Related papers: Efficient Diffusion Planning with Temporal Diffusi…

Learning-based 3D Scanning plays a crucial role in enabling efficient and accurate scanning of target objects. However, recent reinforcement learning-based methods often require large-scale training data and still struggle to generalize to…

Diffusion models have emerged as a powerful class of generative models across various modalities, including image, video, and audio synthesis. However, their deployment is often limited by significant inference latency, primarily due to the…

Generative diffusion models have emerged as a powerful tool for high-quality image synthesis, yet their iterative nature demands significant computational resources. This paper proposes an efficient time step sampling method based on an…

Safe and successful deployment of robots requires not only the ability to generate complex plans but also the capacity to frequently replan and correct execution errors. This paper addresses the challenge of long-horizon trajectory planning…

We propose a new formulation of temporal action detection (TAD) with denoising diffusion, DiffTAD in short. Taking as input random temporal proposals, it can yield action proposals accurately given an untrimmed long video. This presents a…

Diffusion Models (DMs) have demonstrated state-of-the-art performance in content generation without requiring adversarial training. These models are trained using a two-step process. First, a forward - diffusion - process gradually adds…

Diffusion policies excel at visuomotor control but often fail catastrophically under severe out-of-distribution (OOD) disturbances, such as unexpected object displacements or visual corruptions. To address this vulnerability, we introduce…

Diffusion policy has demonstrated promising performance in the field of robotic manipulation. However, its effectiveness has been primarily limited in short-horizon tasks, and its performance significantly degrades in the presence of image…

Diffusion models, as a type of generative model, have achieved impressive results in generating images and videos conditioned on textual conditions. However, the generation process of diffusion models involves denoising dozens of steps to…

Diffusion models have emerged as the de facto choice for generating high-quality visual signals across various domains. However, training a single model to predict noise across various levels poses significant challenges, necessitating…

Diffusion models have recently shown promise in time series forecasting, particularly for probabilistic predictions. However, they often fail to achieve state-of-the-art point estimation performance compared to regression-based methods.…

Unlike discriminative approaches in autonomous driving that predict a fixed set of candidate trajectories of the ego vehicle, generative methods, such as diffusion models, learn the underlying distribution of future motion, enabling more…

Supervised learning approaches to offline reinforcement learning, particularly those utilizing the Decision Transformer, have shown effectiveness in continuous environments and for sparse rewards. However, they often struggle with…

This paper identifies significant redundancy in the query-key interactions within self-attention mechanisms of diffusion transformer models, particularly during the early stages of denoising diffusion steps. In response to this observation,…

The increasing complexity of tasks in robotics demands efficient strategies for multitask and continual learning. Traditional models typically rely on a universal policy for all tasks, facing challenges such as high computational costs and…

With the great success of diffusion models (DMs) in generating realistic synthetic vision data, many researchers have investigated their potential in decision-making and control. Most of these works utilized DMs to sample directly from the…

Diffusion models achieve great success in generating diverse and high-fidelity images, yet their widespread application, especially in real-time scenarios, is hampered by their inherently slow generation speed. The slow generation stems…

Diffusion Policy (DP) enables robots to learn complex behaviors by imitating expert demonstrations through action diffusion. However, in practical applications, hardware limitations often degrade data quality, while real-time constraints…

Diffusion models have achieved remarkable progress in the field of image generation due to their outstanding capabilities. However, these models require substantial computing resources because of the multi-step denoising process during…

Diffusion models generate highly realistic images by learning a multi-step denoising process, naturally embodying the principles of multi-task learning (MTL). Despite the inherent connection between diffusion models and MTL, there remains…