相关论文: A Diffusion-Based Method for Learning the Multi-Ou…

Diffusion models recently proved to be remarkable priors for Bayesian inverse problems. However, training these models typically requires access to large amounts of clean data, which could prove difficult in some settings. In this work, we…

Ensuring fairness in medical image segmentation is critical due to biases in imbalanced clinical data acquisition caused by demographic attributes (e.g., age, sex, race) and clinical factors (e.g., disease severity). To address these…

Mutual Information (MI) and Conditional Mutual Information (CMI) are multi-purpose tools from information theory that are able to naturally measure the statistical dependencies between random variables, thus they are usually of central…

We present ActionDiffusion -- a novel diffusion model for procedure planning in instructional videos that is the first to take temporal inter-dependencies between actions into account in a diffusion model for procedure planning. This…

Adoption of deep learning in safety-critical systems raise the need for understanding what deep neural networks do not understand after models have been deployed. The behaviour of deep neural networks is undefined for so called…

Diffusion models have shown promising capabilities in trajectory generation for planning in offline reinforcement learning (RL). However, conventional diffusion-based planning methods often fail to account for the fact that generating…

Identifying the training data samples that most influence a generated image is a critical task in understanding diffusion models (DMs), yet existing influence estimation methods are constrained to small-scale or LoRA-tuned models due to…

We present MotionDiffuser, a diffusion based representation for the joint distribution of future trajectories over multiple agents. Such representation has several key advantages: first, our model learns a highly multimodal distribution…

Sparse-view computed tomography (CT) reconstruction is fundamentally challenging due to undersampling, leading to an ill-posed inverse problem. Traditional iterative methods incorporate handcrafted or learned priors to regularize the…

Diffusion models (DMs) have emerged as powerful foundation models for a variety of tasks, with a large focus in synthetic image generation. However, their requirement of large annotated datasets for training limits their applicability in…

Magnetic resonance imaging (MRI) is a vital diagnostic tool, but its inherently long acquisition times reduce clinical efficiency and patient comfort. Recent advancements in deep learning, particularly diffusion models, have improved…

Diffusion models (DMs) have gained prominence due to their ability to generate high-quality varied images with recent advancements in text-to-image generation. The research focus is now shifting towards the controllability of DMs. A…

Dataset Distillation aims to synthesize compact datasets that can approximate the training efficacy of large-scale real datasets, offering an efficient solution to the increasing computational demands of modern deep learning. Recently,…

Eosinophilic Esophagitis (EoE) represents a challenging condition for medical providers today. The cause is currently unknown, the impact on a patient's daily life is significant, and it is increasing in prevalence. Traditional approaches…

Model-based reinforcement learning methods often use learning only for the purpose of estimating an approximate dynamics model, offloading the rest of the decision-making work to classical trajectory optimizers. While conceptually simple,…

Medical image segmentation is crucial for clinical diagnosis and treatment planning. Traditional methods typically produce a single segmentation mask, failing to capture inherent uncertainty. Recent generative models enable the creation of…

Annotation variability remains a substantial challenge in medical image segmentation, stemming from ambiguous imaging boundaries and diverse clinical expertise. Traditional deep learning methods producing single deterministic segmentation…

Diffusion models have emerged as powerful generative frameworks by progressively adding noise to data through a forward process and then reversing this process to generate realistic samples. While these models have achieved strong…

Accurate modeling of robot dynamics is essential for model-based control, yet remains challenging under distributional shifts and real-time constraints. In this work, we formulate system identification as an in-context meta-learning problem…

This work introduces Variational Diffusion Distillation (VDD), a novel method that distills denoising diffusion policies into Mixtures of Experts (MoE) through variational inference. Diffusion Models are the current state-of-the-art in…