About
I am an Assistant Professor in the Computer Science Department at University of Maryland, College Park, and an Amazon Scholar at Amazon FAR.
I was previously a research scientist at Amazon FAR and Meta FAIR. I got my PhD from Columbia University in 2025, advised by Carl Vondrick, and my BS from Columbia SEAS in 2021.
Our research aims to develop intelligent systems that can perceive and interact with the physical world. Our lab focuses on solving manipulation problems with the help of machine learning, geometric processing, and foundation models. We often experiment with different methods to leverage data from internet, simulation, and real world to create robust and generalizable representations and policies.
Our lab recruits one or two PhD students each year. Prospective students should apply to the PhD program. If you are current UMD students who’d like to work with us, please submit this Google Form.
News
[Aug 2026] Moved to DC and started my faculty job at UMD!
[Dec 2025] Joined Amazon FAR as a resarch scientist!
[Jul 2025] Joined FAIR as a research scientist!
[Mar 2025] Accepted faculty offer from UMD!
Students
Publication
New York Smells: A Large Multimodal Dataset for Olfaction
Ege Ozguroglu, Junbang Liang, Ruoshi Liu, Mia Chiquier, Michael DeTienne, Wesley Wei Qian, Alexandra Horowitz, Andrew Owens, Carl Vondrick
arXiv 2026
Paper | Project Page | Data
Video Generators are Robot Policies
Junbang Liang, Pavel Tokmakov, Ruoshi Liu, Sruthi Sudhakar, Paarth Shah, Rares Ambrus, Carl Vondrick
arXiv 2026
Paper | Project Page | Video | Code
Self-Improving Autonomous Underwater Manipulation
Ruoshi Liu, Huy Ha, Mengxue Hou, Shuran Song, Carl Vondrick
ICRA 2025
Paper | Project Page | Video | Code
Differentiable Robot Rendering
Ruoshi Liu*, Alper Canberk*, Shuran Song, Carl Vondrick
CoRL 2024 (Oral)
Paper | Project Page | Video | Code
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 | Video | Code
EraseDraw: Learning to Draw Step-by-Step via Erasing Objects from Images
Alper Canberk, Maksym Bondarenko, Ege Ozguroglu, Ruoshi Liu, Carl Vondrick
ECCV 2024
Paper | Project Page | Code | Model Weights
Controlling the World by Sleight of Hand
Sruthi Sudhakar, Ruoshi Liu, Basile Van Hoorick, Carl Vondrick, Richard Zemel
ECCV 2024 (Oral, Best Paper Award Candidate)
Paper | Project Page
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 | Code
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 | 8-min Video | New Scientist Article
GES: Generalized Exponential Splatting for Efficient Radiance Field Rendering
Abdullah Hamdi, Luke Melas-Kyriazi, Guocheng Qian, Jinjie Mai, Ruoshi Liu, Carl Vondrick, Bernard Ghanem, Andrea Vedaldi
CVPR 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 (Highlight)
Paper | Project Page
Sin3DM: Learning a Diffusion Model from a Single 3D Textured Shape
Rundi Wu, Ruoshi Liu, Carl Vondrick, Changxi Zheng
ICLR 2024
Paper | Project Page | Code | Demo
Objaverse-XL: A Colossal Universe of 3D Objects
Matt Deitke, Ruoshi Liu, Matthew Wallingford, Huong Ngo, Oscar Michel, Aditya Kusupati, Alan Fan, Christian Laforte, Vikram Voleti, Samir Yitzhak Gadre, Eli VanderBilt, Aniruddha Kembhavi, Carl Vondrick, Georgia Gkioxari, Kiana Ehsani, Ludwig Schmidt, Ali Farhadi
NeurIPS 2023
Paper | Project Page | Code | Zero123-XL
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
Landscape Learning for Neural Network Inversion
Ruoshi Liu, Chengzhi Mao, Purva Tendulkar, Hao Wang, Carl Vondrick
ICCV 2023
Paper Blog Post
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
Learning the Predictability of the Future
Dídac Surís*, Ruoshi Liu*, Carl Vondrick
CVPR 2021
Paper Project Page
Machine Learning Forecasting of Active Nematics
Zhengyang Zhou, Chaitanya Joshi, Ruoshi Liu, Michael M. Norton, Linnea Lemma, Zvonimir Dogic, Michael F. Hagan, Seth Fraden, Pengyu Hong
Soft Matter 2021
Paper
Services
Reviewer
CVPR, ICCV, ECCV, ICLR, NeurIPS, RSS, CoRL, ICRA, ICML, AAAI, AISTATS, Siggraph, Siggraph Asia, TPAMI, IJCV, ACCV
Area Chair
ICLR, NeurIPS, CoRL
Workshop Organizer
NeurIPS 2026 Robot Learning with World Models, CoRL 2026 Scaling H2R, RSS 2026 Tactile Sensing for Robotic Foundation Models, CVPR 2026 ActiVis: Actionable Visual Perception for Robotics, CVPR 2026 Sense of Space: Multi-Sensory Modeling for Embodied Intelligence, CoRL 2025 Physical World Modeling, ICML 2025 Building Physically Plausible World Models, RSS 2025 Robotics World Modeling, RSS 2025 MultiSensory Robots with Multimodal Capabilities, CVPR 2025 4D Vision Workshop, NYC Computer Vision Day 2025, NYC Computer Vision Day 2023
Teaching
Robot Learning Seminar CMSC848X, Fall 2026
University of Maryland, College Park | Syllabus
Funding
Toyota Research Institute
Amazon Robotics
Other Things
My first name Ruoshi(若石), can be translated into “Like a Rolling Stone”.
My virtual meetings are sometimes interrupted by Pattie, a 5-year-old domestic shorthair.
I enjoy rock climbing, movies, museums, film and digital photography, and occasionally playing the guitar.
As a person, I feel that I’m so weird and complicated. But I love it.