Trains a world-action model that predicts future visual states to guide zero-shot robotic manipulation; introduces CoAE, SVP, IDM and KASO to pretrain generative and action components from scratch on manipulation data, scaling up to 30,000 hours and improving zero-shot success.
[next-mdx-remote-client] error compiling MDX: Unexpected character `2` (U+0032) before name, expected a character that can start a name, such as a letter, `$`, or `_` More information: https://mdxjs.com/docs/troubleshooting-mdx
Helps general coding agents turn 3D perception readings into spatial conclusions using persistent scene memory and plain-language interpretation. It improves open- and closed-model results on MMSI-Bench and ReVSI.
Predicts future egocentric video from actions for human and robot embodiments. It represents movement with camera poses and manipulation with projected skeletons, trained on a unified collection of human and robot experience.
Helps GUI agents focus on the signals needed for each action by dynamically filtering screenshots, audio, video, and device state. FocusGUI trains from action supervision while keeping the backbone frozen.