English
Related papers

Related papers: Echo-Forcing: A Scene Memory Framework for Interac…

200 papers

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

We introduce KV-Fold, a simple, training-free long-context inference protocol that treats the key-value (KV) cache as the accumulator in a left fold over sequence chunks. At each step, the model processes the next chunk conditioned on the…

Machine Learning · Computer Science 2026-05-13 Alireza Nadali , Patrick Cooper , Ashutosh Trivedi , Alvaro Velasquez

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

Multi-shot video generation requires maintaining a consistent appearance of recurring entities across shots while remaining faithful to shot-specific text prompts. Recent autoregressive methods reuse previously generated frames as memory.…

Computer Vision and Pattern Recognition · Computer Science 2026-05-25 Jente Vandersanden , Matheus Gadelha , Chun-Hao P. Huang , Hyeonho Jeong , Yulia Gryaditskaya

There has been a recent explosion of impressive generative models that can produce high quality images (or videos) conditioned on text descriptions. However, all such approaches rely on conditional sentences that contain unambiguous…

Computer Vision and Pattern Recognition · Computer Science 2023-05-09 Tanzila Rahman , Hsin-Ying Lee , Jian Ren , Sergey Tulyakov , Shweta Mahajan , Leonid Sigal

In natural face-to-face interaction, participants seamlessly alternate between speaking and listening, producing facial behaviors (FBs) that are finely informed by long-range context and naturally exhibit contextual appropriateness and…

Computer Vision and Pattern Recognition · Computer Science 2026-03-19 Xiangyu Kong , Xiaoyu Jin , Yihan Pan , Haoqin Sun , Hengde Zhu , Xiaoming Xu , Xiaoming Wei , Lu Liu , Siyang Song

Video large language models (VideoLLMs) show strong capability in video understanding, yet long-context inference is still dominated by massive redundant visual tokens in the prefill stage. We revisit token compression for VideoLLMs under a…

Computer Vision and Pattern Recognition · Computer Science 2026-03-31 Xinying Lin , Xuyang Liu , Yiyu Wang , Teng Ma , Wenqi Ren

Generating long-form content, such as minute-long videos and extended texts, is increasingly important for modern generative models. Block diffusion improves inference efficiency via KV caching and block-wise causal inference and has been…

Computer Vision and Pattern Recognition · Computer Science 2026-02-09 Zhuokun Chen , Jianfei Cai , Bohan Zhuang

Audio-Visual Large Language Models (AV-LLMs) face prohibitive computational overhead from massive audio and video tokens. Token reduction, while extensively explored for video-only LLMs, is insufficient for the audio-visual domain, as these…

Computer Vision and Pattern Recognition · Computer Science 2025-12-12 Chao Gong , Depeng Wang , Zhipeng Wei , Ya Guo , Huijia Zhu , Jingjing Chen

Maintaining spatial world consistency over long horizons remains a central challenge for camera-controllable video generation. Existing memory-based approaches often condition generation on globally reconstructed 3D scenes by rendering…

Computer Vision and Pattern Recognition · Computer Science 2026-02-17 Zun Wang , Han Lin , Jaehong Yoon , Jaemin Cho , Yue Zhang , Mohit Bansal

Large Language Models (LLMs) excel across a variety of language tasks yet are constrained by limited input lengths and high computational costs. Existing approaches\textemdash such as relative positional encodings (e.g., RoPE, ALiBi) and…

Computation and Language · Computer Science 2025-02-18 Kun-Hui Lee , Eunhwan Park , Donghoon Han , Seung-Hoon Na

Recent advances in text-to-video diffusion models have enabled high-fidelity and temporally coherent videos synthesis. However, current models are predominantly optimized for single-event generation. When handling multi-event prompts,…

Computer Vision and Pattern Recognition · Computer Science 2026-03-24 Qianxun Xu , Chenxi Song , Yujun Cai , Chi Zhang

Recent advances in video diffusion models have unlocked new potential for realistic audio-driven talking video generation. However, achieving seamless audio-lip synchronization, maintaining long-term identity consistency, and producing…

Computer Vision and Pattern Recognition · Computer Science 2024-12-06 Longtao Zheng , Yifan Zhang , Hanzhong Guo , Jiachun Pan , Zhenxiong Tan , Jiahao Lu , Chuanxin Tang , Bo An , Shuicheng Yan

Training-free acceleration has emerged as an advanced research area in video generation based on diffusion models. The redundancy of latents in diffusion model inference provides a natural entry point for acceleration. In this paper, we…

Computer Vision and Pattern Recognition · Computer Science 2025-10-08 Yang Xiao , Gen Li , Kaiyuan Deng , Yushu Wu , Zheng Zhan , Yanzhi Wang , Xiaolong Ma , Bo Hui

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

Autoregressive video generation paradigms offer theoretical promise for long video synthesis, yet their practical deployment is hindered by the computational burden of sequential iterative denoising. While cache reuse strategies can…

Computer Vision and Pattern Recognition · Computer Science 2026-05-15 Jing Xu , Yuexiao Ma , Xuzhe Zheng , Xing Wang , Shiwei Liu , Chenqian Yan , Xiawu Zheng , Rongrong Ji , Fei Chao , Songwei Liu

Autoregressive (AR) visual generation has achieved remarkable performance but suffers from high memory usage and low throughput, as it requires caching previously generated visual tokens. Recent research has shown that retaining only a few…

Computer Vision and Pattern Recognition · Computer Science 2026-05-21 Guotao Liang , Baoquan Zhang , Zhiyuan Wen , Yunming Ye

Recent video generation models can produce smooth and visually appealing clips, but they often struggle to synthesize complex dynamics with a coherent chain of consequences. Accurately modeling visual outcomes and state transitions over…

Computer Vision and Pattern Recognition · Computer Science 2026-05-22 Ziqi Huang , Ning Yu , Gordon Chen , Haonan Qiu , Paul Debevec , Ziwei Liu

Prevailing High Dynamic Range (HDR) video reconstruction methods are fundamentally trapped in a fragile alignment-and-fusion paradigm. While explicit spatial alignment can successfully recover fine details in controlled environments, it…

Computer Vision and Pattern Recognition · Computer Science 2026-03-17 Qianyu Zhang , Bolun Zheng , Lingyu Zhu , Aiai Huang , Zongpeng Li , Shiqi Wang

KV cache pruning has emerged as a promising technique for reducing memory and computation costs in long-context auto-regressive generation. Existing methods for vision-language models (VLMs) typically rely on self-attention scores from…

Computer Vision and Pattern Recognition · Computer Science 2024-12-09 Xiaohuan Pei , Tao Huang , Chang Xu