English
Related papers

Related papers: One Attention, One Scale: Phase-Aligned Rotary Pos…

200 papers

Diffusion Transformers (DiTs) have revolutionized high-fidelity video generation, yet their $\mathcal{O}(L^2)$ attention complexity poses a formidable bottleneck for long-sequence synthesis. While recent sparse-linear attention hybrids aim…

Computer Vision and Pattern Recognition · Computer Science 2026-05-21 Yuxi Liu , Zekun Zhang , Yixiang Cai , Renjia Deng , Yutong He , Kun Yuan

Diffusion transformers (DiTs) have emerged as a dominant architecture for text-to-image generation, yet their performance drops when generating at resolutions beyond their training range. Existing training-free approaches mitigate this by…

Computer Vision and Pattern Recognition · Computer Science 2026-05-22 Javad Rajabi , Kimia Shaban , Koorosh Roohi , David B. Lindell , Babak Taati

Rectified flow (RF) models have recently demonstrated superior generative performance compared to DDIM-based diffusion models. However, in real-world applications, they suffer from two major challenges: (1) low inversion accuracy that…

Computer Vision and Pattern Recognition · Computer Science 2025-09-17 Weiming Chen , Zhihan Zhu , Yijia Wang , Zhihai He

Positional encodings are essential to transformer-based generative models, yet their behavior in multimodal and attention-sharing settings is not fully understood. In this work, we present a principled analysis of Rotary Positional…

Graphics · Computer Science 2026-02-06 Aryan Mikaeili , Or Patashnik , Andrea Tagliasacchi , Daniel Cohen-Or , Ali Mahdavi-Amiri

Diffusion Transformers (DiTs) deliver state-of-the-art image quality, yet their training remains notoriously slow. A recent remedy -- representation alignment (REPA) that matches DiT hidden features to those of a non-generative teacher…

Computer Vision and Pattern Recognition · Computer Science 2025-05-23 Ziqiao Wang , Wangbo Zhao , Yuhao Zhou , Zekai Li , Zhiyuan Liang , Mingjia Shi , Xuanlei Zhao , Pengfei Zhou , Kaipeng Zhang , Zhangyang Wang , Kai Wang , Yang You

While modern text-to-image models excel at prompt-based generation, they often lack the fine-grained control necessary for specific user requirements like spatial layouts or subject appearances. Multi-condition control addresses this, yet…

Computer Vision and Pattern Recognition · Computer Science 2026-02-09 Chao Zhou , Tianyi Wei , Yiling Chen , Wenbo Zhou , Nenghai Yu

Recent advances in Diffusion Transformers (DiTs) demonstrate that aligning noisy latent states with well-trained semantic features-as pioneered by Representation Alignment (REPA)-can substantially accelerate training and improve generation…

Computer Vision and Pattern Recognition · Computer Science 2026-05-19 Shaodong Xu , Zhendong Wang , Litong Gong , Zexian Li , Wengang Zhou , Tiezheng Ge , Houqiang Li

Visual Autoregressive (VAR) models have emerged as a strong alternative to diffusion for image synthesis, yet their fixed training resolution prevents direct generation at higher resolutions. Naively transferring training-free extrapolation…

Computer Vision and Pattern Recognition · Computer Science 2026-05-12 Feihong Yan , Shaoyu Liu , Haixuan Wang , Shuai Lu , Linfeng Zhang , Huiqi Li , Xiangyang Ji

Fine-tuning Video Diffusion Models (VDMs) at the user level to generate videos that reflect specific attributes of training data presents notable challenges, yet remains underexplored despite its practical importance. Meanwhile, recent work…

Computer Vision and Pattern Recognition · Computer Science 2025-06-26 Sungwon Hwang , Hyojin Jang , Kinam Kim , Minho Park , Jaegul Choo

The transformer architecture has been widely applied to many machine learning tasks. A main bottleneck in the time to perform transformer computations is a task called attention computation. [Alman and Song, NeurIPS 2023] have shown that in…

Machine Learning · Computer Science 2025-05-20 Josh Alman , Zhao Song

Tensor Attention extends traditional attention mechanisms by capturing high-order correlations across multiple modalities, addressing the limitations of classical matrix-based attention. Meanwhile, Rotary Position Embedding…

Machine Learning · Computer Science 2024-12-25 Xiaoyu Li , Yingyu Liang , Zhenmei Shi , Zhao Song , Mingda Wan

Recent diffusion-based image editing methods commonly rely on text or high-level instructions to guide the generation process, offering intuitive but coarse control. In contrast, we focus on explicit, prompt-free editing, where the user…

Graphics · Computer Science 2026-04-24 Etai Sella , Yoav Baron , Hadar Averbuch-Elor , Daniel Cohen-Or , Or Patashnik

Self-attention and position embedding are two key modules in transformer-based Large Language Models (LLMs). However, the potential relationship between them is far from well studied, especially for long context window extending. In fact,…

Machine Learning · Computer Science 2024-02-29 Shiyi Zhu , Jing Ye , Wei Jiang , Siqiao Xue , Qi Zhang , Yifan Wu , Jianguo Li

Rotary Position Embedding (RoPE) is widely adopted in large language models, but when applied to vision-language models (VLMs) it couples text and image position indices and can introduce spurious cross-modal relative-position bias. We…

Computer Vision and Pattern Recognition · Computer Science 2026-05-22 Chengcheng Wang , Jianyuan Guo , Hongguang Li , Yuchuan Tian , Ying Nie , Chang Xu , Kai Han

Camera-conditioned video generation requires positional encoding that remains reliable under changes in camera motion, lens configuration, and scene structure. However, existing attention-level camera encodings either provide ray-only…

Computer Vision and Pattern Recognition · Computer Science 2026-05-14 Seonghyun Jin , Youngmin Kim , Sunwoo Park , Jong Chul Ye

Despite their generative power, diffusion models struggle to maintain style consistency across images conditioned on the same style prompt, hindering their practical deployment in creative workflows. While several training-free methods…

Computer Vision and Pattern Recognition · Computer Science 2025-09-23 Jiexuan Zhang , Yiheng Du , Qian Wang , Weiqi Li , Yu Gu , Jian Zhang

Rotary Positional Embeddings (RoPE) have become the standard for Large Language Models (LLMs) due to their ability to encode relative positions through geometric rotation. However, we identify a significant limitation we term ''Spectral…

Computation and Language · Computer Science 2026-02-02 Kanishk Awadhiya

Sparse point clouds are a common input modality for 3D surface reconstruction, including in safety-critical settings such as surgical navigation and autonomous perception. Recent point-cloud-conditioned 3D diffusion transformers achieve…

Machine Learning · Computer Science 2026-05-19 Maximilian Plattner , Fabian Paischer , Johannes Brandstetter , Arturs Berzins

Leveraging pre-trained Diffusion Transformers (DiTs) for high-resolution (HR) image synthesis often leads to spatial layout collapse and degraded texture fidelity. Prior work mitigates these issues with complex pipelines that first perform…

Computer Vision and Pattern Recognition · Computer Science 2025-12-02 Yiyang Ma , Feng Zhou , Xuedan Yin , Pu Cao , Yonghao Dang , Jianqin Yin

Rotary positional embeddings (RoPE) are widely used in large language models to encode token positions through multiplicative rotations, yet their behavior at long context lengths remains poorly characterized. In this work, we reinterpret…

Machine Learning · Computer Science 2026-02-12 Feilong Liu
‹ Prev 1 2 3 10 Next ›