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
Trains end-to-end driving without human trajectory supervision by decoupling perception and action: DriveVFM distills multiple frozen vision foundation models into a single camera backbone, and DriveRL trains a privileged closed-loop RL teacher whose rollouts supervise a camera-only planner, yielding state-of-the-art closed-loop benchmark results.
Evaluates a weak teacher's RL-induced policy shift on the student's own rollouts and amplifies verifier-supported updates so stronger models can learn from weaker supervisors and surpass them. It rescales only verifier-supported policy-gradient components to preserve optimization fixed points while accelerating learning, reducing student updates versus standard RL or distillation.
Combines sparse verifier outcomes with dense privileged‑hindsight token scoring to learn an outcome‑calibrated, normalized distribution over complete responses for on‑policy self‑improvement. Key features: sign‑gated guidance (retain/reverse/disable per verifier advantage), profiled trajectory balance with one log‑partition per rollout group, and explicit correction against false‑positive self‑guidance.