Related papers: DDT: Decoupled Diffusion Transformer
Multi-label classification has broad applications and depends on powerful representations capable of capturing multi-label interactions. We introduce \textit{Diff-Feat}, a simple but powerful framework that extracts intermediate features…
Diffusion models are widely recognized for generating high-quality and diverse images, but their poor real-time performance has led to numerous acceleration works, primarily focusing on UNet-based structures. With the more successful…
Low-dose computed tomography (LDCT) is an important topic in the field of radiology over the past decades. LDCT reduces ionizing radiation-induced patient health risks but it also results in a low signal-to-noise ratio (SNR) and a potential…
We present DiffusionBERT, a new generative masked language model based on discrete diffusion models. Diffusion models and many pre-trained language models have a shared training objective, i.e., denoising, making it possible to combine the…
Diffusion Transformers (DiTs) deliver state-of-the-art generative performance but their quadratic training cost with sequence length makes large-scale pretraining prohibitively expensive. Token dropping can reduce training cost, yet na\"ive…
Medical image segmentation is crucial for many healthcare tasks, including disease diagnosis and treatment planning. One key area is the segmentation of skin lesions, which is vital for diagnosing skin cancer and monitoring patients. In…
Recently, a series of diffusion-aware distillation algorithms have emerged to alleviate the computational overhead associated with the multi-step inference process of Diffusion Models (DMs). Current distillation techniques often dichotomize…
Communication efficiency is a widely recognised research problem in Federated Learning (FL), with recent work focused on developing techniques for efficient compression, distribution and aggregation of model parameters between clients and…
Encoder-decoder transformer models have achieved great success on various vision-language (VL) tasks, but they suffer from high inference latency. Typically, the decoder takes up most of the latency because of the auto-regressive decoding.…
Real-world data generation often involves complex inter-dependencies among instances, violating the IID-data hypothesis of standard learning paradigms and posing a challenge for uncovering the geometric structures for learning desired…
Recent advances indicate that diffusion models hold great promise in image super-resolution. While the latest methods are primarily based on latent diffusion models with convolutional neural networks, there are few attempts to explore…
In this paper, we propose Dynamic Compressive Transformer (DCT), a transformer-based framework for modeling the unbounded sequence. In contrast to the previous baselines which append every sentence representation to memory, conditionally…
Continuous normalizing flows (CNFs) and diffusion models (DMs) generate high-quality data from a noise distribution. However, their sampling process demands multiple iterations to solve an ordinary differential equation (ODE) with high…
Diffusion models are highly regarded for their controllability and the diversity of images they generate. However, class-conditional generation methods based on diffusion models often focus on more common categories. In large-scale…
Remote sensing image super-resolution (SR) is a crucial task to restore high-resolution (HR) images from low-resolution (LR) observations. Recently, the Denoising Diffusion Probabilistic Model (DDPM) has shown promising performance in image…
Intrinsic image decomposition is fundamental for visual understanding, as RGB images entangle material properties, illumination, and view-dependent effects. Recent diffusion-based methods have achieved strong results for single-view…
Recently, Transformer-based encoder-decoder models have demonstrated strong performance in multilingual speech recognition. However, the decoder's autoregressive nature and large size introduce significant bottlenecks during inference.…
Diffusion-based multimodal large language models (Diffusion MLLMs) have recently demonstrated impressive non-autoregressive generative capabilities across vision-and-language tasks. However, Diffusion MLLMs exhibit substantially slower…
Multimodal transformer exhibits high capacity and flexibility to align image and text for visual grounding. However, the existing encoder-only grounding framework (e.g., TransVG) suffers from heavy computation due to the self-attention…
Due to its effectiveness and performance, the Transformer translation model has attracted wide attention, most recently in terms of probing-based approaches. Previous work focuses on using or probing source linguistic features in the…