arXiv Machine Learning October 8, 2026 By Xiao Zhang, Yuxin Chen, Zhixuan Liang, Guojian Zhan, Chenran Li, Chenfeng Xu, Masayoshi Tomizuka, Yiheng Li

Immiscible Diffusion Policy: Preserving Multimodal Robot Actions through Label-Free Noise Assignment

Read the original on arXiv Machine Learning →

The paper introduces Immiscible Diffusion Policy, a label‑free training add‑on that prevents diffusion policies from collapsing to a single action modality. By assigning action‑noise pairs, it preserves distinct noise‑to‑action routes without altering the policy architecture or inference. Experiments on five simulated and two real‑world humanoid manipulation tasks show significant improvements in maintaining multimodal action distributions, increasing non‑dominant modality proportions by up to 14.6× and recovering missing modalities in four‑modality tasks.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

Hugging Face Trending Papers

Oct 7

Immiscible Diffusion Policy: Preserving Multimodal Robot Actions through Label-Free Noise Assignment

When diffusion policies were first introduced, they were expected to recover multi-modal action distributions. However, we find this expectation does not always hold, as diffusion policies often colla...

diffusion robotics multimodal

arXiv AI

Jun 16

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

arXiv:2512. 07212v3 Announce Type: replace Abstract: Imitation learning with diffusion models has advanced robotic control by capturing the multi-modal action distributions.

By Zhaoyang Liu, Mokai Pan, Zhongyi Wang, Kaizhen Zhu, Haotao Lu, Haipeng Zhang, Jingya Wang, Ye Shi

diffusion robotics multimodal benchmarks

arXiv AI

Jul 21

Asynchronous Multimodal Diffusion Policy Composition via Latency-Aware Guidance Fusion

arXiv:2607. 17257v1 Announce Type: cross Abstract: Diffusion policies have shown strong potential for robotic imitation learning, and recent extensions incorporate additional modalities to improve manipulation performance.

By Zihao He, Hongjie Fang, Shirun Tang, Cewu Lu, Haoshu Fang

diffusion robotics multimodal

arXiv AI

Jun 11

Ambient Diffusion Policy: Imitation Learning from Suboptimal Data in Robotics

arXiv:2606. 12365v1 Announce Type: cross Abstract: We propose Ambient Diffusion Policy, a simple and principled method for imitation learning from suboptimal data in robotics.

By Adam Wei, Nicholas Pfaff, Thomas Cohn, Arif Kerem Day{\i}, Constantinos Daskalakis, Giannis Daras, Russ Tedrake

diffusion robotics data-engineering

Hugging Face Trending Papers

Jun 10

Ambient Diffusion Policy: Imitation Learning from Suboptimal Data in Robotics

We propose Ambient Diffusion Policy, a simple and principled method for imitation learning from suboptimal data in robotics. High-quality, task-specific robot data is expensive and time-consuming to collect, while suboptimal datasets with lower-quality or out-of-distribution demonstrations are abundant.

diffusion robotics data-engineering

arXiv Machine Learning

Jun 8

SERNF: Sample-Efficient Real-World Dexterous Policy Fine-Tuning via Action-Chunked Critics and Normalizing Flows

arXiv:2602. 09580v4 Announce Type: replace-cross Abstract: Real-world fine-tuning of dexterous manipulation policies remains challenging due to limited real-world interaction budgets and highly multimodal action distributions.

By Chenyu Yang, Denis Tarasov, Davide Liconti, Romain Guntz, Hehui Zheng, Robert K. Katzschmann

diffusion robotics fine-tuning multimodal

One email a morning, machine-written

Related stories

Immiscible Diffusion Policy: Preserving Multimodal Robot Actions through Label-Free Noise Assignment

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

Asynchronous Multimodal Diffusion Policy Composition via Latency-Aware Guidance Fusion

Ambient Diffusion Policy: Imitation Learning from Suboptimal Data in Robotics

Ambient Diffusion Policy: Imitation Learning from Suboptimal Data in Robotics

SERNF: Sample-Efficient Real-World Dexterous Policy Fine-Tuning via Action-Chunked Critics and Normalizing Flows