相关论文: Kicking it Off(-shell) with Direct Diffusion

In this paper, we argue that iterative computation with diffusion models offers a powerful paradigm for not only generation but also visual perception tasks. We unify tasks such as depth estimation, optical flow, and amodal segmentation…

Diffusion models have shown remarkable performance on many generative tasks. Despite recent success, most diffusion models are restricted in that they only allow linear transformation of the data distribution. In contrast, broader family of…

Most natural objects have inherent complexity and variability. While some simple objects can be modeled from first principles, many real-world phenomena, such as cloud formation, require computationally expensive simulations that limit…

This paper presents a principled approach for detecting out-of-distribution (OOD) samples in deep neural networks (DNN). Modeling probability distributions on deep features has recently emerged as an effective, yet computationally cheap…

Obtaining 3D conformations of realistic polyatomic molecules at the quantum chemistry level remains challenging, and although recent machine learning advances offer promise, predicting large-molecule structures still requires substantial…

Reaction-diffusion systems with cross-diffusion terms in addition to, or instead of, the usual self-diffusion demonstrate interesting features which motivate their further study. The present work is aimed at designing a toy…

The computational intensity of detector simulation and event reconstruction poses a significant difficulty for data analysis in collider experiments. This challenge inspires the continued development of machine learning techniques to serve…

We make the first steps towards diffusion models for unconditional generation of multivariate and Arctic-wide sea-ice states. While targeting to reduce the computational costs by diffusion in latent space, latent diffusion models also offer…

Learning diverse policies for non-prehensile manipulation is essential for improving skill transfer and generalization to out-of-distribution scenarios. In this work, we enhance exploration through a two-fold approach within a hybrid…

Recent advancements in large vision-language models have enabled highly expressive and diverse vector sketch generation. However, state-of-the-art methods rely on a time-consuming optimization process involving repeated feedback from a…

The importance of including experimental resonances in constructing effective inter-cluster interactions has been investigated. For this, we first address the question of how to obtain the analytical properties of the Jost function in…

There are many astrophysical and laboratory scenarios where kinetic effects play an important role. These range from astrophysical shocks and plasma shell collisions, to high intensity laser-plasma interactions, with applications to fast…

Diffusion models have emerged as a powerful framework for generative tasks in deep learning. They decompose generative modeling into two computational primitives: deterministic neural-network evaluation and stochastic sampling. Current…

This paper introduces distribution-based prediction, a novel approach to using Large Language Models (LLMs) as predictive tools by interpreting output token probabilities as distributions representing the models' learned representation of…

Transformers are often the go-to architecture to build foundation models that ingest a large amount of training data. But these models do not estimate the probability density distribution when trained on regression problems, yet obtaining…

Long-horizon contact-rich manipulation has long been a challenging problem, as it requires reasoning over both discrete contact modes and continuous object motion. We introduce Implicit Contact Diffuser (ICD), a diffusion-based model that…

Layout-to-image generation refers to the task of synthesizing photo-realistic images based on semantic layouts. In this paper, we propose LayoutDiffuse that adapts a foundational diffusion model pretrained on large-scale image or text-image…

In this work, we investigate the problem of creating high-fidelity 3D content from only a single image. This is inherently challenging: it essentially involves estimating the underlying 3D geometry while simultaneously hallucinating unseen…

Guided diffusion-model generation is a promising direction for customizing the generation process of a pre-trained diffusion model to address specific downstream tasks. Existing guided diffusion models either rely on training the guidance…

We introduce precise object silhouette as a new form of user control in text-to-image diffusion models, which we dub Shape-Guided Diffusion. Our training-free method uses an Inside-Outside Attention mechanism during the inversion and…