Vincent Sitzmann is an Assistant Professor at MIT where he leads the Scene Representation Group. He received his PhD at Stanford University with Gordon Wetzstein and his Bachelor’s degree from the Technical University of Munich. Vincent’s research goal is to build machines that learn to understand and interact with the world autonomously by building “world models” - mental simulators that enable an agent to simulate what will happen next in their environment and as a consequence of their actions, a critical piece of AI and key in downstream applications in graphics, vision, and robotics.

Artem Lukoianov is a PhD student at MIT CSAIL working with Prof. Justin Solomon and Vincent. He graduated from the Swiss Federal Institute of Technology in Lausanne with a Master’s degree in Data Science, and from the Moscow Institute of Physics and Technology with an undergraduate degree in applied math.

He is interested in Machine Perception and Equivariant Representational Learning.

Ayush is a postdoctoral researcher at MIT CSAIL working with Bill Freeman, Josh Tenenbaum, and Vincent. He completed his Ph.D. at the Max Planck Institute for Informatics with Christian Theobalt. He received an Otto Hahn Medal from the Max Planck Society for his PhD.

His research develops methods for perceiving and recreating the 3D structure of the visual world from sparse image observations in a self-supervised manner.

He is now an Assistant Professor at the University of Cambridge, UK.

Boyuan Chen is a second-year PhD student working with Vincent and Prof. Russ Tedrake. Before joining MIT, he graduated from UC Berkeley where he researched on deep reinforcement learning and worked at Google X researching visual-language models for robot planning. Boyuan is a full-stack robotic enthusiast who has built many robots himself.

He is broadly interested in connecting deep learning with mathematical structures in decision making. In particular, he hopes to bridge 3D computer vision and robotics so intelligent robots can free humanity from tedious tasks.

Cameron graduated from UCSD for his undergraduate studies in computer science, and is currently working with Vincent and Ayush to develop scalable neural scene representations.

He is particularly interested in endowing models with 3D representations for both geometry and motion, with the ultimate goal of building rich backbones for sample-efficient learning of downstream tasks.

David is a PhD student at MIT CSAIL, advised by Vincent.

He graduated from Brown University with an undergraduate degree in computer engineering and is currently working at Common Sense Machines in Cambridge.

George is a first-year PhD student working with Prof. Antonio Torralba and Vincent.

He just finished his Master’s degree at Carnegie Mellon and previously did his undergrad at Louisiana Tech. He is interested in applying generative models to scene representations and neural rendering.

Ana Dodik is a PhD student and Presidential Fellow at MIT CSAIL working on neural representations for geometry processing.

Prior to joining MIT, she spent two years developing next-generation virtual presence at Meta. She graduated with a Master’s degree from ETH Zurich, where she spent a year collaborating with Disney Research Studios on problems at the intersection of machine learning and offline rendering. She also spent time as a research assistant at the Computer Vision and Geometry group at ETH Zurich and as a computer vision intern at Microsoft and Oculus.

Ali is a sophomore at MIT studying Electrical Engineering & Computer Science. She is working on a UROP with the Scene Representation Group in video generation and motion modelling. She previously worked in Marin Soljacic’s lab on understanding contrastive learning.

She is interested in understanding the nature of intelligence and vision.

Chonghyuk (Andrew) Song is a first-year PhD student at MIT CSAIL advised by Prof. Vincent Siztmann. Prior to joining MIT, he graduated with a Master’s degree from CMU, where he worked with Prof. Deva Ramanan and Prof. Jun-Yan Zhu on dynamic scene reconstruction from video.

Ishaan is a first-year PhD student at MIT CSAIL working with Prof. Vincent Sitzmann and Prof. Phillip Isola. Before MIT, he was an undergraduate student at Columbia University where he worked on 3D scene representations for predictive models of physical systems, and vision-and-language research.

He is interested in designing algorithms to learn models of control and dynamics from perception in open world scenes and the impact such models can have on robotic tasks that require dexterity and precision.

Kairo is a fourth year Undergraduate Student working towards his Bachelor’s degree in Artificial Intelligence and Decision Making. Prior to joining the group as an Undergraduate Researcher he completed two research internships at Google where he built models for Webpage Translation, and Video Question Answering.

As a part of the group Kairo worked with Ayush to develop general neural scene representations that can be adapted for a variety of downstream tasks and applications.

Lester is a PhD student and Presidential Fellow at MIT CSAIL working with Vincent Sitzmann and Josh Tenenbaum. Lester received his Bachelor’s degree in Computer Science from the University of Rochester with the highest honors in research.

Lester is interested in building inverse models that capture the rich and structured representation of our world from unstructured observation. To this end, his research draws ideas from vision+graphics, robotics, and computational cognitive science.

Amani is a visiting student working with Vincent on 3D reconstruction from single-image observations.

Previously, Amani completed his undergraduate studies at University of Delaware. Broadly, Amani is interested in out-of-distribution generalization, generative modelling, and inverse problems.

He is now pursuing his PhD at Harvard.

Eric is a PhD student at MIT CSAIL advised by Prof. Vincent Sitzmann. Before starting his PhD, he was an undergrad at Cornell University where he conducted research in computer vision, computer graphics and geometric deep learning. Eric’s research is supported by the NSF Graduate Research Fellowship Program.

Hyunwoo is a PhD student at MIT CSAIL, advised by Prof. Vincent Sitzmann. Before joining MIT, he earned his Master’s degree from Yonsei University, where he worked on equivariant generative modeling and 3D representations for robotic manipulation.

His research focuses on geometry-grounded representation learning for embodied agents. Hyunwoo’s overarching goal is to establish a foundational framework that enables intelligent systems to discover the underlying causal structures of the world through observing and interacting with their environment.

Isabella is an MEng student at MIT who graduated from MIT with bachelor’s degrees in EECS and math in 2024. She is interested in developing embodied agents with the rich 3D spatial reasoning capabilities of humans and animals, with an emphasis on developing learned representations of agent morphologies.

She is now pursuing her PhD at UC Berkeley.

Kiwhan is an undergraduate at MIT working with Vincent Sitzmann. Prior to joining the group, he was a student researcher at the MIT-IBM Watson AI Lab, where he worked on equivariant machine learning and graph representation learning.

His research goal is to build AI models that can understand, generate, and interact with the world. He is particularly focused on enhancing visual generative models to be more versatile, efficient, and generalizable.