Related papers: MDSGen: Fast and Efficient Masked Diffusion Tempor…

Audio-driven portrait animation, which synthesizes realistic videos from reference images using audio signals, faces significant challenges in real-time generation of high-fidelity, temporally coherent animations. While recent…

We present DiffInDScene, a novel framework for tackling the problem of high-quality 3D indoor scene generation, which is challenging due to the complexity and diversity of the indoor scene geometry. Although diffusion-based generative…

Most generative models of audio directly generate samples in one of two domains: time or frequency. While sufficient to express any signal, these representations are inefficient, as they do not utilize existing knowledge of how sound is…

Acceleration methods for diffusion models (e.g., token merging or downsampling) typically optimize synthesis quality under reduced compute, yet often ignore discriminative capacity. We revisit token compression with a joint objective and…

Generative models such as Generative Adversarial Networks (GANs) and Variational Auto-Encoders (VAEs) are widely utilized to model the generative process of user interactions. However, these generative models suffer from intrinsic…

Recent development of neural vocoders based on the generative adversarial neural network (GAN) has shown obvious advantages of generating raw waveform conditioned on mel-spectrogram with fast inference speed and lightweight networks.…

The diffusion model is capable of generating high-quality data through a probabilistic approach. However, it suffers from the drawback of slow generation speed due to the requirement of a large number of time steps. To address this…

Convolutional neural networks (CNNs), such as the time-delay neural network (TDNN), have shown their remarkable capability in learning speaker embedding. However, they meanwhile bring a huge computational cost in storage size, processing,…

Training medical image segmentation models for rare yet clinically important imaging modalities is challenging due to the scarcity of annotated data, and manual mask annotations can be costly and labor-intensive to acquire. This paper…

Medical image synthesis is a challenging task due to the scarcity of paired data. Several methods have applied CycleGAN to leverage unpaired data, but they often generate inaccurate mappings that shift the anatomy. This problem is further…

While deep neural networks (NN) significantly advance image compressed sensing (CS) by improving reconstruction quality, the necessity of training current CS NNs from scratch constrains their effectiveness and hampers rapid deployment.…

Open-vocabulary semantic segmentation (OVSS) aims to segment objects from arbitrary text categories without requiring densely annotated datasets. Although contrastive learning based models enable zero-shot segmentation, they often lose fine…

Generative diffusion processes are an emerging and effective tool for image and speech generation. In the existing methods, the underlying noise distribution of the diffusion process is Gaussian noise. However, fitting distributions with…

This paper proposes a new unsupervised audio-visual speech enhancement (AVSE) approach that combines a diffusion-based audio-visual speech generative model with a non-negative matrix factorization (NMF) noise model. First, the diffusion…

Previous efforts have managed to generate production-ready 3D assets from text or images. However, these methods primarily employ NeRF or 3D Gaussian representations, which are not adept at producing smooth, high-quality geometries required…

Discrete diffusion models generate sequences by iteratively denoising samples corrupted by categorical noise, offering an appealing alternative to autoregressive decoding for structured and symbolic generation. However, standard training…

Generating samples from limited information is a fundamental problem across scientific domains. Classical maximum entropy methods provide principled uncertainty quantification from moment constraints but require sampling via MCMC or…

Diffusion and flow matching models have unlocked unprecedented capabilities for creative content creation, such as interactive image and streaming video generation. The growing demand for higher resolutions, frame rates, and context…

Diffusion model (DM) based Video Super-Resolution (VSR) approaches achieve impressive perceptual quality. However, they suffer from error accumulation, spatial artifacts, and a trade-off between perceptual quality and fidelity, primarily…

Automatic speech recognition (ASR) systems based on large language models (LLMs) achieve superior performance by leveraging pretrained LLMs as decoders, but their token-by-token generation mechanism leads to inference latency that grows…