English
Related papers

Related papers: Infinity-RoPE: Action-Controllable Infinite Video …

200 papers

Predicting human gaze in video is fundamental to advancing scene understanding and multimodal interaction. While traditional saliency maps provide spatial probability distributions and scanpaths offer ordered fixations, both abstractions…

Computer Vision and Pattern Recognition · Computer Science 2026-03-27 Jenna Kang , Colin Groth , Tong Wu , Finley Torrens , Patsorn Sangkloy , Gordon Wetzstein , Qi Sun

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

We propose RoPECraft, a training-free video motion transfer method for diffusion transformers that operates solely by modifying their rotary positional embeddings (RoPE). We first extract dense optical flow from a reference video, and…

Computer Vision and Pattern Recognition · Computer Science 2025-11-26 Ahmet Berke Gokmen , Yigit Ekin , Bahri Batuhan Bilecen , Aysegul Dundar

We describe an adaptation of VACE (Video All-in-one Creation and Editing) for real-time autoregressive video generation. VACE provides unified video control (reference guidance, structural conditioning, inpainting, and temporal extension)…

Computer Vision and Pattern Recognition · Computer Science 2026-02-17 Ryan Fosdick

Generative recommenders, typically transformer-based autoregressive models, predict the next item or action from a user's interaction history. Their effectiveness depends on how the model represents where an interaction event occurs in the…

Information Retrieval · Computer Science 2025-10-24 Xiaokai Wei , Jiajun Wu , Daiyao Yi , Reza Shirkavand , Michelle Gong

Recent advances in 3D Large Multimodal Models (LMMs) built on Large Language Models (LLMs) have established the alignment of 3D visual features with LLM representations as the dominant paradigm. However, the inherited Rotary Position…

Computer Vision and Pattern Recognition · Computer Science 2026-02-17 Guanting Ye , Qiyan Zhao , Wenhao Yu , Xiaofeng Zhang , Jianmin Ji , Yanyong Zhang , Ka-Veng Yuen

Research on diffusion model-based video generation has advanced rapidly. However, limitations in object fidelity and generation length hinder its practical applications. Additionally, specific domains like animated wallpapers require…

Computer Vision and Pattern Recognition · Computer Science 2024-04-17 Fanyi Wang , Peng Liu , Haotian Hu , Dan Meng , Jingwen Su , Jinjin Xu , Yanhao Zhang , Xiaoming Ren , Zhiwang Zhang

While diffusion models excel at generating images with conventional dimensions, pushing them to synthesize ultra-high-resolution imagery at extreme aspect ratios (EAR) often triggers catastrophic structural failures, such as object…

Computer Vision and Pattern Recognition · Computer Science 2026-04-03 Haodong Yu , Yabo Zhang , Donglin Di , Ruyi Zhang , Wangmeng Zuo

Producing long, coherent video sequences with stable 3D structure remains a major challenge, particularly in streaming scenarios. Motivated by this, we introduce Endless World, a real-time framework for infinite, 3D-consistent video…

Computer Vision and Pattern Recognition · Computer Science 2025-12-16 Ke Zhang , Yiqun Mei , Jiacong Xu , Vishal M. Patel

We present InfiniCube, a scalable method for generating unbounded dynamic 3D driving scenes with high fidelity and controllability. Previous methods for scene generation either suffer from limited scales or lack geometric and appearance…

Computer Vision and Pattern Recognition · Computer Science 2025-06-27 Yifan Lu , Xuanchi Ren , Jiawei Yang , Tianchang Shen , Zhangjie Wu , Jun Gao , Yue Wang , Siheng Chen , Mike Chen , Sanja Fidler , Jiahui Huang

Controllable ultra-long video generation is a fundamental yet challenging task. Although existing methods are effective for short clips, they struggle to scale due to issues such as temporal inconsistency and visual degradation. In this…

Computer Vision and Pattern Recognition · Computer Science 2025-08-06 Jianxiong Gao , Zhaoxi Chen , Xian Liu , Jianfeng Feng , Chenyang Si , Yanwei Fu , Yu Qiao , Ziwei Liu

Video-based world models hold significant potential for generating high-quality embodied manipulation data. However, current video generation methods struggle to achieve stable long-horizon generation: classical diffusion-based approaches…

Computer Vision and Pattern Recognition · Computer Science 2025-09-29 Yu Shang , Lei Jin , Yiding Ma , Xin Zhang , Chen Gao , Wei Wu , Yong Li

Predictive world models that simulate future observations under explicit camera control are fundamental to interactive AI. Despite rapid advances, current systems lack spatial persistence: they fail to maintain stable scene structures over…

Computer Vision and Pattern Recognition · Computer Science 2026-02-24 Chendong Xiang , Jiajun Liu , Jintao Zhang , Xiao Yang , Zhengwei Fang , Shizun Wang , Zijun Wang , Yingtian Zou , Hang Su , Jun Zhu

Autoregressive (AR) video diffusion models enable long-form video generation but remain expensive due to repeated multi-step denoising. Existing training-free acceleration methods rely on binary cache-or-recompute decisions, overlooking…

Computer Vision and Pattern Recognition · Computer Science 2026-04-06 Hanshuai Cui , Zhiqing Tang , Zhi Yao , Fanshuai Meng , Weijia Jia , Wei Zhao

Video autoencoders compress videos into compact latent representations for efficient reconstruction, playing a vital role in enhancing the quality and efficiency of video generation. However, existing video autoencoders often entangle…

Computer Vision and Pattern Recognition · Computer Science 2025-12-15 Cuifeng Shen , Lumin Xu , Xingguo Zhu , Gengdai Liu

Modern visual agents require representations that are general, causal, and physically structured to operate in real-time streaming environments. However, current vision foundation models remain fragmented, specializing narrowly in image…

Computer Vision and Pattern Recognition · Computer Science 2026-03-13 Yibin Yan , Jilan Xu , Shangzhe Di , Haoning Wu , Weidi Xie

Video generation models have advanced significantly, yet they still struggle to synthesize complex human movements due to the high degrees of freedom in human articulation. This limitation stems from the intrinsic constraints of pixel-only…

Computer Vision and Pattern Recognition · Computer Science 2025-12-23 Yuxiao Yang , Hualian Sheng , Sijia Cai , Jing Lin , Jiahao Wang , Bing Deng , Junzhe Lu , Haoqian Wang , Jieping Ye

We present Infinity, a Bitwise Visual AutoRegressive Modeling capable of generating high-resolution, photorealistic images following language instruction. Infinity redefines visual autoregressive model under a bitwise token prediction…

Computer Vision and Pattern Recognition · Computer Science 2025-06-18 Jian Han , Jinlai Liu , Yi Jiang , Bin Yan , Yuqi Zhang , Zehuan Yuan , Bingyue Peng , Xiaobing Liu

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

Video diffusion models have rich world priors, but their use in spatial tasks is limited by poor control, spatial-temporal inconsistent results, and entangled scene-camera dynamics. Current approaches, such as per-task fine-tuning or…

Graphics · Computer Science 2026-03-24 Chenxi Song , Yanming Yang , Tong Zhao , Ruibo Li , Chi Zhang