Related papers: WiT: Waypoint Diffusion Transformers via Trajector…

Recent DiT-based text-to-image models increasingly adopt LLMs as text encoders, yet text conditioning remains largely static and often utilizes only a single LLM layer, despite pronounced semantic hierarchy across LLM layers and…

Diffusion Transformers (DiTs) can generate short photorealistic videos, yet directly training and sampling longer videos with full attention across the video remains computationally challenging. Alternative methods break long videos down…

The Vision Transformer (ViT) leverages the Transformer's encoder to capture global information by dividing images into patches and achieves superior performance across various computer vision tasks. However, the self-attention mechanism of…

We present Scalable Interpolant Transformers (SiT), a family of generative models built on the backbone of Diffusion Transformers (DiT). The interpolant framework, which allows for connecting two distributions in a more flexible way than…

Image fusion aims to blend complementary information from multiple sensing modalities, yet existing approaches remain limited in robustness, adaptability, and controllability. Most current fusion networks are tailored to specific tasks and…

While diffusion models excel at image synthesis, useful representations have been shown to emerge from generative pre-training, suggesting a path towards unified generative and discriminative learning. However, suboptimal semantic flow…

Diffusion models face a fundamental trade-off between generation quality and computational efficiency. Latent Diffusion Models (LDMs) offer an efficient solution but suffer from potential information loss and non-end-to-end training. In…

In this work, we empirically study Diffusion Transformers (DiTs) for text-to-image generation, focusing on architectural choices, text-conditioning strategies, and training protocols. We evaluate a range of DiT-based…

Tokens or patches within Vision Transformers (ViT) lack essential semantic information, unlike their counterparts in natural language processing (NLP). Typically, ViT tokens are associated with rectangular image patches that lack specific…

This paper presents the Large Vision Diffusion Transformer (LaVin-DiT), a scalable and unified foundation model designed to tackle over 20 computer vision tasks in a generative framework. Unlike existing large vision models directly adapted…

Diffusion Transformer (DiT), a promising diffusion model for visual generation, demonstrates impressive performance but incurs significant computational overhead. Intriguingly, analysis of pre-trained DiT models reveals that global…

In this paper, we introduce a novel approach to trajectory generation for autonomous driving, combining the strengths of Diffusion models and Transformers. First, we use the historical trajectory data for efficient preprocessing and…

Learning efficient and expressive visual representation has long been the pursuit of computer vision research. While Vision Transformers (ViTs) gradually replace traditional Convolutional Neural Networks (CNNs) as more scalable vision…

In autonomous driving, deep models have shown remarkable performance across various visual perception tasks with the demand of high-quality and huge-diversity training datasets. Such datasets are expected to cover various driving scenarios…

A surge of interest has emerged in utilizing Transformers in diverse vision tasks owing to its formidable performance. However, existing approaches primarily focus on optimizing internal model architecture designs that often entail…

Diffusion Transformers (DiTs) have emerged as a leading architecture for text-to-image synthesis, producing high-quality and photorealistic images. However, the quadratic scaling properties of the attention in DiTs hinder image generation…

Although certain vision transformer (ViT) and CNN architectures generalize well on vision tasks, it is often impractical to use them on green, edge, or desktop computing due to their computational requirements for training and even testing.…

Diffusion models have revolutionized the field of content synthesis and editing. Recent models have replaced the traditional UNet architecture with the Diffusion Transformer (DiT), and employed flow-matching for improved training and…

Diffusion Transformers rely on static patchify tokenization, assigning the same token budget to smooth backgrounds, detailed object regions, noisy early timesteps, and late-stage refinements. We introduce the Dynamic Chunking Diffusion…

We present JointDiT, a diffusion transformer that models the joint distribution of RGB and depth. By leveraging the architectural benefit and outstanding image prior of the state-of-the-art diffusion transformer, JointDiT not only generates…