{"ID":2884727,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2508.06266","arxiv_id":"2508.06266","title":"ADPro: a Test-time Adaptive Diffusion Policy via Manifold-constrained Denoising and Task-aware Initialization for Robotic Manipulation","abstract":"Diffusion policies have recently emerged as a powerful class of visuomotor controllers for robot manipulation, offering stable training and expressive multi-modal action modeling. However, existing approaches typically treat action generation as an unconstrained denoising process, ignoring valuable a priori knowledge about geometry and control structure. In this work, we propose the Adaptive Diffusion Policy (ADP), a test-time adaptation method that introduces two key inductive biases into the diffusion. First, we embed a geometric manifold constraint that aligns denoising updates with task-relevant subspaces, leveraging the fact that the relative pose between the end-effector and target scene provides a natural gradient direction, and guiding denoising along the geodesic path of the manipulation manifold. Then, to reduce unnecessary exploration and accelerate convergence, we propose an analytically guided initialization: rather than sampling from an uninformative prior, we compute a rough registration between the gripper and target scenes to propose a structured initial noisy action. ADP is compatible with pre-trained diffusion policies and requires no retraining, enabling test-time adaptation that tailors the policy to specific tasks, thereby enhancing generalization across novel tasks and environments. Experiments on RLBench, CALVIN, and real-world datasets show that ADPro, an implementation of ADP, improves success rates, generalization, and sampling efficiency, achieving up to 25% faster execution and 9% points over strong diffusion baselines.","short_abstract":"Diffusion policies have recently emerged as a powerful class of visuomotor controllers for robot manipulation, offering stable training and expressive multi-modal action modeling. However, existing approaches typically treat action generation as an unconstrained denoising process, ignoring valuable a priori knowledge a...","url_abs":"https://arxiv.org/abs/2508.06266","url_pdf":"https://arxiv.org/pdf/2508.06266v2","authors":"[\"Zezeng Li\",\"Rui Yang\",\"Ruochen Chen\",\"ZhongXuan Luo\",\"Liming Chen\"]","published":"2025-08-08T12:34:26Z","proceeding":"cs.RO","tasks":"[\"cs.RO\"]","methods":"[\"Diffusion Model\",\"LoRA\"]","has_code":false}