Sample from What You See: Visuomotor Policy Learning via Diffusion Bridge with Observation-Embedded Stochastic Differential Equation

• URL: http://arxiv.org/abs/2512.07212v1
• Date: Mon, 08 Dec 2025 06:47:32 GMT
• Title: Sample from What You See: Visuomotor Policy Learning via Diffusion Bridge with Observation-Embedded Stochastic Differential Equation
• Abstract summary: Imitation learning with diffusion models has advanced robotic control by capturing multi-modal action distributions.<n>Existing approaches treat observations as high-level conditioning inputs to the denoising network, rather than integrating them into the dynamics of the diffusion process itself.<n>We introduce BridgePolicy, a generative visuomotor policy that embeds observations within the differential equation via a diffusion-bridge formulation.
• Score: 28.95872004551021
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Imitation learning with diffusion models has advanced robotic control by capturing multi-modal action distributions. However, existing approaches typically treat observations as high-level conditioning inputs to the denoising network, rather than integrating them into the stochastic dynamics of the diffusion process itself. As a result, sampling must begin from random Gaussian noise, weakening the coupling between perception and control and often yielding suboptimal performance. We introduce BridgePolicy, a generative visuomotor policy that explicitly embeds observations within the stochastic differential equation via a diffusion-bridge formulation. By constructing an observation-informed trajectory, BridgePolicy enables sampling to start from a rich, informative prior rather than random noise, substantially improving precision and reliability in control. A key challenge is that classical diffusion bridges connect distributions with matched dimensionality, whereas robotic observations are heterogeneous and multi-modal and do not naturally align with the action space. To address this, we design a multi-modal fusion module and a semantic aligner that unify visual and state inputs and align observation and action representations, making the bridge applicable to heterogeneous robot data. Extensive experiments across 52 simulation tasks on three benchmarks and five real-world tasks demonstrate that BridgePolicy consistently outperforms state-of-the-art generative policies.

