English
Related papers

Related papers: Future Forcing: Future-aware Training-free KV Cach…

200 papers

Autoregressive models have emerged as a powerful approach for visual generation but suffer from slow inference speed due to their sequential token-by-token prediction process. In this paper, we propose a simple yet effective approach for…

Computer Vision and Pattern Recognition · Computer Science 2025-04-04 Yuqing Wang , Shuhuai Ren , Zhijie Lin , Yujin Han , Haoyuan Guo , Zhenheng Yang , Difan Zou , Jiashi Feng , Xihui Liu

For autoregressive (AR) modeling of high-resolution images, vector quantization (VQ) represents an image as a sequence of discrete codes. A short sequence length is important for an AR model to reduce its computational costs to consider…

Computer Vision and Pattern Recognition · Computer Science 2022-03-10 Doyup Lee , Chiheon Kim , Saehoon Kim , Minsu Cho , Wook-Shin Han

Autoregressive diffusion enables real-time frame streaming, yet existing sliding-window caches discard past context, causing fidelity degradation, identity drift, and motion stagnation over long horizons. Current approaches preserve a fixed…

Computer Vision and Pattern Recognition · Computer Science 2026-03-16 Youngrae Kim , Qixin Hu , C. -C. Jay Kuo , Peter A. Beerel

The growing size of Large Language Models (LLMs) makes efficient inference challenging, primarily due to the memory demands of the autoregressive Key-Value (KV) cache. Existing eviction or compression methods reduce cost but rely on…

Computation and Language · Computer Science 2026-02-12 Luca Moschella , Laura Manduchi , Ozan Sener

Key-value (KV) caching has become the de-facto to accelerate generation speed for large language models (LLMs) inference. However, the growing cache demand with increasing sequence length has transformed LLM inference to be a memory bound…

Machine Learning · Computer Science 2024-10-02 Hao Kang , Qingru Zhang , Souvik Kundu , Geonhwa Jeong , Zaoxing Liu , Tushar Krishna , Tuo Zhao

Recent approaches to real-time long video generation typically employ streaming tuning strategies, attempting to train a long-context student using a short-context (memoryless) teacher. In these frameworks, the student performs long…

Computer Vision and Pattern Recognition · Computer Science 2026-02-06 Shuo Chen , Cong Wei , Sun Sun , Ping Nie , Kai Zhou , Ge Zhang , Ming-Hsuan Yang , Wenhu Chen

Video world models should maintain evolving states when evidence is unobserved, yet current generators often freeze hidden states upon interruption. This is not simply a capacity problem: pretrained video diffusion transformers already…

Computer Vision and Pattern Recognition · Computer Science 2026-05-26 Tianshuo Xu , Yichen Xie , Depu Meng , Chensheng Peng , Quentin Herau , Bo Jiang , Yihan Hu , Wei Zhan

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

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

Memory consumption of the Key-Value (KV) cache represents a major bottleneck for efficient large language model inference. While attention-score-based KV cache pruning shows promise, it faces critical practical limitations: attention scores…

Artificial Intelligence · Computer Science 2025-10-02 Alessio Devoto , Maximilian Jeblick , Simon Jégou

Autoregressive conditional image generation models have emerged as a dominant paradigm in text-to-image synthesis. These methods typically convert images into one-dimensional token sequences and leverage the self-attention mechanism, which…

Computer Vision and Pattern Recognition · Computer Science 2025-06-24 Xunzhi Xiang , Qi Fan

The autoregressive video diffusion model has recently gained considerable research interest due to its causal modeling and iterative denoising. In this work, we identify that the multi-head self-attention in these models under-utilizes…

Computer Vision and Pattern Recognition · Computer Science 2026-01-29 Hang Guo , Zhaoyang Jia , Jiahao Li , Bin Li , Yuanhao Cai , Jiangshan Wang , Yawei Li , Yan Lu

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

We present ART$\boldsymbol{\cdot}$V, an efficient framework for auto-regressive video generation with diffusion models. Unlike existing methods that generate entire videos in one-shot, ART$\boldsymbol{\cdot}$V generates a single frame at a…

Computer Vision and Pattern Recognition · Computer Science 2023-12-01 Wenming Weng , Ruoyu Feng , Yanhui Wang , Qi Dai , Chunyu Wang , Dacheng Yin , Zhiyuan Zhao , Kai Qiu , Jianmin Bao , Yuhui Yuan , Chong Luo , Yueyi Zhang , Zhiwei Xiong

Multimodal Large Language Models face severe challenges in computational efficiency and memory consumption due to the substantial expansion of the visual KV cache when processing long visual contexts. Existing KV cache compression methods…

Machine Learning · Computer Science 2026-05-07 Sihao Liu , YuFan Xiong , Zhonghua Jiang , Zhaode Wang , chengfei lv Shengyu Zhang

Existing cache-based acceleration methods for video diffusion models primarily skip early or mid denoising steps, which often leads to structural discrepancies relative to full-timestep generation and can hinder instruction following and…

Computer Vision and Pattern Recognition · Computer Science 2025-08-13 Zhentao Fan , Zongzuo Wang , Weiwei Zhang

Recently, large language models (LLMs) have shown remarkable reasoning abilities by producing long reasoning traces. However, as the sequence length grows, the key-value (KV) cache expands linearly, incurring significant memory and…

Computation and Language · Computer Science 2026-02-04 Zican Dong , Peiyu Liu , Junyi Li , Zhipeng Chen , Han Peng , Shuo Wang , Wayne Xin Zhao

Videos are inherently temporal sequences by their very nature. In this work, we explore the potential of modeling videos in a chronological and scalable manner with autoregressive (AR) language models, inspired by their success in natural…

Computer Vision and Pattern Recognition · Computer Science 2026-03-17 Yizhuo Li , Yuying Ge , Yixiao Ge , Ying Shan , Ping Luo

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

Transformer-based Large Language Models rely critically on the KV cache to efficiently handle extended contexts during the decode phase. Yet, the size of the KV cache grows proportionally with the input length, burdening both memory…

Computation and Language · Computer Science 2025-08-14 Payman Behnam , Yaosheng Fu , Ritchie Zhao , Po-An Tsai , Zhiding Yu , Alexey Tumanov