English
Related papers

Related papers: LEDiT: Your Length-Extrapolatable Diffusion Transf…

200 papers

The Position Embedding (PE) is critical for Vision Transformers (VTs) due to the permutation-invariance of self-attention operation. By analyzing the input and output of each encoder layer in VTs using reparameterization and visualization,…

Computer Vision and Pattern Recognition · Computer Science 2022-12-23 Runyi Yu , Zhennan Wang , Yinhuai Wang , Kehan Li , Yian Zhao , Jian Zhang , Guoli Song , Jie Chen

Diffusion Transformers (DiTs) deliver remarkable image and video generation quality but incur high computational cost, limiting scalability and on-device deployment. We introduce CoReDiT, a structured token pruning framework for DiTs across…

Computer Vision and Pattern Recognition · Computer Science 2026-05-15 Zhuojin Li , Hsin-Pai Cheng , Hong Cai , Shizhong Han , Fatih Porikli

Diffusion models have demonstrated excellent capabilities in text-to-image generation. Their semantic understanding (i.e., prompt following) ability has also been greatly improved with large language models (e.g., T5, Llama). However,…

Computer Vision and Pattern Recognition · Computer Science 2024-11-05 Anthony Chen , Jianjin Xu , Wenzhao Zheng , Gaole Dai , Yida Wang , Renrui Zhang , Haofan Wang , Shanghang Zhang

Length extrapolation algorithms based on Rotary position embedding (RoPE) have shown promising results in extending the context length of language models. However, understanding how position embedding can capture longer-range contextual…

Computation and Language · Computer Science 2024-10-22 Xiangyu Hong , Che Jiang , Biqing Qi , Fandong Meng , Mo Yu , Bowen Zhou , Jie Zhou

Diffusion Transformers (DiTs) have recently achieved remarkable success in text-guided image generation. In image editing, DiTs project text and image inputs to a joint latent space, from which they decode and synthesize new images.…

Computer Vision and Pattern Recognition · Computer Science 2024-11-14 Zitao Shuai , Chenwei Wu , Zhengxu Tang , Bowen Song , Liyue Shen

Recent breakthroughs in Diffusion Transformers (DiTs) have revolutionized the field of visual synthesis due to their superior scalability. To facilitate DiTs' capability of capturing meaningful internal representations, recent works such as…

Computer Vision and Pattern Recognition · Computer Science 2026-03-05 Mengping Yang , Zhiyu Tan , Binglei Li , Xiaomeng Yang , Hesen Chen , Hao Li

We introduce GeoDiT, a diffusion transformer designed for text-to-satellite image generation with point-based control. Existing controlled satellite image generative models often require pixel-level maps that are time-consuming to acquire,…

Computer Vision and Pattern Recognition · Computer Science 2026-03-03 Srikumar Sastry , Dan Cher , Brian Wei , Aayush Dhakal , Subash Khanal , Dev Gupta , Nathan Jacobs

Logit Lens is a widely adopted method for mechanistic interpretability of transformer-based language models, enabling the analysis of how internal representations evolve across layers by projecting them into the output vocabulary space.…

Computer Vision and Pattern Recognition · Computer Science 2025-04-24 Ryota Takatsuki , Sonia Joseph , Ippei Fujisawa , Ryota Kanai

Rotary Position Embedding (RoPE) performs remarkably on language models, especially for length extrapolation of Transformers. However, the impacts of RoPE on computer vision domains have been underexplored, even though RoPE appears capable…

Computer Vision and Pattern Recognition · Computer Science 2024-07-17 Byeongho Heo , Song Park , Dongyoon Han , Sangdoo Yun

Diffusion-based inverse algorithms have shown remarkable performance across various inverse problems, yet their reliance on numerous denoising steps incurs high computational costs. While recent developments of fast diffusion ODE solvers…

Computer Vision and Pattern Recognition · Computer Science 2025-10-22 Jiawei Zhang , Ziyuan Liu , Leon Yan , Gen Li , Yuantao Gu

Recent image diffusion transformers achieve high-fidelity generation, but struggle to generate images beyond these scales, suffering from content repetition and quality degradation. In this work, we present UltraImage, a principled…

Computer Vision and Pattern Recognition · Computer Science 2025-12-05 Min Zhao , Bokai Yan , Xue Yang , Hongzhou Zhu , Jintao Zhang , Shilong Liu , Chongxuan Li , Jun Zhu

Diffusion models (DMs) have gained prominence due to their ability to generate high-quality varied images with recent advancements in text-to-image generation. The research focus is now shifting towards the controllability of DMs. A…

Computer Vision and Pattern Recognition · Computer Science 2024-12-06 Enis Simsar , Alessio Tonioni , Yongqin Xian , Thomas Hofmann , Federico Tombari

Transformer models are permutation equivariant. To supply the order and type information of the input tokens, position and segment embeddings are usually added to the input. Recent works proposed variations of positional encodings with…

Computation and Language · Computer Science 2021-11-04 Pu-Chin Chen , Henry Tsai , Srinadh Bhojanapalli , Hyung Won Chung , Yin-Wen Chang , Chun-Sung Ferng

Enabling LLMs to handle lengthy context is currently a research hotspot. Most LLMs are built upon rotary position embedding (RoPE), a popular position encoding method. Therefore, a prominent path is to extrapolate the RoPE trained on…

Computation and Language · Computer Science 2024-12-13 Meizhi Zhong , Chen Zhang , Yikun Lei , Xikai Liu , Yan Gao , Yao Hu , Kehai Chen , Min Zhang

Despite the remarkable capabilities of Multimodal Large Language Models (MLLMs), they still suffer from visual fading in long-context scenarios. Specifically, the attention to visual tokens diminishes as the text sequence lengthens, leading…

Computer Vision and Pattern Recognition · Computer Science 2026-03-12 Lin Chen , Bolin Ni , Qi Yang , Zili Wang , Kun Ding , Ying Wang , Houwen Peng , Shiming Xiang

Length generalization, the ability to generalize from small training context sizes to larger ones, is a critical challenge in the development of Transformer-based language models. Positional encoding (PE) has been identified as a major…

Computation and Language · Computer Science 2023-11-08 Amirhossein Kazemnejad , Inkit Padhi , Karthikeyan Natesan Ramamurthy , Payel Das , Siva Reddy

Despite their remarkable performance, modern Diffusion Transformers are hindered by substantial resource requirements during inference, stemming from the fixed and large amount of compute needed for each denoising step. In this work, we…

Recent advances in diffusion models have significantly improved the performance of reference-guided line art colorization. However, existing methods still struggle with region-level color consistency, especially when the reference and…

Computer Vision and Pattern Recognition · Computer Science 2025-08-14 Qianru Qiu , Jiafeng Mao , Kento Masui , Xueting Wang

Discrete diffusion models are a new class of text generators that offer advantages such as bidirectional context use, parallelizable generation, and flexible prompting compared to autoregressive models. However, a critical limitation of…

Machine Learning · Computer Science 2025-10-23 Andrew Zhang , Anushka Sivakumar , Chiawei Tang , Chris Thomas

Diffusion-based image compression has recently shown outstanding perceptual fidelity, yet its practicality is hindered by prohibitive sampling overhead and high memory usage. Most existing diffusion codecs employ U-Net architectures, where…

Image and Video Processing · Electrical Eng. & Systems 2026-03-16 Junqi Shi , Ming Lu , Xingchen Li , Anle Ke , Ruiqi Zhang , Zhan Ma