Related papers

• PriGo: Test-Time Primitive Guidance to Diffusion and Flow Policies for Adaptive Robotic Manipulation [28.358317763869664]
  PriGo is a primitive-guided test-time adaptive framework for robust robotic manipulation.<n>We introduce PANet, a lightweight primitive prediction module that infers primitive distributions directly from observations.<n>Unlike prior primitive-conditioned approaches, PriGo operates entirely at test time and can be seamlessly integrated into pretrained diffusion and flow policies.
  arXiv  Detail & Related papers  (2026-07-08T07:08:11Z)
• DiffusionVS: A Generative Framework for Robust Visual Servoing Based on Diffusion Policy [10.755467302335617]
  Visual servoing is a fundamental technique in robotic manipulation and navigation.<n> Diffusion Policy maintains temporal consistency by predicting action sequences and improves robustness through implicit data augmentation.<n>Online training paradigm is adopted, continuously expanding the diversity of training data through interactive experience collection.
  arXiv  Detail & Related papers  (2026-06-17T08:06:05Z)
• Ada3Drift: Adaptive Training-Time Drifting for One-Step 3D Visuomotor Robotic Manipulation [53.750389076941396]
  Diffusion-based visuomotor policies capture multimodal action distributions through iterative denoising, but their high inference latency limits real-time robotic control.<n>We propose Ada3Drift, which learns a training-time drifting field that attracts predicted actions toward expert demonstration modes.<n>Ada3Drift achieves state-of-the-art performance while requiring $10times$ fewer function evaluations than diffusion-based alternatives.
  arXiv  Detail & Related papers  (2026-03-12T14:36:53Z)
• Enhancing Adversarial Transferability by Balancing Exploration and Exploitation with Gradient-Guided Sampling [82.52485740425321]
  Adrial attacks present a critical challenge to deep neural networks' robustness.<n> transferability of adversarial attacks faces a dilemma between Exploitation (maximizing attack potency) and Exploration (enhancing cross-model generalization)
  arXiv  Detail & Related papers  (2025-11-01T05:43:47Z)
• Dual-Stream Diffusion for World-Model Augmented Vision-Language-Action Model [62.889356203346985]
  We propose DUal-STream diffusion (DUST), a world-model augmented VLA framework that handles the modality conflict.<n>DUST achieves up to 6% gains over a standard VLA baseline and implicit world-modeling methods.<n>On real-world tasks with the Franka Research 3, DUST outperforms baselines in success rate by 13%.
  arXiv  Detail & Related papers  (2025-10-31T16:32:12Z)
• Acoustic Waveform Inversion with Image-to-Image Schrödinger Bridges [0.0]
  We introduce a conditional Image-to-Image Schr"odinger Bridge (c$textI2textSB$) framework to generate high-resolution samples.<n>Our experiments demonstrate that the proposed solution outperforms our reimplementation of conditional diffusion model.
  arXiv  Detail & Related papers  (2025-06-18T10:55:26Z)
• Consistent World Models via Foresight Diffusion [56.45012929930605]
  We argue that a key bottleneck in learning consistent diffusion-based world models lies in the suboptimal predictive ability.<n>We propose Foresight Diffusion (ForeDiff), a diffusion-based world modeling framework that enhances consistency by decoupling condition understanding from target denoising.
  arXiv  Detail & Related papers  (2025-05-22T10:01:59Z)
• Prior Does Matter: Visual Navigation via Denoising Diffusion Bridge Models [17.339359071659494]
  We propose a novel visual navigation framework leveraging the denoising diffusion bridge models named NaviBridger.<n>This approach enables action generation by initiating from any informative prior actions, enhancing guidance and efficiency in the denoising process.<n>Experiments in both simulated and real-world indoor and outdoor scenarios demonstrate that NaviBridger accelerates policy inference and outperforms the baselines in generating target action sequences.
  arXiv  Detail & Related papers  (2025-04-14T09:42:35Z)
• Dita: Scaling Diffusion Transformer for Generalist Vision-Language-Action Policy [73.75271615101754]
  We present Dita, a scalable framework that leverages Transformer architectures to directly denoise continuous action sequences.<n>Dita employs in-context conditioning -- enabling fine-grained alignment between denoised actions and raw visual tokens from historical observations.<n>Dita effectively integrates cross-embodiment datasets across diverse camera perspectives, observation scenes, tasks, and action spaces.
  arXiv  Detail & Related papers  (2025-03-25T15:19:56Z)
• Generalized Interpolating Discrete Diffusion [65.74168524007484]
  Masked diffusion is a popular choice due to its simplicity and effectiveness.<n>We generalize a new family of general interpolating discrete diffusion (GIDD) which offers greater flexibility in the design of the noising processes.<n>Exploiting GIDD's flexibility, we explore a hybrid approach combining masking and uniform noise, leading to improved sample quality.
  arXiv  Detail & Related papers  (2025-03-06T14:30:55Z)
• Controllable Motion Generation via Diffusion Modal Coupling [19.534234002173314]
  We propose a novel framework that enhances controllability in diffusion models by leveraging multi-modal prior distributions.<n>We evaluate our approach on motion prediction using a dataset and multi-task control in Maze2D environments.
  arXiv  Detail & Related papers  (2025-03-04T07:22:34Z)
• DPBridge: Latent Diffusion Bridge for Dense Prediction [49.1574468325115]
  We introduce DPBridge, the first latent diffusion bridge framework for dense prediction tasks.<n>Our method consistently achieves superior performance, demonstrating its effectiveness and capability generalization under different scenarios.
  arXiv  Detail & Related papers  (2024-12-29T15:50:34Z)
• Diffusion Bridge Implicit Models [25.213664260896103]
  Denoising diffusion bridge models (DDBMs) are a powerful variant of diffusion models for interpolating between two arbitrary paired distributions.<n>We take the first step in fast sampling of DDBMs without extra training, motivated by the well-established recipes in diffusion models.<n>We induce a novel, simple, and insightful form of ordinary differential equation (ODE) which inspires high-order numerical solvers.
  arXiv  Detail & Related papers  (2024-05-24T19:08:30Z)
• CamoDiffusion: Camouflaged Object Detection via Conditional Diffusion Models [72.93652777646233]
  Camouflaged Object Detection (COD) is a challenging task in computer vision due to the high similarity between camouflaged objects and their surroundings. We propose a new paradigm that treats COD as a conditional mask-generation task leveraging diffusion models. Our method, dubbed CamoDiffusion, employs the denoising process of diffusion models to iteratively reduce the noise of the mask.
  arXiv  Detail & Related papers  (2023-05-29T07:49:44Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.