English
Related papers

Related papers: Focused Forcing: Content-Aware Per-Frame KV Select…

200 papers

Long-context language modeling is increasingly constrained by the Key-Value (KV) cache, whose memory and decode-time access costs scale linearly with the prefix length. This bottleneck has motivated a range of context-compression methods,…

Machine Learning · Computer Science 2026-05-13 Yoav Gelberg , Yam Eitan , Michael Bronstein , Yarin Gal , Haggai Maron

Long video understanding is heavily bottlenecked by a rigid one-shot paradigm: existing methods either densely encode videos at prohibitive memory and latency costs, or aggressively compress them into sparse frame sets that irreversibly…

Computer Vision and Pattern Recognition · Computer Science 2026-05-14 Xiao Yang , Yingzhe Ma , Haoxuan Yu , Zixin Li , Ning Qin

Autoregressive (AR) visual generation has emerged as a powerful paradigm for image and multimodal synthesis, owing to its scalability and generality. However, existing AR image generation suffers from severe memory bottlenecks due to the…

Computer Vision and Pattern Recognition · Computer Science 2025-12-05 Ziran Qin , Youru Lv , Mingbao Lin , Zeren Zhang , Chanfan Gan , Tieyuan Chen , Weiyao Lin

We address the problem of efficiently compressing video for conferencing-type applications. We build on recent approaches based on image animation, which can achieve good reconstruction quality at very low bitrate by representing face…

Computer Vision and Pattern Recognition · Computer Science 2023-07-11 Goluck Konuko , Stéphane Lathuilière , Giuseppe Valenzise

Recent diffusion models enable high-quality video generation, but suffer from slow runtimes. The large transformer-based backbones used in these models are bottlenecked by spatiotemporal attention. In this paper, we identify that a…

Computer Vision and Pattern Recognition · Computer Science 2026-03-06 Shai Yehezkel , Shahar Yadin , Noam Elata , Yaron Ostrovsky-Berman , Bahjat Kawar

Accommodating long sequences efficiently in autoregressive Transformers, especially within an extended context window, poses significant challenges due to the quadratic computational complexity and substantial KV memory requirements…

Computation and Language · Computer Science 2024-06-25 Chao Lou , Zixia Jia , Zilong Zheng , Kewei Tu

In Learned Video Compression (LVC), improving inter prediction, such as enhancing temporal context mining and mitigating accumulated errors, is crucial for boosting rate-distortion performance. Existing LVCs mainly focus on mining the…

Image and Video Processing · Electrical Eng. & Systems 2025-10-29 Wei Jiang , Junru Li , Kai Zhang , Li Zhang

Recent joint audio-visual diffusion models achieve remarkable generation quality but suffer from high latency due to their bidirectional attention dependencies, hindering real-time applications. We propose OmniForcing, the first framework…

Multimedia · Computer Science 2026-03-16 Yaofeng Su , Yuming Li , Zeyue Xue , Jie Huang , Siming Fu , Haoran Li , Ying Li , Zezhong Qian , Haoyang Huang , Nan Duan

Key frame selection in video understanding presents significant challenges. Traditional top-K selection methods, which score frames independently, often fail to optimize the selection as a whole. This independent scoring frequently results…

Computer Vision and Pattern Recognition · Computer Science 2025-12-15 Yiqing Yang , Kin-Man Lam

One of the core components of conventional (i.e., non-learned) video codecs consists of predicting a frame from a previously-decoded frame, by leveraging temporal correlations. In this paper, we propose an end-to-end learned system for…

Image and Video Processing · Electrical Eng. & Systems 2020-04-22 Nannan Zou , Honglei Zhang , Francesco Cricri , Hamed R. Tavakoli , Jani Lainema , Emre Aksu , Miska Hannuksela , Esa Rahtu

Reconstructing 3D geometry from streaming video requires continuous inference under bounded resources. Recent geometric foundation models achieve impressive reconstruction quality through all-to-all attention, yet their quadratic cost…

Computer Vision and Pattern Recognition · Computer Science 2026-04-30 Si-Yu Lu , Po-Ting Chen , Hui-Che Hsu , Sin-Ye Jhong , Wen-Huang Cheng , Yung-Yao Chen

Long-horizon LLM inference turns the key--value (KV) cache into the dominant GPU memory consumer and makes per-token attention increasingly expensive. Many common eviction policies use static recency windows or historical attention, leaving…

Machine Learning · Computer Science 2026-05-26 Yubo Li , Yidi Miao

Recent incremental learning for action recognition usually stores representative videos to mitigate catastrophic forgetting. However, only a few bulky videos can be stored due to the limited memory. To address this problem, we propose…

Computer Vision and Pattern Recognition · Computer Science 2022-11-03 Yixuan Pei , Zhiwu Qing , Jun Cen , Xiang Wang , Shiwei Zhang , Yaxiong Wang , Mingqian Tang , Nong Sang , Xueming Qian

Recently, substantial research effort has focused on how to apply CNNs or RNNs to better extract temporal patterns from videos, so as to improve the accuracy of video classification. In this paper, however, we show that temporal…

Computer Vision and Pattern Recognition · Computer Science 2017-11-28 Xiang Long , Chuang Gan , Gerard de Melo , Jiajun Wu , Xiao Liu , Shilei Wen

The ability to understand long videos is vital for embodied intelligent agents, because their effectiveness depends on how well they can accumulate, organize, and leverage long-horizon perceptual memories. Recently, multimodal LLMs have…

Computer Vision and Pattern Recognition · Computer Science 2026-03-05 Tatiana Zemskova , Solomon Andryushenko , Ilya Obrubov , Viktoriia Khoruzhaia , Ekaterina Eroshenko , Ekaterina Derevyanka , Dmitry Yudin

While standard flow-matching models transport noise to data uniformly, incorporating an explicit generation order - specifically, establishing coarse, low-frequency structure before fine detail - has proven highly effective for synthesizing…

Machine Learning · Computer Science 2026-04-24 Weitao Du

Recent reasoning models such as OpenAI-o1 and DeepSeek-R1 have shown strong performance on complex tasks including mathematical reasoning and code generation. However, this performance gain comes with substantially longer output sequences,…

Machine Learning · Computer Science 2026-04-28 Yi Su , Zhenxu Tian , Dan Qiao , Yuechi Zhou , Juntao Li , Min Zhang

Generating long sequences of tokens given a long-context input is a very compute-intensive inference scenario for large language models (LLMs). One prominent inference speed-up approach is to construct a smaller key-value (KV) cache,…

Computation and Language · Computer Science 2025-03-04 Fangyuan Xu , Tanya Goyal , Eunsol Choi

Autoregressive video generation aims at real-time, open-ended synthesis. Yet, cinematic storytelling is not merely the endless extension of a single scene; it requires progressing through evolving events, viewpoint shifts, and discrete shot…

Computer Vision and Pattern Recognition · Computer Science 2026-05-13 Yihao Meng , Zichen Liu , Hao Ouyang , Qiuyu Wang , Ka Leong Cheng , Yue Yu , Hanlin Wang , Haobo Li , Jiapeng Zhu , Yanhong Zeng , Xing Zhu , Yujun Shen , Qifeng Chen , Huamin Qu

Visual AutoRegressive modeling (VAR) based on next-scale prediction has revitalized autoregressive visual generation. Although its full-context dependency, i.e., modeling all previous scales for next-scale prediction, facilitates more…

Computer Vision and Pattern Recognition · Computer Science 2026-03-04 Yu Zhang , Jingyi Liu , Yiwei Shi , Qi Zhang , Duoqian Miao , Changwei Wang , Longbing Cao