Related papers: DiffMoE: Dynamic Token Selection for Scalable Diff…

In this paper, we present DiT-MoE, a sparse version of the diffusion Transformer, that is scalable and competitive with dense networks while exhibiting highly optimized inference. The DiT-MoE includes two simple designs: shared expert…

Diffusion Probabilistic Models (DPMs) have emerged as the de facto approach for high-fidelity image synthesis, operating diffusion processes on continuous VAE latent, which significantly differ from the text generation methods employed by…

Generating high-quality labeled image datasets is crucial for training accurate and robust machine learning models in the field of computer vision. However, the process of manually labeling real images is often time-consuming and costly. To…

We aim to leverage diffusion to address the challenging image matting task. However, the presence of high computational overhead and the inconsistency of noise sampling between the training and inference processes pose significant obstacles…

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,…

Image classification serves as the cornerstone of computer vision, traditionally achieved through discriminative models based on deep neural networks. Recent advancements have introduced classification methods derived from generative…

Diffusion models have emerged as a promising approach for text generation, with recent works falling into two main categories: discrete and continuous diffusion models. Discrete diffusion models apply token corruption independently using…

Mixture-of-Experts (MoE) architectures have emerged as a powerful paradigm for scaling neural networks while maintaining computational efficiency. However, standard MoE implementations rely on two rigid design assumptions: (1) fixed Top-K…

Diffusion Transformer (DiT) has demonstrated remarkable performance in text-to-image generation; however, its large parameter size results in substantial inference overhead. Existing parameter compression methods primarily focus on pruning,…

Beyond high-fidelity image synthesis, diffusion models have recently exhibited promising results in dense visual perception tasks. However, most existing work treats diffusion models as a standalone component for perception tasks, employing…

Diffusion models demonstrate outstanding performance in image generation, but their multi-step inference mechanism requires immense computational cost. Previous works accelerate inference by leveraging layer or token cache techniques to…

Prior masked modeling motion generation methods predominantly study text-to-motion. We present DiMo, a discrete diffusion-style framework, which extends masked modeling to bidirectional text--motion understanding and generation. Unlike…

We introduce Transfusion, a recipe for training a multi-modal model over discrete and continuous data. Transfusion combines the language modeling loss function (next token prediction) with diffusion to train a single transformer over…

Mixture-of-Experts (MoE) has emerged as a powerful paradigm for scaling model capacity while preserving computational efficiency. Despite its notable success in large language models (LLMs), existing attempts to apply MoE to Diffusion…

The landscape of image generation has been forever changed by open vocabulary diffusion models. However, at their core these models use transformers, which makes generation slow. Better implementations to increase the throughput of these…

Diffusion models demonstrate remarkable capabilities in capturing complex data distributions and have achieved compelling results in many generative tasks. While they have recently been extended to dense prediction tasks such as depth…

Recently, large-scale diffusion models, e.g., Stable diffusion and DallE2, have shown remarkable results on image synthesis. On the other hand, large-scale cross-modal pre-trained models (e.g., CLIP, ALIGN, and FILIP) are competent for…

Acoustic echo and background noise pose challenges on speech enhancement in hands-free systems and speakerphones. Discriminatively trained end-to-end methods represent a powerful solution for joint acoustic echo control (AEC) and denoising.…

Can continuous diffusion models bring the same performance breakthrough on natural language they did for image generation? To circumvent the discrete nature of text data, we can simply project tokens in a continuous space of embeddings, as…

While many unsupervised learning models focus on one family of tasks, either generative or discriminative, we explore the possibility of a unified representation learner: a model which addresses both families of tasks simultaneously. We…