English
Related papers

Related papers: Quant VideoGen: Auto-Regressive Long Video Generat…

200 papers

Diffusion models have achieved impressive performance in video generation, but their iterative denoising process remains computationally expensive due to the large number of tokens processed at each timestep. Recently, progressive…

Computer Vision and Pattern Recognition · Computer Science 2026-05-21 Shikang Zheng , Jingkai Huang , Jiacheng Liu , Guantao Chen , Lixuan , Yuqi Lin , Peiliang Cai , Linfeng Zhang

Key-value (KV) cache memory management is the primary bottleneck limiting throughput and cost-efficiency in large-scale GPU inference serving. Current systems suffer from three compounding inefficiencies: (1) the absence of unified KV cache…

Hardware Architecture · Computer Science 2026-05-01 Sanjeev Rao Ganjihal

Large language models have shown exceptional capabilities in a wide range of tasks, such as text generation and video generation, among others. However, due to their massive parameter count, these models often require substantial storage…

Machine Learning · Computer Science 2024-10-18 Qian Tao , Wenyuan Yu , Jingren Zhou

Generating consistent long videos is a complex challenge: while diffusion-based generative models generate visually impressive short clips, extending them to longer durations often leads to memory bottlenecks and long-term inconsistency. In…

Computer Vision and Pattern Recognition · Computer Science 2025-07-22 Wenqi Ouyang , Zeqi Xiao , Danni Yang , Yifan Zhou , Shuai Yang , Lei Yang , Jianlou Si , Xingang Pan

Long streaming video QA remains challenging due to growing visual tokens and limited reasoning length of large language models (LLMs). KV-caching stores the Key-Value (KV) of the historical tokens via LLM prefill and enables more efficient…

Computer Vision and Pattern Recognition · Computer Science 2026-05-22 Junbin Xiao , Jiajun Chen , Tianxiang Sun , Xun Yang , Angela Yao

The widespread deployment of cloud-hosted generative models raises a fundamental challenge: enabling efficient autoregressive generation while preserving the privacy of both user prompts and model parameters in untrusted environments. We…

Cryptography and Security · Computer Science 2026-02-16 Hedong Zhang , Neusha Javidnia , Shweta Pardeshi , Qian Lou , Farinaz Koushanfar

Efficient inference with Large Language Models (LLMs) increasingly relies on Key-Value (KV) caches to store previously computed key and value vectors at each layer. These caches are essential to minimize redundant computation during…

Hardware Architecture · Computer Science 2026-04-08 Oteo Mamo , Olga Kogiou , Hyunjin Yi , Weikuan Yu

Autoregressive video diffusion models have enabled real-time, action-conditioned world generation. However, sustaining a persistent world, where revisiting a previously seen viewpoint yields consistent content, remains an open problem. Full…

Computer Vision and Pattern Recognition · Computer Science 2026-05-22 Jung Yi , Minjae Kim , Paul Hyunbin Cho , Wooseok Jang , Sangdoo Yun , Seungryong Kim

Visual Autoregressive (VAR) models have recently demonstrated impressive image generation quality while maintaining low latency. However, they suffer from severe KV-cache memory constraints, often requiring gigabytes of memory per generated…

Computer Vision and Pattern Recognition · Computer Science 2026-05-15 Jonathan Cederlund , Axel Berg , Durmus Alp Emre Acar , Chuteng Zhou , Pontus Giselsson

Transformer-based large language models (LLMs) demonstrate impressive performance across various natural language processing tasks. Serving LLM inference for generating long contents, however, poses a challenge due to the enormous memory…

Machine Learning · Computer Science 2024-07-01 Wonbeom Lee , Jungi Lee , Junghwan Seo , Jaewoong Sim

Long Chain-of-Thought (CoT) reasoning has significantly advanced the capabilities of Large Language Models (LLMs), but this progress is accompanied by substantial memory and latency overhead from the extensive Key-Value (KV) cache. Although…

Machine Learning · Computer Science 2025-12-23 Tao Zhang , Ziqian Zeng , Hao Peng , Huiping Zhuang , Cen Chen

Multi-frame video enhancement tasks aim to improve the spatial and temporal resolution and quality of video sequences by leveraging temporal information from multiple frames, which are widely used in streaming video processing,…

Computer Vision and Pattern Recognition · Computer Science 2025-05-27 ZhanFeng Feng , Long Peng , Xin Di , Yong Guo , Wenbo Li , Yulun Zhang , Renjing Pei , Yang Wang , Yang Cao , Zheng-Jun Zha

Recent advances in autoregressive video diffusion have enabled real-time frame streaming, yet existing solutions still suffer from temporal repetition, drift, and motion deceleration. We find that naively applying StreamingLLM-style…

Computer Vision and Pattern Recognition · Computer Science 2025-12-05 Jung Yi , Wooseok Jang , Paul Hyunbin Cho , Jisu Nam , Heeji Yoon , Seungryong Kim

Visual Autoregressive (VAR) modeling has garnered significant attention for its innovative next-scale prediction approach, which yields substantial improvements in efficiency, scalability, and zero-shot generalization. Nevertheless, the…

Machine Learning · Computer Science 2025-05-27 Kunjun Li , Zigeng Chen , Cheng-Yen Yang , Jenq-Neng Hwang

Long-context Large Language Models (LLMs) face significant memory bottlenecks during inference due to the linear growth of key-value (KV) cache with sequence length. While individual optimization techniques like KV cache quantization,…

Machine Learning · Computer Science 2025-12-02 Sai Gokhale , Devleena Das , Rajeev Patwari , Ashish Sirasao , Elliott Delaye

We introduce LogQuant, a groundbreaking 2-bit quantization technique for KV Cache in large language model (LLM) inference, delivering substantial memory savings while preserving superior performance. Previous methods either assume that…

Machine Learning · Computer Science 2026-05-19 Han Chen , Zicong Jiang , Zining Zhang , Bingsheng He , Pingyi Luo , Mian Lu , Yuqiang Chen

Recent advances in video generation have been dominated by diffusion and flow-matching models, which produce high-quality results but remain computationally intensive and difficult to scale. In this work, we introduce VideoAR, the first…

Computer Vision and Pattern Recognition · Computer Science 2026-01-15 Longbin Ji , Xiaoxiong Liu , Junyuan Shang , Shuohuan Wang , Yu Sun , Hua Wu , Haifeng Wang

Text-to-video diffusion models enable the generation of high-quality videos that follow text instructions, making it easy to create diverse and individual content. However, existing approaches mostly focus on high-quality short video…

Computer Vision and Pattern Recognition · Computer Science 2025-04-17 Roberto Henschel , Levon Khachatryan , Hayk Poghosyan , Daniil Hayrapetyan , Vahram Tadevosyan , Zhangyang Wang , Shant Navasardyan , Humphrey Shi

Existing vector quantization (VQ) based autoregressive models follow a two-stage generation paradigm that first learns a codebook to encode images as discrete codes, and then completes generation based on the learned codebook. However, they…

Computer Vision and Pattern Recognition · Computer Science 2023-05-22 Mengqi Huang , Zhendong Mao , Zhuowei Chen , Yongdong Zhang

Foundational world models must be both interactive and preserve spatiotemporal coherence for effective future planning with action choices. However, present models for long video generation have limited inherent world modeling capabilities…

Computer Vision and Pattern Recognition · Computer Science 2026-05-29 Taiye Chen , Xun Hu , Zihan Ding , Chi Jin