English
Related papers

Related papers: TokenTrim: Inference-Time Token Pruning for Autore…

200 papers

While video compression algorithms effectively reduce bitrate, aggressive quantization often compromises temporal coherence, introducing artifacts such as flicker, motion inconsistency, and unstable textures. Although spatial quality…

Image and Video Processing · Electrical Eng. & Systems 2026-05-19 Peter Zsoldos

We present a novel unconditional video generative model designed to address long-term spatial and temporal dependencies, with attention to computational and dataset efficiency. To capture long spatio-temporal dependencies, our approach…

Computer Vision and Pattern Recognition · Computer Science 2024-08-13 Partha Ghosh , Soubhik Sanyal , Cordelia Schmid , Bernhard Schölkopf

Generating long-duration videos has always been a significant challenge due to the inherent complexity of spatio-temporal domain and the substantial GPU memory demands required to calculate huge size tensors. While diffusion based…

Computer Vision and Pattern Recognition · Computer Science 2024-12-02 Siyang Zhang , Ser-Nam Lim

Auto-Regressive Video Diffusion Models (AR-VDMs) have shown strong capabilities in generating long, photorealistic videos, but suffer from two key limitations: (i) history forgetting, where the model loses track of previously generated…

Computer Vision and Pattern Recognition · Computer Science 2025-12-30 Jing Wang , Fengzhuo Zhang , Xiaoli Li , Vincent Y. F. Tan , Tianyu Pang , Chao Du , Aixin Sun , Zhuoran Yang

Autoregressive (AR) architectures have achieved significant successes in LLMs, inspiring explorations for video generation. In LLMs, top-p/top-k sampling strategies work exceptionally well: language tokens have high semantic density and low…

Computer Vision and Pattern Recognition · Computer Science 2026-02-02 Yizhao Han , Tianxing Shi , Zhao Wang , Zifan Xu , Zhiyuan Pu , Mingxiao Li , Qian Zhang , Wei Yin , Xiao-Xiao Long

Text-to-video (T2V) diffusion models have rapidly advanced, yet generations still occasionally fail in practice, such as low text-video alignment or low perceptual quality. Since diffusion sampling is non-deterministic, it is difficult to…

Computer Vision and Pattern Recognition · Computer Science 2026-03-17 Kwon Byung-Ki , Sohwi Lim , Nam Hyeon-Woo , Moon Ye-Bin , Tae-Hyun Oh

Unsupervised multi-object scene decomposition is a fast-emerging problem in representation learning. Despite significant progress in static scenes, such models are unable to leverage important dynamic cues present in video. We propose a…

Computer Vision and Pattern Recognition · Computer Science 2020-06-29 Polina Zablotskaia , Edoardo A. Dominici , Leonid Sigal , Andreas M. Lehrmann

Unlike offline processing, streaming video vision-language models face two fundamental constraints: causality and accumulation. Causality prevents access to future frames that offline methods exploit, while accumulation causes tokens to…

Computer Vision and Pattern Recognition · Computer Science 2026-03-17 Xueyi Chen , Keda Tao , Kele Shao , Huan Wang

In this work, we introduce a new problem, named as {\em story-preserving long video truncation}, that requires an algorithm to automatically truncate a long-duration video into multiple short and attractive sub-videos with each one…

Computer Vision and Pattern Recognition · Computer Science 2019-10-15 Fan Yang , Xiao Liu , Dongliang He , Chuang Gan , Jian Wang , Chao Li , Fu Li , Shilei Wen

Deep neural networks are likely to fail when the test data is corrupted in real-world deployment (e.g., blur, weather, etc.). Test-time optimization is an effective way that adapts models to generalize to corrupted data during testing,…

Computer Vision and Pattern Recognition · Computer Science 2023-03-01 Chenyu Yi , Siyuan Yang , Yufei Wang , Haoliang Li , Yap-Peng Tan , Alex C. Kot

We introduce Self Forcing, a novel training paradigm for autoregressive video diffusion models. It addresses the longstanding issue of exposure bias, where models trained on ground-truth context must generate sequences conditioned on their…

Computer Vision and Pattern Recognition · Computer Science 2025-11-11 Xun Huang , Zhengqi Li , Guande He , Mingyuan Zhou , Eli Shechtman

Video Large Language Models (Video LLMs) achieve strong performance on video understanding tasks but suffer from high inference costs due to the large number of visual tokens. We propose KiToke, a training-free, query-agnostic token…

Computer Vision and Pattern Recognition · Computer Science 2026-04-07 Haifeng Huang , Yang Li

Image style transfer models based on convolutional neural networks usually suffer from high temporal inconsistency when applied to videos. Some video style transfer models have been proposed to improve temporal consistency, yet they fail to…

Computer Vision and Pattern Recognition · Computer Science 2018-11-02 Chang Gao , Derun Gu , Fangjun Zhang , Yizhou Yu

Recent text-to-video models have demonstrated strong temporal generation capabilities, yet their potential for image restoration remains underexplored. In this work, we repurpose CogVideo for progressive visual restoration tasks by…

Computer Vision and Pattern Recognition · Computer Science 2025-12-03 Peng Kang , Xijun Wang , Yu Yuan

Token compression expedites the training and inference of Vision Transformers (ViTs) by reducing the number of the redundant tokens, e.g., pruning inattentive tokens or merging similar tokens. However, when applied to downstream tasks,…

Computer Vision and Pattern Recognition · Computer Science 2024-08-14 Shibo Jie , Yehui Tang , Jianyuan Guo , Zhi-Hong Deng , Kai Han , Yunhe Wang

Recovering images distorted by atmospheric turbulence is a challenging inverse problem due to the stochastic nature of turbulence. Although numerous turbulence mitigation (TM) algorithms have been proposed, their efficiency and…

Image and Video Processing · Electrical Eng. & Systems 2024-04-09 Xingguang Zhang , Nicholas Chimitt , Yiheng Chi , Zhiyuan Mao , Stanley H. Chan

Transient computational fluid dynamics (CFD) remains expensive when long horizons and multi-scale turbulence are involved. Data-driven surrogates promise relief, yet many degrade over multiple steps or drift from physical behavior. This…

Fluid Dynamics · Physics 2025-12-01 Blaise Madiega , Mathieu Olivier

Time series generation is a crucial research topic in the area of decision-making systems, which can be particularly important in domains like autonomous driving, healthcare, and, notably, robotics. Recent approaches focus on learning in…

Machine Learning · Computer Science 2024-09-16 Jian Qian , Bingyu Xie , Biao Wan , Minhao Li , Miao Sun , Patrick Yin Chiang

Video classification is a challenging task in computer vision. Although Deep Neural Networks (DNNs) have achieved excellent performance in video classification, recent research shows adding imperceptible perturbations to clean videos can…

Machine Learning · Computer Science 2019-09-12 Xiaojun Jia , Xingxing Wei , Xiaochun Cao

Autoregressive large language models (LLMs) compress knowledge from their training data through next-token conditional distributions. This limits tractable querying of this knowledge to start-to-end autoregressive sampling. However, many…

Machine Learning · Computer Science 2024-03-15 Edward J. Hu , Moksh Jain , Eric Elmoznino , Younesse Kaddar , Guillaume Lajoie , Yoshua Bengio , Nikolay Malkin