Related papers: DiSPo: Diffusion-SSM based Policy Learning for Coa…

Diffusion policies have demonstrated strong performance in generative modeling, making them promising for robotic manipulation guided by natural language instructions. However, generalizing language-conditioned diffusion policies to…

Diffusion policies generate robot motions by learning to denoise action-space trajectories conditioned on observations. These observations are commonly streams of RGB images, whose high dimensionality includes substantial task-irrelevant…

Diffusion models achieve impressive performance in human motion generation. However, current approaches typically ignore the significance of frequency-domain information in capturing fine-grained motions within the latent space (e.g., low…

Diffusion models have achieved impressive results in generative tasks such as text-to-image synthesis, yet they often struggle to fully align outputs with nuanced user intent and maintain consistent aesthetic quality. Existing…

Reinforcement learning (RL) struggles to scale to large, combinatorial action spaces common in many real-world problems. This paper introduces a novel framework for training discrete diffusion models as highly effective policies in these…

Visual-motor policy learning has advanced with architectures like diffusion-based policies, known for modeling complex robotic trajectories. However, their prolonged inference times hinder high-frequency control tasks requiring real-time…

Popular reinforcement learning (RL) algorithms tend to produce a unimodal policy distribution, which weakens the expressiveness of complicated policy and decays the ability of exploration. The diffusion probability model is powerful to…

Diffusion models, praised for their success in generative tasks, are increasingly being applied to robotics, demonstrating exceptional performance in behavior cloning. However, their slow generation process stemming from iterative denoising…

In this study, we propose Shortcut Fine-Tuning (SFT), a new approach for addressing the challenge of fast sampling of pretrained Denoising Diffusion Probabilistic Models (DDPMs). SFT advocates for the fine-tuning of DDPM samplers through…

This work introduces DiffuseLoco, a framework for training multi-skill diffusion-based policies for dynamic legged locomotion from offline datasets, enabling real-time control of diverse skills on robots in the real world. Offline learning…

With intelligent room-side sensing and service robots widely deployed, human motion prediction (HMP) is essential for safe, proactive assistance. However, many existing HMP methods either produce a single, deterministic forecast that…

Diffusion policies have emerged as powerful generative models for offline policy learning, whose sampling process can be rigorously characterized by a score function guiding a stochastic differential equation (SDE). However, the same…

Diffusion models have become the most popular approach for high-quality image generation, but their high computational cost still remains a significant challenge. To address this problem, we propose U-Shape Mamba (USM), a novel diffusion…

Motion style transfer is a significant research direction in the field of computer vision, enabling virtual digital humans to rapidly switch between different styles of the same motion, thereby significantly enhancing the richness and…

Robots hold great promise for performing repetitive or hazardous tasks, but achieving human-like dexterity, especially in contact-rich and dynamic environments, remains challenging. Rigid robots, which rely on position or velocity control,…

Diffusion Probabilistic Models (DPMs) have achieved great success in image generation but suffer from high inference latency due to their iterative denoising nature. Motivated by the evolving feature dynamics across the denoising…

Existing segmentation models trained on a single medical imaging dataset often lack robustness when encountering unseen organs or tumors. Developing a robust model capable of identifying rare or novel tumor categories not present during…

Diffusion models have achieved great success in image generation, with the backbone evolving from U-Net to Vision Transformers. However, the computational cost of Transformers is quadratic to the number of tokens, leading to significant…

Linear State Space Models (SSMs) offer remarkable performance gains in efficient sequence modeling, with constant inference-time computation and memory complexity. Recent advances, such as Mamba, further enhance SSMs with input-dependent…

Recent progress in imitation learning has been enabled by policy architectures that scale to complex visuomotor tasks, multimodal distributions, and large datasets. However, these methods often rely on learning from large amount of expert…