TheMachine Press

A daily newspaper for the age of artificial intelligence.

Morning editionPermanent story

robotics

Two Robot Arms Predicted the Scene Together

Jointly denoising actions and future 3D tracks improved bimanual manipulation.

Published Updated Story ID: mp-2026-09-23-011
Read the complete editionStory JSON

Summary

Jointly denoising actions and future 3D tracks improved bimanual manipulation.

JAMB generates two-arm actions and future three-dimensional point tracks together, letting each evolving hypothesis refine the other. Across 16 simulated tasks, the authors report 83.4% average success, 23.9 percentage points above the strongest evaluated baseline. On three real-world tasks, it beat action-only and auxiliary-geometry methods by 50.0 and 21.2 points. The gains come from the reported task suite and do not establish general dexterity.

Why it matters

Jointly denoising actions and future 3D tracks improved bimanual manipulation.

Limits and context

  • On three real-world tasks, it beat action-only and auxiliary-geometry methods by 50.0 and 21.2 points.
  • The gains come from the reported task suite and do not establish general dexterity.

Key claims

  1. Jointly denoising actions and future 3D tracks improved bimanual manipulation.

    Qualification: On three real-world tasks, it beat action-only and auxiliary-geometry methods by 50.0 and 21.2 points.

    Evidence: source-2026-09-23-011

Sources

  1. arXiv preprint 2609.25322arXiv · primary research

Corrections

No corrections have been recorded for this story.