This Week in New Models: RoboJEPA, Long-WAM, VioLA and 4 More to Know
TheTuringPost · x · 2026-10-14
Turing Post rounds up seven new models worth knowing this week, with the accompanying image detailing RoboJEPA's architecture (frozen V-JEPA 2.1 visual encoder plus a trainable predictor supporting K-step autoregressive rollout with KV cache):
- RoboJEPA: latent world models trained across 12 robotic embodiments, with prediction accuracy linked to planning performance
- Long-WAM: world-action model using longer visual histories for better robot control
- VioLA: generalist humanoid control model learning body and hand movements mostly from human recordings
- UNITAS: 3D-native world-action model representing observations, actions, and scene changes in a shared 3D space
- DreamTrue: world model trained to predict when an action will go wrong
- Kandinsky 6.0 Video: open video generation with synchronized audio, speech, and lip sync
- MiMo-V2.6: omni-modal family exploring scaling RL toward self-improvement
Related event: Turing Post Weekly: Robotics World Models Take Center Stage(3 posts)→
More from Embodied
- DynaRobotics' robot Taku rings the Nasdaq opening bell — chris_j_paxton · 2026-10-14
- VAP-TAMP wins IROS best paper: VLMs help robots handle surprises — chris_j_paxton · 2026-10-14
- NAVER's WATCH: Cross-Video Human-Video Pretraining Lifts Robot Success Rate to 77.7% — naver-ai · 2026-10-14
- LeRobot adds remote inference via Zenoh: robot stays light, policy runs on cloud GPU — kamathsblog · 2026-10-14
- Robot Dog Tries to Climb Its Own Back: Conitzer's Latest Funny AI Fail — conitzer · 2026-10-14
- XPENG's AUGUstus VLA model hits SOTA on NAVSIM and deploys on real vehicles at 12Hz — XPENG-AI · 2026-10-14