视频大模型

Input-Aware Sparse Attention for Real-Time Co-Speech Video Generation

Beijia Lu, Ziyi Chen, Jing Xiao, Jun-Yan Zhu

机构 * Carnegie Mellon University（卡内基梅隆大学） ； PAII Inc.（PAII公司） 纠错

专题命中 长视频与时序推理 ：video generation(title)；分类 cs.CV

Comments Project Page: https://beijia11.github.io/IASA

From Long Videos to Engaging Clips: A Human-Inspired Video Editing Framework with Multimodal Narrative Understanding

Xiangfeng Wang, Xiao Li, Yadong Wei, Xueyu Song, Yang Song, Xiaoqiang Xia, Fangrui Zeng, Zaiyi Chen, Liu Liu, Gu Xu, Tong Xu

机构 * University of Science and Technology of China（中国科学技术大学） ； ByteDance China（字节跳动中国） 纠错

专题命中 长视频与时序推理 ：long video(title)；分类 cs.CV

Comments Accepted by EMNLP 2025 Industry Track

Memory Forcing: Spatio-Temporal Memory for Consistent Scene Generation on Minecraft

Junchao Huang, Xinting Hu, Boyao Han, Shaoshuai Shi, Zhuotao Tian, Tianyu He, Li Jiang

专题命中 长视频与时序推理 ：video diffusion(abstract)；分类 cs.CV

Comments 19 pages, 8 figures