DECO: Decoupled Multimodal Diffusion Transformer for Bimanual Dexterous Manipulation with a Plugin Tactile Adapter
arXiv:2602.05513
The paper introduces DECO, a diffusion‑based transformer that separately processes vision, proprioception, and tactile inputs for bimanual dexterous robot manipulation, and includes a lightweight tactile adapter for efficient parameter tuning. It also provides a new 50‑hour multimodal dataset (DECO‑50) and demonstrates improved real‑world performance on dual‑arm robots.
Abstract
Bimanual dexterous manipulation relies on integrating multimodal inputs to perform complex real-world tasks. To address the challenges of effectively combining these modalities, we propose DECO, a decoupled multimodal diffusion transformer that disentangles vision, proprioception, and tactile signals through specialized conditioning pathways, enabling structured and controllable integration of multimodal inputs, with a lightweight adapter for parameter-efficient injection of additional signals. Alongside DECO, we release DECO-50 dataset for bimanual dexterous manipulation with tactile sensing, consisting of 50 hours of data and over 5M frames, collected via teleoperation on real dual-arm robots. We train DECO on DECO-50 and conduct extensive real-world evaluation with over 2,000 robot rollouts. Experimental results show that DECO achieves the best performance across all tasks, with a 72.25% average success rate and a 21% improvement over the baseline. Moreover, the tactile adapter brings an additional 10.25% average success rate across all tasks and a 20% gain on complex contact-rich tasks while tuning less than 10% of the model parameters.
25 pages, 8 figures. Project Page: https://baai-humanoid.github.io/DECO-webpage/