paper.dinq.meAI 与前沿科学顶会 · 学术新星雷达

更新于

返回新星榜

ZW

Zhibin Wang

AAAI 2026×3CVPR 2026×3ICLR 2026多模态效率与系统推理智能体与工具对齐与偏好

新星分贡献者

73

一作贡献0

核心/参与44

方向广度16

合作网络12

0 一作 · 7 篇 · AAAI 2026 / CVPR 2026 / ICLR 2026

获取完整研究档案

首次获取该候选人的完整档案及 StartLux 评估共 20 积分；每位用户单独解锁，之后查看免费。主动刷新 20 积分。

联系方式

实时查找电子邮箱，费用不超过20积分；未找到邮箱不扣费。

2026 顶会论文

7

作者位次 #2/8ICLR 2026Poster· Computer Vision / Vision Models & Multimodal

ReWatch-R1: Boosting Complex Video Reasoning in Large Vision-Language Models through Agentic Data Synthesis

Congzhi Zhang · Zhibin Wang · Yinchao Ma · Jiawei Peng · Yihan Wang · Qiang Zhou · Jun Song · Zerui Huang (Taobao &amp

多模态推理智能体与工具OpenReview

作者位次 #8/12CVPR 2026Poster· Computer Vision & Pattern Recognition

SpatialReward: Verifiable Spatial Reward Modeling for Fine-Grained Spatial Consistency in Text-to-Image Generation

Sashuai Zhou · Qiang Zhou · Junpeng Ma · Yue Cao · Ruofan Hu · Ziang Zhang · Xiaoda Yang · Zhibin Wang · Jun Song · Cheng Yu · Zerui Huang (Taobao &amp · Zhou Zhao

多模态对齐与偏好OpenReview 项目页

作者位次 #9/13CVPR 2026Spotlight· Computer Vision & Pattern Recognition

AdaSpark: Adaptive Sparsity for Efficient Long-Video Understanding

Handong Li · Zikang Liu · Longteng Guo · Tongtian Yue · Yepeng Tang · Xinxin Zhu · Chuanyang Zheng · Ziming Wang · Zhibin Wang · Jun Song · Cheng Yu · Zerui Huang (Taobao &amp · Jing Liu

多模态效率与系统OpenReview 项目页

作者位次 #8/12CVPR 2026Poster· Computer Vision & Pattern Recognition

GIFT: Global Irreplaceability Frame Targeting for Efficient Video Understanding

Junpeng Ma · Sashuai Zhou · Guanghao Li · Xin Gao · Yue Cao · Hengyu Zeng · Yuxiang Yan · Zhibin Wang · Jun Song · Zerui Huang (Taobao &amp · Shanghang Zhang · Jian Pu

多模态效率与系统OpenReview 项目页

作者位次 #3/6AAAI 2026Poster· Artificial Intelligence

StreamKV: Streaming Video Question-Answering with Segment-based KV Cache Retrieval and Compression

Yilong Chen · Xiang Bai · Zhibin Wang · Chengyu Bai · Yuhan Dai · Ming Lu

效率与系统多模态检索与知识OpenReview

作者位次 #4/7AAAI 2026Poster· Artificial Intelligence

MMG-Vid: Maximizing Marginal Gains at Segment-level and Token-level for Efficient Video LLMs

Junpeng Ma · Qizhe Zhang · Ming Lu · Zhibin Wang · Qiang Zhou · Jun Song · Shanghang Zhang

多模态效率与系统OpenReview

作者位次 #3/7AAAI 2026Poster· Artificial Intelligence

Contribution-aware Token Compression for Efficient Video Understanding via Reinforcement Learning

Yinchao Ma · Qiang Zhou · Zhibin Wang · Xianing Chen · Hanqing Yang · Jun Song · Zerui Huang (Taobao &amp

效率与系统多模态强化学习与后训练OpenReview

常见合作者

Z&Zerui Huang (Taobao &amp×5 QZQiang Zhou×4 JSJun Song×4 JMJunpeng Ma×3 YMYinchao Ma×2 SZSashuai Zhou×2 YCYue Cao×2 CYCheng Yu×2 SZShanghang Zhang×2 MLMing Lu×2 JSJun Song×2 CZCongzhi Zhang