Video understanding · Multimodal learning

Ruixiang Zhao 赵瑞祥

Ph.D. Candidate Renmin University of China

I am a fourth-year Ph.D. candidate at AIMC-Lab, School of Information, Renmin University of China, advised by Prof. Xirong Li. I received my B.Eng. degree from Renmin University of China in 2022.

My research focuses on video understanding and multimodal learning, with recent work on streaming audio–visual understanding and real-time interaction.

Email Google Scholar GitHub

Renmin University of China

Research

Publications

^† Equal contribution

2026

Realtime-Venus-Omni architecture and audio-visual memory

arXiv preprint, 2026. Latest

Realtime-Venus: A full-duplex interaction system with asynchronous delegation

Venus Team (Ant Group), Tsinghua University

Ruixiang Zhao^† · Core contributor ↗

Paper Project Page Code Models

OmniPro: A Comprehensive Benchmark for Omni-Proactive Streaming Video Understanding overview

arXiv preprint, 2026.

OmniPro: A Comprehensive Benchmark for Omni-Proactive Streaming Video Understanding

Ruixiang Zhao, Jie Yang, Zijie Xin, Tianyi Wang, Fengyun Rao, Jing LYU, Xirong Li

Paper Project Page Code Dataset

Stage-adaptive Token Selection for Efficient Omni-modal LLMs overview

arXiv preprint, 2026.

Stage-adaptive Token Selection for Efficient Omni-modal LLMs

Zijie Xin, Jie Yang, Ruixiang Zhao, Tianyi Wang, Fengyun Rao, Jing LYU, Xirong Li

Paper Code

SAVE: Speech-Aware Video Representation Learning for Video-Text Retrieval overview

The IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2026. CCF-A

SAVE: Speech-Aware Video Representation Learning for Video-Text Retrieval

Ruixiang Zhao^†, Zhihao Xu^†, Bangxiang Lan, Zijie Xin, Jingyu Liu, Xirong Li

Paper Code

2025

Hybrid-Tower: Fine-grained Pseudo-query Interaction and Generation for Text-to-Video Retrieval overview

International Conference on Computer Vision (ICCV), 2025. CCF-A

Hybrid-Tower: Fine-grained Pseudo-query Interaction and Generation for Text-to-Video Retrieval

Bangxiang Lan, Ruobing Xie, Ruixiang Zhao, Xingwu Sun, Zhanhui Kang, Gang Yang, Xirong Li

Paper Project Page Code

ASR-enhanced Multimodal Representation Learning for Cross-Domain Product Retrieval overview

IEEE Transactions on Multimedia (T-MM), 2025. IF: 9.7. CCF-A

ASR-enhanced Multimodal Representation Learning for Cross-Domain Product Retrieval

Ruixiang Zhao, Jian Jia, Yan Li, Xuehan Bai, Quan Chen, Han Li, Peng Jiang, Xirong Li

Paper Project Page

2024

Holistic Features are almost Sufficient for Text-to-Video Retrieval overview

The IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2024. CCF-A

Holistic Features are almost Sufficient for Text-to-Video Retrieval

Kaibin Tian^†, Ruixiang Zhao^†, Zijie Xin, Bangxiang Lan, Xirong Li

Paper Code

2023

ChinaOpen: A Dataset for Open-world Multimodal Learning overview

ACM International Conference on Multimedia (ACM MM), 2023. CCF-A

ChinaOpen: A Dataset for Open-world Multimodal Learning

Aozhu Chen, Ziyuan Wang, Chengbo Dong, Kaibin Tian, Ruixiang Zhao, Xun Liang, Zhanhui Kang, Xirong Li

Paper

Academic community

Service

Teaching Assistant

Data Structure and Algorithms I
Renmin University of China · 2023

Get in touch

Contact

Email

ruixiangzhao@ruc.edu.cn

Visitors

— Homepage views

Loading visit count…

Since Sep 2026 · Approximate visitor locations.

Statistics by Busuanzi · MapMyVisitors

World map; no visitor locations loaded

Visitor map awaiting connection