Rishabh Kabra @rkabra.bsky.social · 30/11/2025The sandwich technique came up again. So I decided to frame it properly 010
Rishabh Kabra @rkabra.bsky.social · 04/08/2025I had a score disappear even when the reviewer said they will maintain their score. So it has likely nothing to do with whether the score changed. 040
Reposted by Rishabh KabraMehdi S. M. Sajjadi @msajjadi.com · 10/07/2025Scaling 4D Representations Self-supervised learning from video does scale! In our latest work, we scaled masked auto-encoding models to 22B params, boosting performance on pose estimation, tracking & more. Paper: arxiv.org/abs/2412.15212 Code & models: github.com/google-deepmind/representations4d 0208
Rishabh Kabra @rkabra.bsky.social · 30/06/2025Veo 3 goes to Glastonbury: www.youtube.com/watch?v=aKkr... @googleuk.bsky.socialyoutube.comVeo 3: Celebrating festival seasonYouTube video by Google UK 010
Reposted by Rishabh KabraMehdi S. M. Sajjadi @msajjadi.com · 13/02/2025Generative Video Diffusion: does a model trained with this objective learn better features compared to image generation? We investigated this question and more in our latest work, please check it out! *From Image to Video: An Empirical Study of Diffusion Representations* arxiv.org/abs/2502.07001 062
Rishabh Kabra @rkabra.bsky.social · 11/12/2024A self-supervised video representation model that allows visual tokens to move “off-the-grid” to represent scene elements consistently as they move across the image plane. We evaluate on downstream tasks including point tracking, monocular depth estimation, and object tracking. moog-paper.github.iomoog-paper.github.ioMoving Off-the-Grid: Scene-Grounded Video RepresentationsMoving Off-the-Grid: Scene-Grounded Video Representations 010
Rishabh Kabra @rkabra.bsky.social · 11/12/2024*Moving Off-the-Grid: Scene-Grounded Video Representations*. Thursday afternoon poster. 110
Rishabh Kabra @rkabra.bsky.social · 11/12/2024We learn per-object tokens (Neural Assets) that disentangle appearance and 3D pose from multi-object scenes. A sequence-of-tokens format allows us to reuse the text-to-image architecture of existing generative models. neural-assets-paper.github.ioneural-assets-paper.github.ioNeural AssetsNeural Assets 110
Rishabh Kabra @rkabra.bsky.social · 11/12/2024*Neural Assets: 3D-Aware Multi-Object Scene Synthesis with Image Diffusion Models*. Thursday morning poster. 110
Rishabh Kabra @rkabra.bsky.social · 11/12/2024I’m hanging out at NeurIPS this week. Come check out my co-authors’ presentations of the following Spotlight papers! 110
