DreamX: one latent action space for humans and robots
This is a AI post classified by AGK Intelligence as AI video (a model release), kept by the AI Radar because it carries real work, not commentary.
DreamX: one latent action space for humans and robots It repurposes a pretrained video diffusion model to learn compact latent actions (300x compression) that capture motion alone, enabling any-to-any video transfer and zero-shot human-to-robot action transfer.
Posted by DailyPapers (22.4k followers) 36 min ago · 1 likes · 361 views · view the original post on X. Kept by the AI Radar as AI video.
More AI work like this
- read this again: AI can now vectorize any video into layers for pixel-level editing — @EXM7777
- AI isn't just generating videos anymore. — @minchoi
- Behind the scenes of a fashion campaign made with Kling 4.0. — @Kling_ai
- Okay just approved my Grok Bot Video Studios proposal that it came back with in… — @MichaelGannotti
- New improved Grok Bot Video Studio prompt testing out this morning: — @MichaelGannotti
- If you still think AI video is a slot machine, try sending this to Claude Code: — @Voxyz_ai
- it's so funny — @itsolelehmann
- 90 minutes. One fantasy world. Built scene by scene through PixVerse Canvas. — @PixVerse
Every post is read and classified by AGK Intelligence: what it is, which market it belongs to, and whether the link is a real tool. 65.2k posts from 5k X accounts over the last 14 days, 10.6k tools, 19 markets. New posts are collected several times an hour and the full ranking is recomputed every hour — last update 2026-11-07 16:45 UTC. Full method.