity Stories
Will Price, Carl Vondrick, Dima Damen
CVPR 2022
Paper
There is a Time and Place for Reasoning Beyond the Image
Xingyu Fu, Ben Zhou, Ishaan Preetam Chandratreya, Carl Vondrick, Dan Roth
ACL 2022 (Oral)
Paper
Code + Data
Real-Time Neural Voice Camouflage
Mia Chiquier, Chengzhi Mao, Carl Vondrick
ICLR 2022 (Oral)
Paper
Project Page
Science
Discrete Representations Strengthen Vision Transformer Robustness
Chengzhi Mao, Lu Jiang, Mostafa Dehghani, Carl Vondrick, Rahul Sukthankar, Irfan
Essa
ICLR 2022
Paper
Full-Body Visual Self-Modeling of Robot Morphologies
Boyuan Chen, Robert Kwiatkowski, Carl Vondrick, Hod Lipson
Science Robotics 2022
Paper
Project Page
Code
The Boombox: Visual Reconstruction from Acoustic Vibrations
Boyuan Chen, Mia Chiquier, Hod Lipson, Carl Vondrick
CoRL 2021
Paper
Project Page
Video Overview
Adversarial Attacks are Reversible with Natural Supervision
Chengzhi Mao, Mia Chiquier, Hao Wang, Junfeng Yang, Carl Vondrick
ICCV 2021
Paper
Code
Dissecting Image Crops
Basile Van Hoorick, Carl Vondrick
ICCV 2021
Paper
Code
Learning the Predictability of the Future
Dídac Surís*, Ruoshi Liu*, Carl Vondrick
CVPR 2021
Paper
Project Page
Code
Models
Talk
Generative Interventions for Causal Learning
Chengzhi Mao, Amogh Gupta, Augustine Cha, Hao Wang, Junfeng Yang, Carl Vondrick
CVPR 2021
Paper
Code
Learning Goals from Failure
Dave Epstein, Carl Vondrick
CVPR 2021
Paper
Project Page
Data
Code
Talk
Visual Behavior Modelling for Robotic Theory of Mind
Boyuan Chen, Carl Vondrick, Hod Lipson
Scientific Reports 2021
Paper
Project Page
Listening to Sounds of Silence for Speech Denoising
Ruilin Xu, Rundi Wu, Yuko Ishiwaka, Carl Vondrick, Changxi Zheng
NeurIPS 2020
Paper
Project Page
Multitask Learning Strengthens Adversarial Robustness
Chengzhi Mao, Amogh Gupta, Vikram Nitin, Baishakhi Ray, Shuran Song, Junfeng Yang,
Carl Vondrick
ECCV 2020 (Oral)
Paper
We Have So Much In Common: Modeling Semantic Relational Set Abstractions in
Videos
Alex Andonian, Camilo Fosco, Mathew Monfort, Allen Lee, Carl Vondrick, Rogerio
Feris, Aude Oliva
ECCV 2020
Paper
Project Page
Learning to Learn Words from Visual Scenes
Dídac Surís*, Dave Epstein*, Heng Ji, Shih-Fu Chang, Carl Vondrick
ECCV 2020
Paper
Project Page
Code
Talk
Oops! Predicting Unintentional Action in Video
Dave Epstein, Boyuan Chen, Carl Vondrick
CVPR 2020
Paper
Project Page
Data
Code
Talk
Metric Learning for Adversarial Robustness
Chengzhi Mao, Ziyuan Zhong, Junfeng Yang, Carl Vondrick, Baishakhi Ray
NeurIPS 2019
Paper
Code
VideoBERT: A Joint Model for Video and Language Representation Learning
Chen Sun, Austin Myers, Carl Vondrick, Kevin Murphy, Cordelia Schmid
ICCV 2019
Paper
Blog
Multi-level Multimodal Common Semantic Space for Image-Phrase Grounding
Hassan Akbari, Svebor Karaman, Surabhi Bhargava, Brian Chen, Carl Vondrick, Shih-Fu
Chang
CVPR 2019
Paper
Code
Relational Action Forecasting
Chen Sun, Abhinav Shrivastava, Carl Vondrick, Rahul Sukthankar, Kevin Murphy,
Cordelia Schmid
CVPR 2019 (Oral)
Paper
Moments in Time Dataset: one million videos for event understanding
Mathew Monfort et al
PAMI 2019
Paper
Project Page
Tracking Emerges by Colorizing Videos
Carl Vondrick, Abhinav Shrivastava, Alireza Fathi, Sergio Guadarrama, Kevin Murphy
ECCV 2018
