diffusion-policy

Tag

Cards List
#diffusion-policy

Diffusion Policy Optimization without Drifting Apart

arXiv cs.LG · 16h ago Cached

DiPOD stabilizes diffusion policy optimization by interleaving self-distillation with policy-gradient updates to maintain a tight ELBO, preventing the double-drift phenomenon and achieving higher rewards in both language and continuous control tasks.

0 favorites 0 likes
#diffusion-policy

@RuohanZhang76: Excited to introduce StereoPolicy, led by @EvansXuHan. StereoPolicy is an effective way to add geometric cues to modern…

X AI KOLs Following · 2026-06-03 Cached

Introduces StereoPolicy, a framework that leverages synchronized stereo image pairs to improve geometric reasoning for robot manipulation policies, avoiding the fragility of RGB-D and point clouds. It integrates with diffusion-based and vision-language-action policies, showing consistent improvements in simulation and real-world tasks.

0 favorites 0 likes
#diffusion-policy

From Noise to Control: Parameterized Diffusion Policies

arXiv cs.AI · 2026-06-02 Cached

This paper introduces Parameterized Diffusion Policy (PDP), a framework that makes diffusion policies controllable by conditioning on low-dimensional latent parameters, enabling smooth behavior interpolation and adaptation without retraining. It demonstrates improved performance on complex multimodal robot tasks in simulation and real-world experiments.

0 favorites 0 likes
#diffusion-policy

Scaling World-Model Reinforcement Learning Through Diffusion Policy Optimization

arXiv cs.LG · 2026-05-27 Cached

Proposes Model-Based Diffusion Policy Optimization (MBDPO), a framework that unifies search and policy optimization in world models using diffusion policy representations, achieving consistent scaling behavior and superior performance across offline and online reinforcement learning tasks.

0 favorites 0 likes
#diffusion-policy

Frequency-Guided Action Diffusion via Sub-Frequency Manifold Traversal

Hugging Face Daily Papers · 2026-05-27 Cached

This paper introduces the Frequency Guidance Operator (FGO), a method for diffusion policies that smooths action generation by steering noisy samples through intermediate sub-frequency manifolds, improving performance on robotic manipulation tasks.

0 favorites 0 likes
← Back to home

Submit Feedback