中文
相关论文

相关论文: Echo-Forcing: A Scene Memory Framework for Interac…

200 篇论文

Interactive long video generation requires prompt switching to introduce new subjects or events, while maintaining perceptual fidelity and coherent motion over extended horizons. Recent distilled streaming video diffusion models reuse a…

计算机视觉与模式识别 · 计算机科学 2026-03-17 Yang Yang , Tianyi Zhang , Wei Huang , Jinwei Chen , Boxi Wu , Xiaofei He , Deng Cai , Bo Li , Peng-Tao Jiang

Autoregressive video diffusion models support real-time synthesis but suffer from error accumulation and context loss over long horizons. We discover that attention heads in AR video diffusion transformers serve functionally distinct roles…

计算机视觉与模式识别 · 计算机科学 2026-05-15 Jiahao Tian , Yiwei Wang , Gang Yu , Chi Zhang

Autoregressive (AR) video generation has emerged as a promising paradigm for long-horizon video synthesis, where each frame is generated conditioned on previously generated tokens. To accelerate inference, the KV cache is used to avoid…

计算机视觉与模式识别 · 计算机科学 2026-05-29 Jiayi Luo , Qiyan Liu , Tengyang Wang , JunHao Liu , Jiayu Chen , Cong Wang , Hanxin Zhu , Chen Gao , Xiaobin Hu , Qingyun Sun , Zhibo Chen

Autoregressive (AR) video diffusion has recently emerged as a promising paradigm for long video generation, enabling causal synthesis beyond the limits of bidirectional models. To address training-inference mismatch, a series of…

计算机视觉与模式识别 · 计算机科学 2026-03-24 Zengqun Zhao , Yanzuo Lu , Ziquan Liu , Jifei Song , Jiankang Deng , Ioannis Patras

Recent advances in autoregressive video diffusion have enabled sequential and streaming video generation. However, long-horizon generation requires increasingly large KV caches, making efficient compression without sacrificing quality…

计算机视觉与模式识别 · 计算机科学 2026-05-19 Peiliang Cai , Evelyn Zhang , Jiacheng Liu , Hao Lin , Ruiqi Zhang , Weile Mo , Yue Ma , Shikang Zheng , Jiehang Huang , Dongrui Liu , Linfeng Zhang

Autoregressive video generation enables streaming and open-ended long video synthesis, but still suffers from long-term degradation caused by accumulated errors. Existing KVCache strategies usually apply unified historical-frame retention,…

计算机视觉与模式识别 · 计算机科学 2026-05-14 Jiayu Chen , Junbei Tang , Wenbiao Zhao , Maoliang Li , Jiayi Luo , Zihao Zheng , Jiawei Yang , Guojie Luo , Xiang Chen

Autoregressive video synthesis offers a promising pathway for infinite-horizon generation but is fundamentally hindered by three intertwined challenges: semantic forgetting from context limitations, visual drift due to positional…

计算机视觉与模式识别 · 计算机科学 2026-04-14 Jintao Chen , Chengyu Bai , Junjun Hu , Xinda Xue , Mu Xu

Self-forcing video generation extends a short-horizon video model to longer rollouts by repeatedly feeding generated content back in as context. This scaling path immediately exposes a systems bottleneck: the key-value (KV) cache grows with…

机器学习 · 计算机科学 2026-03-31 Suraj Ranganath , Vaishak Menon , Anish Patnaik

Autoregressive (AR) video diffusion models adopt a streaming generation framework, enabling long-horizon video generation with real-time responsiveness, as exemplified by the Self Forcing training paradigm. However, existing AR video…

计算机视觉与模式识别 · 计算机科学 2026-05-12 Yicheng Ji , Zhizhou Zhong , Jun Zhang , Qin Yang , XiTai Jin , Ying Qin , Wenhan Luo , Shuiyang Mao , Wei Liu , Huan Li

