Vincent Sitzmann

@vincesitzmann

Building AI that learns by interacting with the world. Associate Professor @ MIT, leading the Scene Representation Group (scenerepresentations.org).

Cambridge, Massachusetts

vincentsitzmann.com

Replies Reposts Media

Pinned
Vincent Sitzmann
@vincesitzmann
Jun 8
Introducing MilliVid, our new method for long-context video generation! MilliVid creates videos that are consistent over long time spans, without using retrieval heuristics or 3D maps! (1/n) davidcharatan.com/millivid/#
00:00
11
Vincent Sitzmann
@vincesitzmann
Sep 3
This looks like a really cool product, congrats to the @theworldlabs team!
World Labs
@theworldlabs
Sep 1
Introducing Atlas: The world's first multimodal world model that generates image and video frames with pixel-perfect camera control and reconstructs them in 3D. Model the world, move the camera, and simulate space & time.
00:00
4
Vincent Sitzmann
@vincesitzmann
Aug 25
I was a guest on the @MIT_CSAIL podcast to discuss robots, AI, and what the near future might look like. @klgiven did a great job steering the conversation, and I think much of our chat is accessible to non-experts - hope you find it interesting! bit.ly/4zruZdt Also on
Why AI Still Can't Load the Dishwasher | CSAIL Alliances
From cap.csail.mit.edu
1
Vincent Sitzmann
@vincesitzmann
Jul 15
Congrats - this looks super exciting, Russ & team!!
Russ Tedrake
@RussTedrake
Jul 15
In January, I started "building something new" with an incredible team. Today I finally get to share some first details about what we've been building. We've called it Walden Robotics (waldenrobotics.com). I thought long and hard about my own reasons for starting this
2
Vincent Sitzmann
@vincesitzmann
Jun 23
We are open-sourcing a fine-tuned video policy + pre-trained IDM! In our paper, we demonstrate that this paradigm has the potential for plug-and-play manipulation across embodiments - very exciting :)
Lester Li
@sizhe_lester_li
Jun 23
Robot learning is moving beyond policies built for one robot, one scene, one task. At MIT, we’re exploring a different path: turning video world models into embodiment-agnostic robot policies. Introducing VERA: a 14B video-to-action system that controls robots across
00:00
1