@DavidCharatan

CS PhD Student at MIT

 Cambridge, MA
davidcharatan.com
Joined September 2016
  • Tweets25
  • Following104
  • Followers317
David Charatan retweeted
Eric Ming Chen@ericmchen1Oct 20
If video models scale like LLMs, they'll soon generate a perfect video plan for any embodied task. Do we need anything else? Introducing Mirror, which learns to follow these plans just by practicing, and even crafts an iron pickaxe in Minecraft w/o rewards or action labels! (1/n)
9
44
14
379
47,683
David Charatan retweeted
George Cazenavette@GCazenavetteSep 10
We discovered that our latest Dataset Distillation project can be used to create some beautiful synthetic images based on an artist's body of work! Come see us at the @eccvconf Art Gallery starting today! Explanation and some of my favorites in thread below: 1/ (Claude Monet)
5
17
4
93
26,215
The code for MilliVid is now public! github.com/dcharatan/millivi…

GitHub - dcharatan/millivid: [to appear at NeurIPS 2026] Official implementation of "MilliVid:...

[to appear at NeurIPS 2026] Official implementation of "MilliVid: Adaptive Latents for Long-Range Consistency in Video Generation" - dcharatan/millivid

github.com
6
2
40
13,772
David Charatan retweeted
Vincent Sitzmann
@vincesitzmannJun 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/#
11
72
7
438
75,701
Happy to finally share our latest work on Dataset Distillation! "Dataset Distillation for Pre-Trained Self-Supervised Vision Models," set to appear at #NeurIPS 2025! We learn 1 image per class to train linear heads for pre-trained models. linear-gradient-matching.git… 1/6

Dataset Distillation for Pre-Trained Self-Supervised Vision Models

Distilling image datasets to a single sample per class to train classifiers on top of pre-trained self-supervised vision models.

linear-gradient-matching.github.io
1
9
2
31
4,597
David Charatan retweeted
Lester Li
@sizhe_lester_li27 Jun 2025
Now in Nature! 🚀 Our method learns a controllable 3D model of any robot from vision, enabling single-camera closed-loop control at test time! This includes robots previously uncontrollable, soft, and bio-inspired, potentially lowering the barrier of entry to automation! Paper: nature.com/articles/s41586-0… (1/n)
5
68
11
423
100,517
David Charatan retweeted
Boyuan Chen
@BoyuanChen03 Jul 2024
Introducing Diffusion Forcing, which unifies next-token prediction (eg LLMs) and full-seq. diffusion (eg SORA)! It offers improved performance & new sampling strategies in vision and robotics, such as stable, infinite video generation, better diffusion planning, and more! (1/8)
13
209
25
1,348
208,954
Announcing (fashionably late) our #CVPR2024 paper on GenAI detection! with @AvneeshSud, Thomas Leung, and @b_usmn Fake-Inversion: Learning to Detect Images from Unseen Models by Inverting Stable Diffusion fake-inversion.github.io/ More info in 🧵 1/7
1
8
1
17
2,577
Introducing “FlowMap”, the first self-supervised, differentiable structure-from-motion method that is competitive with conventional SfM like Colmap! cameronosmith.github.io/flow… IMO this solves a major missing piece for internet-scale training of 3D Deep Learning methods. 1/n
11
101
13
606
128,720
Announcing the 1st Workshop on Dataset Distillation @CVPR 2024! #CVPR2024 sites.google.com/view/dd-cvp… More info in 🧵 1/4
2
27
4
106
41,928
Introducing pixelSplat: feed-forward Gaussian splats from image pairs! Led by @DavidCharatan and @sizhe_lester_li, collaborating with @taiyasaki! We propose a memory-efficient, fast and editable alternative to pixelNeRF based on 3D Gaussian Splatting! davidcharatan.com/pixelsplat… 1/n
8
45
6
269
47,687
Load more