Related papers: D3PIA: A Discrete Denoising Diffusion Model for Pi…

The practical applications of diffusion models have been limited by the misalignment between generated images and corresponding text prompts. Recent studies have introduced direct preference optimization (DPO) to enhance the alignment of…

Conditional generative models typically demand large annotated training sets to achieve high-quality synthesis. As a result, there has been significant interest in designing models that perform plug-and-play generation, i.e., to use a…

Developing generative models to create or conditionally create symbolic music presents unique challenges due to the combination of limited data availability and the need for high precision in note pitch. To address these challenges, we…

Due to the lack of large-scale text-3D correspondence data, recent text-to-3D generation works mainly rely on utilizing 2D diffusion models for synthesizing 3D data. Since diffusion-based methods typically require significant optimization…

Discrete diffusion models are a powerful class of generative models with strong performance across many domains. For efficiency, however, discrete diffusion typically parameterizes the generative (reverse) process with factorized…

Recent literature has effectively leveraged diffusion models trained on continuous variables as priors for solving inverse problems. Notably, discrete diffusion models with discrete latent codes have shown strong performance, particularly…

Existing customization methods require access to multiple reference examples to align pre-trained diffusion probabilistic models (DPMs) with user-provided concepts. This paper aims to address the challenge of DPM customization when the only…

Diffusion probabilistic models have been shown to generate state-of-the-art results on several competitive image synthesis benchmarks but lack a low-dimensional, interpretable latent space, and are slow at generation. On the other hand,…

Diffusion and flow-based models have become the state of the art for generative AI across a wide range of data modalities, including images, videos, shapes, molecules, music, and more. This tutorial provides a self-contained introduction to…

We tackle the problem of text-driven 3D generation from a geometry alignment perspective. Given a set of text prompts, we aim to generate a collection of objects with semantically corresponding parts aligned across them. Recent methods…

Denoising Diffusion Probabilistic Model (DDPM) is able to make flexible conditional image generation from prior noise to real data, by introducing an independent noise-aware classifier to provide conditional gradient guidance at each time…

Prevailing Dataset Distillation (DD) methods leveraging generative models confront two fundamental limitations. First, despite pioneering the use of diffusion models in DD and delivering impressive performance, the vast majority of…

We present DIRECT-3D, a diffusion-based 3D generative model for creating high-quality 3D assets (represented by Neural Radiance Fields) from text prompts. Unlike recent 3D generative models that rely on clean and well-aligned 3D data,…

Accurately predicting 3D occupancy grids from visual inputs is critical for autonomous driving, but current discriminative methods struggle with noisy data, incomplete observations, and the complex structures inherent in 3D scenes. In this…

Diffusion models have shown promising results in cross-modal generation tasks involving audio and music, such as text-to-sound and text-to-music generation. These text-controlled music generation models typically focus on generating music…

Realistic music generation is a challenging task. When building generative models of music that are learnt from data, typically high-level representations such as scores or MIDI are used that abstract away the idiosyncrasies of a particular…

Spatial audio is crucial for immersive 360-degree video experiences, yet most 360-degree videos lack it due to the difficulty of capturing spatial audio during recording. Automatically generating spatial audio such as first-order ambisonics…

Spatial audio is crucial for immersive 360-degree video experiences, yet most 360-degree videos lack it due to the difficulty of capturing spatial audio during recording. Automatically generating spatial audio such as first-order ambisonics…

Data augmentation for domain-specific image classification tasks often struggles to simultaneously address diversity, faithfulness, and label clarity of generated data, leading to suboptimal performance in downstream tasks. While existing…

Current generative models are able to generate high-quality artefacts but have been shown to struggle with compositional reasoning, which can be defined as the ability to generate complex structures from simpler elements. In this paper, we…