Autoregressive video diffusion models have demonstrated remarkable progress, yet they remain bottlenecked by intractable linear KV-cache growth, temporal repetition, and compounding errors during long-video generation. To address these…

计算机视觉与模式识别 · 计算机科学 2026-03-27 Xiaofeng Mao , Shaohao Rui , Kaining Ying , Bo Zheng , Chuanhao Li , Mingmin Chi , Kaipeng Zhang

The linear memory growth of the KV cache poses a significant bottleneck for LLM inference in long-context tasks. Existing static compression methods often fail to preserve globally important information. Although recent dynamic retrieval…

计算与语言 · 计算机科学 2026-04-21 Zhiyuan Shi , Qibo Qiu , Feng Xue , Zhonglin Jiang , Li Yu , Jian Jiang , Xiaofei He , Wenxiao Wang

The increasing memory demand of the Key-Value (KV) cache poses a significant bottleneck for Large Language Models (LLMs) in long-context applications. Existing low-rank KV compression methods reduce this footprint by modifying model…

计算与语言 · 计算机科学 2026-05-14 Shiyu Ji , Yixuan Wang , Yijun Liu , Qingfu Zhu , Wanxiang Che

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…

计算机视觉与模式识别 · 计算机科学 2025-12-05 Jung Yi , Wooseok Jang , Paul Hyunbin Cho , Jisu Nam , Heeji Yoon , Seungryong Kim

Recent advances in interactive video generation have shown promising results, yet existing approaches struggle with scene-consistent memory capabilities in long video generation due to limited use of historical context. In this work, we…

计算机视觉与模式识别 · 计算机科学 2025-08-13 Jiwen Yu , Jianhong Bai , Yiran Qin , Quande Liu , Xintao Wang , Pengfei Wan , Di Zhang , Xihui Liu

We introduce Sparse Forcing, a training-and-inference paradigm for autoregressive video diffusion models that improves long-horizon generation quality while reducing decoding latency. Sparse Forcing is motivated by an empirical observation…

计算机视觉与模式识别 · 计算机科学 2026-04-24 Boxun Xu , Yuming Du , Zichang Liu , Siyu Yang , Ziyang Jiang , Siqi Yan , Rajasi Saha , Albert Pumarola , Wenchen Wang , Peng Li

A unified autoregressive model is a Transformer-based framework that addresses diverse multimodal tasks (e.g., text, image, video) as a single sequence modeling problem under a shared token space. Such models rely on the KV-cache mechanism…

计算机视觉与模式识别 · 计算机科学 2026-01-09 Kunyang Li , Mubarak Shah , Yuzhang Shang

We introduce Self Forcing, a novel training paradigm for autoregressive video diffusion models. It addresses the longstanding issue of exposure bias, where models trained on ground-truth context must generate sequences conditioned on their…

计算机视觉与模式识别 · 计算机科学 2025-11-11 Xun Huang , Zhengqi Li , Guande He , Mingyuan Zhou , Eli Shechtman

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…

计算机视觉与模式识别 · 计算机科学 2026-02-06 Shuo Chen , Cong Wei , Sun Sun , Ping Nie , Kai Zhou , Ge Zhang , Ming-Hsuan Yang , Wenhu Chen

Long-form video generation presents a dual challenge: models must capture long-range dependencies while preventing the error accumulation inherent in autoregressive decoding. To address these challenges, we make two contributions. First,…

计算机视觉与模式识别 · 计算机科学 2025-10-06 Xiaofei Wu , Guozhen Zhang , Zhiyong Xu , Yuan Zhou , Qinglin Lu , Xuming He

The core challenge for streaming video generation is maintaining the content consistency in long context, which poses high requirement for the memory design. Most existing solutions maintain the memory by compressing historical frames with…

计算机视觉与模式识别 · 计算机科学 2025-12-17 Sihui Ji , Xi Chen , Shuai Yang , Xin Tao , Pengfei Wan , Hengshuang Zhao
‹ 上一页 1 2 3 10 下一页 ›