About Me
I am a researcher and Ph.D. supervisor at the College of Computer Science, Inner Mongolia University. I received my Ph.D. in Computer Science and Technology from Inner Mongolia University in December 2024, advised by Prof. Huaiwen Zhang.
My research focuses on reliable cross-modal semantic learning: understanding and aligning information across text, images, videos, and human motion. I work on multimodal retrieval, learning with imperfect supervision, and generative retrieval, with recent interests in multimodal recommendation and video fact-checking.
Research Interests
- Multimodal retrieval. Hierarchical and compositional semantic alignment; text–motion retrieval.
- Reliable learning. Robust supervision calibration, noisy correspondence, and active learning.
- Generative multimodal intelligence. Generative retrieval, recommendation, and video fact-checking.
Publications
View Google Scholar† Equal contribution.
2026
- ACM MM
Hierarchical Token Learning with Discriminative Training for Generative Text-to-Image Retrieval
ACM Multimedia (ACM MM), 2026. Accepted
- ACM MM
CAGRec: Collaborative-Anchor Guided Multimodal Generative Recommender
ACM Multimedia (ACM MM), 2026. Accepted
- ACM MM
VIGOR: Video Fact-Checking via Experience-Guided Multi-Agent Collaborative Reasoning
ACM Multimedia (ACM MM), 2026. Accepted
- ACL Findings
CSI: An Investigative Multi-Agent Framework for Explainable Short Video Fake News Detection
Findings of the Association for Computational Linguistics: ACL 2026, 2026.
2025
- TPAMI
Active Supervised Cross-Modal Retrieval
IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2025.
2024
- ACM MM
Multi-Instance Multi-Label Learning for Text-motion Retrieval
ACM Multimedia (ACM MM), 2024.
- SIGIR
- WWW
T³RD: Test-Time Training for Rumor Detection on Social Media
The ACM Web Conference (WWW), 2024.
- ICASSP
Hierarchical Speaker Representation for Target Speaker Extraction
IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2024.
2023
- TMM
Robust Video-Text Retrieval via Noisy Pair Calibration
IEEE Transactions on Multimedia (TMM), 2023.
- ACM MM
C²MR: Continual Cross-Modal Retrieval for Streaming Multi-modal Data
ACM Multimedia (ACM MM), 2023.
- TCSVT
Debiased Video-Text Retrieval via Soft Positive Sample Calibration
IEEE Transactions on Circuits and Systems for Video Technology (TCSVT), 2023.
- ICCV
C²ST: Cross-Modal Contextualized Sequence Transduction for Continuous Sign Language Recognition
IEEE/CVF International Conference on Computer Vision (ICCV), 2023.
2022
- ICASSP
Alleviating the Loss-Metric Mismatch in Supervised Single-Channel Speech Enhancement
IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2022.
Experience & Education
- Present
Researcher · Ph.D. Supervisor
College of Computer Science, Inner Mongolia University
- 2021–2024
Ph.D. in Computer Science and Technology
Inner Mongolia University · Advisor: Prof. Huaiwen Zhang
- 2019–2021
Graduate study in Software Engineering
Inner Mongolia University · Transferred to the Ph.D. program · Advisor: Prof. Xueliang Zhang
- 2015–2019
Bachelor’s degree in E-commerce
Inner Mongolia University
Research Funding
- 2026–2028
NSFC Young Scientists Fund (Category C)
Principal investigator
- 2026–2028
Inner Mongolia Science and Technology Major Project
Subproject lead
Honors & Awards
- 2025Doctoral Dissertation Award, ACM Hohhot Chapter
- 2025Second Prize, Undergraduate Teaching Achievement Award, Inner Mongolia University
- 2024CAST Young Elite Scientists Sponsorship Program — Doctoral Student Track (supported by CCF)
- 2024President’s Scholarship, Inner Mongolia University
- National Scholarship for Doctoral Students
- First Prize, 6th Curriculum Ideological and Political Education Teaching Competition, Inner Mongolia University
Academic Service
- Professional membership. Member, CSIG Technical Committee on Multimedia.
- Conference reviewing. AAAI, ACM Multimedia, SIGIR, and KDD.
- Journal reviewing. IEEE Transactions on Multimedia and Knowledge-Based Systems.
