Transformer Transformer: A Unified Model for Motion-Conditioned Robot Co-design
transformer-transformer.github.io · 2,707 words · saved by 5 readers
Transformer Transformer: A Unified Model for Motion-Conditioned Robot Co-design. Project website.
Transformer Transformer Huy Ha, Karen Liu, Shuran Song Conference on Robot Learning 2026 Not all robots are created equal Not all robots are created equal — but what if you could design one for a specific task? We propose Transformer Transformer, a unified model that does exactly this: hand it a manipulation demonstration, and it generates a complete robot — every link, joint, motor, and inertial property — optimized for that motion. We fabricated one such design for cloth flinging on an ALOHA2 bimanual platform; it reduced tracking error by 73% and max joint speed by 30% versus the…
saved by
related reading
- Diffusion Policy: Visuomotor Policy Learning via Action Diffusiondiffusion-policy.cs.columbia.edu
- State of Robot Learning, December 2025vedder.io
- Differentiable Robot Renderingdrrobot.cs.columbia.edu
- A Steerable Model with Emergent Capabilitiespi.website
- How Claude Performs on Robotics Tasks \ Anthropicanthropic.com
- Generating Robot Hands from Human Demonstrationsarxiv.org
- BeyondMimic: From Motion Tracking to Versatile Humanoid Control via Guided Diffusionarxiv.org
- UniTracker: Learning Universal Whole-Body Motion Tracker for Humanoid Robotsarxiv.org
- GitHub - adam-maj/robotics: A deep dive on the history of robotics and the future of humanoidsgithub.com
- A Careful Examination of Large Behavior Models for Multitask Dexterous Manipulationtoyotaresearchinstitute.github.io
- [2509.22407] EMMA: Generalizing Real-World Robot Manipulation via Generative Visual Transferarxiv.org
- How Can We Make Robotics More like Generative Modeling? | Eric Jangevjang.com