2026-11-02 ~ 11-08 · Embodied AI
Generative · Personalization · AI Search · Infra · Embodied AI
- 1. UMI-Live for In-The-Wild Bimanual Robotics Data Collection · 📖 Deep dive
The most expensive part of teaching a robot a task is often collecting demonstrations: teleoperation means hauling the whole robot to each site. UMI lets a person demonstrate with a pair of handheld grippers instead…
Appeared in: 11-02
- 2. FORGE: Feasible Online Reduced-Order Reference Generation and Whole-Body Execution for Agile Humanoid Locomotion
Getting a humanoid to sprint, walk backwards, sidestep, spin in place and hop on one leg usually means preparing reference trajectories or training a separate policy for each behaviour. FORGE does it in two stages…
Appeared in: 11-02
- 3. Vector-Quantized World Model: Latent Feedback Motion Planning for Robot Manipulation
For a task like the Tower of Hanoi, where a robot must chain many moves, planning with a visual world model tends to drift further off the longer it plans. VQ-WM compresses images into a finite set of discrete states…
Appeared in: 11-02
- 4. Catch It All!: Generalizable Dynamic Catching with a Dexterous Hand
Catching thrown objects is hard for a humanoid because objects differ so much: plush toys barely bounce, chip bags deform, hard balls rebound on contact, and a humanoid's wrist torque is small enough that overly…
Appeared in: 11-02
- 5. METATRON: A Promptable Whole-Body Execution Layer for Humanoids
Walking, recovering from a shove, picking things up and sitting down usually each need their own trained humanoid controller, even though all of them rely on the same balance and whole-body coordination…
Appeared in: 11-02
- 6. ProWorld: Multi-View World Model with Proprioceptive Feedback for Closed-Loop Policy Evaluation
Evaluating robot policies by running trial after trial on a real robot is slow and expensive, so people want to use frames generated by a world model as the test environment. There are two difficulties…
Appeared in: 11-02
- 7. Cross-Controller Transfer via In-Context Behavior Adaptation
The same action command makes a robot move differently under different controllers: whether it controls joints or the end-effector, whether it sends positions or velocities…
Appeared in: 11-02
- 8. LocoManiLab: A Unified Testbed for Data, Policies, Controllers, and Deployment in Humanoid Loco-Manipulation
Research on humanoids that walk and manipulate at the same time is hard to compare, because every group uses different policies, controllers and tasks. LocoManiLab puts data collection, training…
Appeared in: 11-02
- 9. JEDI: Joint-Embedding Demonstration Compression for In-Context Imitation Learning
Getting a robot to do a new task from a few demonstrations without updating weights is limited above all by context length. One demonstration spans hundreds of steps of multi-view frames and still takes thousands of…
Appeared in: 11-02
- 10. AgiBot Innovation Day 2026: Full-Stack Releases for Real-World Embodied Deployment
At this year's Innovation Day, AgiBot proposed a new unit, Worken (effective intelligent work hours), meant to answer how much useful work robots actually do. AgiBot's analogy: steam engines were measured in…
Appeared in: 11-02