English
Related papers

Related papers: PackForcing: Short Video Training Suffices for Lon…

200 papers

Test-Time Training (TTT) models context dependencies by adapting part of the model's weights (referred to as fast weights) during inference. This fast weight, akin to recurrent states in RNNs, stores temporary memories of past tokens in the…

Machine Learning · Computer Science 2025-06-02 Tianyuan Zhang , Sai Bi , Yicong Hong , Kai Zhang , Fujun Luan , Songlin Yang , Kalyan Sunkavalli , William T. Freeman , Hao Tan

While large language models (LLMs) excel at handling long-context sequences, they require substantial prefill computation and key-value (KV) cache, which can heavily burden computational efficiency and memory usage in both prefill and…

Machine Learning · Computer Science 2026-04-21 Dongwon Jo , Jiwon Song , Yulhwa Kim , Jae-Joon Kim

Streaming video generation, as one fundamental component in interactive world models and neural game engines, aims to generate high-quality, low-latency, and temporally coherent long video streams. However, most existing work suffers from…

Computer Vision and Pattern Recognition · Computer Science 2025-09-30 Kunhao Liu , Wenbo Hu , Jiale Xu , Ying Shan , Shijian Lu

Masked-based autoregressive models have demonstrated promising image generation capability in continuous space. However, their potential for video generation remains under-explored. In this paper, we propose \textbf{VideoMAR}, a concise and…

Computer Vision and Pattern Recognition · Computer Science 2025-06-19 Hu Yu , Biao Gong , Hangjie Yuan , DanDan Zheng , Weilong Chai , Jingdong Chen , Kecheng Zheng , Feng Zhao

Long-context video modeling is critical for multimodal large language models (MLLMs), enabling them to process movies, online video streams, and so on. Despite its advances, handling long videos remains challenging due to the difficulty in…

Computer Vision and Pattern Recognition · Computer Science 2025-07-15 Xinhao Li , Yi Wang , Jiashuo Yu , Xiangyu Zeng , Yuhan Zhu , Haian Huang , Jianfei Gao , Kunchang Li , Yinan He , Chenting Wang , Yu Qiao , Yali Wang , Limin Wang

Diffusion transformers have shown significant effectiveness in both image and video synthesis at the expense of huge computation costs. To address this problem, feature caching methods have been introduced to accelerate diffusion…

Machine Learning · Computer Science 2025-02-20 Chang Zou , Xuyang Liu , Ting Liu , Siteng Huang , Linfeng Zhang

Token-based video representation has emerged as a promising approach for enabling large language models (LLMs) to interpret video content. However, existing token reduction techniques, such as pruning and merging, often disrupt essential…

Computer Vision and Pattern Recognition · Computer Science 2025-09-30 Haichao Zhang , Yun Fu

Multi-modal Large Language Models (MLLMs) serving systems commonly employ KV-cache compression to reduce memory footprint. However, existing compression methods introduce significant processing overhead and queuing delays, particularly in…

Multimedia · Computer Science 2025-03-12 Jianian Zhu , Hang Wu , Haojie Wang , Yinghui Li , Biao Hou , Ruixuan Li , Jidong Zhai

Unified models aim to support both understanding and generation by encoding images into discrete tokens and processing them alongside text within a single autoregressive framework. This unified design offers architectural simplicity and…

Computer Vision and Pattern Recognition · Computer Science 2026-03-13 Ziyao Wang , Chen Chen , Jingtao Li , Weiming Zhuang , Jiabo Huang , Ang Li , Lingjuan Lyu

Tokenized visual representations have shown promise in image compression, yet their extension to video remains underexplored due to the challenges posed by complex temporal dynamics and stringent bit rate constraints. In this paper, we…

Image and Video Processing · Electrical Eng. & Systems 2025-11-20 Lebin Zhou , Cihan Ruan , Nam Ling , Zhenghao Chen , Wei Wang , Wei Jiang

Video-based multimodal large language models (Video-LLMs) possess significant potential for video understanding tasks. However, most Video-LLMs treat videos as a sequential set of individual frames, which results in insufficient…

Computer Vision and Pattern Recognition · Computer Science 2024-10-16 Xiaohan Lan , Yitian Yuan , Zequn Jie , Lin Ma

Existing video tokenizers typically use the traditional Variational Autoencoder (VAE) architecture for video compression and reconstruction. However, to achieve good performance, its training process often relies on complex multi-stage…

Computer Vision and Pattern Recognition · Computer Science 2025-03-28 Nianzu Yang , Pandeng Li , Liming Zhao , Yang Li , Chen-Wei Xie , Yehui Tang , Xudong Lu , Zhihang Liu , Yun Zheng , Yu Liu , Junchi Yan

TabPFN v2 achieves better results than tree-based models on several tabular benchmarks, which is notable since tree-based models are usually the strongest choice for tabular data. However, it cannot handle more than 10K context tokens…

Machine Learning · Computer Science 2025-09-18 Renat Sergazinov , Shao-An Yin

We propose an efficient framework to compress massive video-frame features before feeding them into large multimodal models, thereby mitigating the severe token explosion arising from hour-long videos. Our design leverages a bidirectional…

Computer Vision and Pattern Recognition · Computer Science 2026-02-10 Geewook Kim , Minjoon Seo

Most text-video retrieval methods utilize the text-image pre-trained models like CLIP as a backbone. These methods process each sampled frame independently by the image encoder, resulting in high computational overhead and limiting…

Computer Vision and Pattern Recognition · Computer Science 2025-03-13 Leqi Shen , Tianxiang Hao , Tao He , Sicheng Zhao , Yifeng Zhang , Pengzhang Liu , Yongjun Bao , Guiguang Ding

Frame-level autoregressive (frame-AR) models have achieved significant progress, enabling real-time video generation comparable to bidirectional diffusion models and serving as a foundation for interactive world models and game engines.…

Computer Vision and Pattern Recognition · Computer Science 2025-12-24 Tianrui Zhu , Shiyi Zhang , Zhirui Sun , Jingqi Tian , Yansong Tang

Key-Value (KV) cache remains a major bottleneck for deploying Large Language Models (LLMs) in long-generation tasks. Prior work often applies uniform compression across both prefill and decoding caches, but compressing the prefill cache…

Artificial Intelligence · Computer Science 2026-05-29 Soumyadeep Jana , Sagar Nishad , Sanasam Ranbir Singh

Recently, with the emergence of large language models, multimodal LLMs have demonstrated exceptional capabilities in image and video modalities. Despite advancements in video comprehension, the substantial computational demands of long…

Computer Vision and Pattern Recognition · Computer Science 2025-08-13 Ming Nie , Chunwei Wang , Hang Xu , Li Zhang

Long-form video question answering (VQA) overwhelms current vision-language models (VLMs) because attention and key-value (KV) caches grow with runtime, forcing either expensive inference or near-sighted sliding windows. We introduce…

Computer Vision and Pattern Recognition · Computer Science 2025-11-18 Shrenik Patel , Daivik Patel

Long Video Question-Answering (LVQA) presents a significant challenge for Multi-modal Large Language Models (MLLMs) due to immense context and overloaded information, which could also lead to prohibitive memory consumption. While existing…

Computer Vision and Pattern Recognition · Computer Science 2026-01-06 Henghui Du , Chunjie Zhang , Xi Chen , Chang Zhou , Di Hu