Paper
Blog
The Sound of Pixels
Hang Zhao, Chuang Gan, Andrew Rouditchenko, Carl Vondrick, Josh McDermott, Antonio
Torralba
ECCV 2018
Paper
Project Page
Actor-centric Relation Network
Chen Sun, Abhinav Shrivastava, Carl Vondrick, Kevin Murphy, Rahul Sukthankar,
Cordelia Schmid
ECCV 2018
Paper
AVA: A Video Dataset of Spatio-temporally Localized Atomic Visual Actions
Chunhui Gu et al
CVPR 2018 (Spotlight)
Paper
Project Page
Following Gaze in Video
Adria Recasens, Carl Vondrick, Aditya Khosla, Antonio Torralba
ICCV 2017
Paper
Generating the Future with Adversarial Transformers
Carl Vondrick, Antonio Torralba
CVPR 2017
Paper
Project Page
Cross-Modal Scene Networks
Yusuf Aytar*, Lluis Castrejon*, Carl Vondrick, Hamed Pirsiavash, Antonio Torralba
PAMI 2017
Paper
Project Page
See, Hear, and Read: Deep Aligned Representations
Yusuf Aytar, Carl Vondrick, Antonio Torralba
arXiv 2017
Paper
Project Page
Generating Videos with Scene Dynamics
Carl Vondrick, Hamed Pirsiavash, Antonio Torralba
NeurIPS 2016
Paper
Project Page
Code
NBC
Scientific American
New Scientist
MIT News
SoundNet: Learning Sound Representations from Unlabeled Video
Yusuf Aytar*, Carl Vondrick*, Antonio Torralba
NeurIPS 2016
Paper
Project Page
Code
NPR
New Scientist
Week Junior
MIT News
Anticipating Visual Representations with Unlabeled Video
Carl Vondrick, Hamed Pirsiavash, Antonio Torralba
CVPR 2016 (Spotlight)
Paper
Project Page
NPR
CNN
AP
Wired
Stephen Colbert
MIT News
Predicting Motivations of Actions by Leveraging Text
Carl Vondrick, Deniz Oktay, Hamed Pirsiavash, Antonio Torralba
CVPR 2016
Paper
Dataset
Learning Aligned Cross-Modal Representations from Weakly Aligned Data
Lluis Castrejon*, Yusuf Aytar*, Carl Vondrick, Hamed Pirsiavash, Antonio Torralba
CVPR 2016
Paper
Project Page
Demo
Visualizing Object Detection Features
Carl Vondrick, Aditya Khosla, Hamed Pirsiavash, Tomasz Malisiewicz, Antonio Torralba
IJCV 2016
Paper
Project Page
Slides
MIT News
Do We Need More Training Data?
Xiangxin Zhu, Carl Vondrick, Charless C. Fowlkes, Deva Ramanan
IJCV 2015
Paper
Dataset
Learning Visual Biases from Human Imagination
Carl Vondrick, Hamed Pirsiavash, Aude Oliva, Antonio Torralba
NeurIPS 2015
Paper
Project Page
Technology Review
Where are they looking?
Adria Recasens*, Aditya Khosla*, Carl Vondrick, Antonio Torralba
NeurIPS 2015
Paper
Project Page
Demo
Assessing the Quality of Actions
Hamed Pirsiavash, Carl Vondrick, Antonio Torralba
ECCV 2014
Paper
Project Page
HOGgles: Visualizing Object Detection Features
Carl Vondrick, Aditya Khosla, Tomasz Malisiewicz, Antonio Torralba
ICCV 2013 (Oral)
Paper
Project Page
Slides
MIT News
Do We Need More Training Data or Better Models for Object Detection?
Xiangxin Zhu, Carl Vondrick, Deva Ramanan, Charless C. Fowlkes
BMVC 2012
Paper
Dataset
Efficiently Scaling Up Crowdsourced Video Annotation
Carl Vondrick, Donald Patterson, Deva Ramanan
IJCV 2012
Paper
Project Page
Video Annotation and Tracking with Active Learning
Carl Vondrick, Deva Ramanan
NeurIPS 2011
Paper
Project Page
A Large-scale Benchmark Dataset for Event Recognition
Sangmin Oh, et al.
CVPR 2011
Paper
Project Page
Efficiently Scaling Up Video Annotation with Crowdsourced Marketplaces
Carl Vondrick, Deva Ramanan, Donald Patterson
ECCV 2010
Paper
Project Page