2026 顶会论文
10作者位次 #11/12ECCV 2026Poster
DiaDem: Advancing Dialogue Descriptions in Audiovisual Video Captioning for Multimodal Large Language Models
Xinlong Chen · Weihong Lin · Jingyun Hua · Linli Yao · Yue Ding · Bozhou Li · Bohan Zeng · Yang Shi · Qiang Liu · Yuanxing Zhang · Pengfei Wan · Liang Wang
多模态Vision-Language Models & Foundation ModelsOpenReview 作者位次 #8/11ECCV 2026Spotlight
MAVIN: Multi-Shot Audio-Visual Generation with Customized Narrative Control
Kaiqi Liu · Yunyao Mao · Ziqi Cai · Zheng Geng · Jing Wang · Qiulin Wang · Xintao Wang · Pengfei Wan · Kun Gai · Shuchen Weng · Boxin Shi
多模态Video Generation, Avatars & Dynamic WorldsOpenReview 作者位次 #6/6ECCV 2026Poster
Decoupling Complexity from Scale in Latent Diffusion Model
Tianxiong Zhong · Xingye Tian · Xuebo Wang · Boyuan Jiang · Xin Tao · Pengfei Wan
多模态Low-Level Vision, Restoration & Generative PriorsOpenReview 作者位次 #7/8ECCV 2026Poster
ShotStream: Streaming Multi-Shot Video Generation for Interactive Storytelling
Yawen Luo · Xiaoyu Shi · Jun-hao Zhuang · Yutian Chen · Quande Liu · Xintao Wang · Pengfei Wan · Tianfan Xue
多模态Video Understanding, Generation and Multimodal LearningOpenReview 作者位次 #5/7ECCV 2026Poster
MindFlow: Harmonizing Cognitive Semantics and Acoustic Dynamics for Facial Animation Generation in Dyadic Conversations
Hejia Chen · Haoxian Zhang · Xu He · Xiaoqiang Liu · Pengfei Wan · Shoulong Zhang · Shuai Li
安全多模态Video Generation, Avatars & Dynamic WorldsOpenReview 作者位次 #7/9ECCV 2026Poster
GRAN-TED: Generating Robust, Aligned, and Nuanced Text Embedding for Diffusion Models
Bozhou Li · Sihan Yang · Yushuo Guan · Ruichuan An · Xinlong Chen · Yang Shi · Pengfei Wan · Wentao Zhang · Yuanxing Zhang
对齐与偏好多模态Low-Level Vision, Restoration & Generative PriorsOpenReview 作者位次 #6/8ECCV 2026Poster
From Evaluation to Enhancement: Benchmarking and Improving Think-with-Video Reasoning for Video Generative Models
Meng Luo · Yicheng Liu · Jiahao Wang · Yuanxing Zhang · Xin Tao · Pengfei Wan · Kun Gai · Hao Fei
多模态评测与基准推理Video Understanding, Generation and Multimodal LearningOpenReview 作者位次 #6/7ECCV 2026Poster
OmniX: From Unified Panoramic Generation and Perception To Graphics-Ready 3D Scenes
Yukun Huang · Jiwen Yu · Yanning Zhou · Jianan Wang · Xintao Wang · Pengfei Wan · Xihui Liu
可解释性3D Graphics and Geometric RepresentationsOpenReview 作者位次 #7/8ECCV 2026Poster
Embed-RL: Reinforcement Learning for Reasoning-Driven Multimodal Embeddings
Haonan Jiang · Yuji Wang · Yongjie Zhu · Xin Lu · Wenyu Qin · Meng Wang · Pengfei Wan · Yansong Tang
多模态强化学习与后训练推理Multimodal, Video & Document UnderstandingOpenReview 作者位次 #8/10ECCV 2026Poster
MemLearner: Learning to Query Context Memory for Video World Models
Jiwen Yu · Jianxiong Gao · Jianhong Bai · Yiran Qin · Kaiyi Huang · Quande Liu · Xintao Wang · Pengfei Wan · Kun Gai · Xihui Liu
多模态检索与知识Video Generation, Avatars & Dynamic WorldsOpenReview