My name is Yan Zhuang. I am a Ph.D. candidate in the Affective Computing and Advanced Intelligence Laboratory and Intelligame Lab at University of Electronic Science and Technology of China (UESTC), advised by Prof. Fuji Ren. I earned my Master’s degree in Computer Technology from UESTC under the guidance of Prof. Yanru Zhang, and my Bachelor’s degree in Information and Computing Science from Anhui Science and Technology University.

My research interest lies in Multimodal Intelligence. During my Ph.D., I focused on multimodal representation alignment, fusion, and unified generalization, with applications in affective computing and robust learning under missing/noisy modalities. Going forward, I am pivoting toward MLLM-driven Applications, including world models, embodied intelligence, and open-ended multimodal reasoning.

I am actively seeking postdoctoral positions related to MLLM (Multimodal Large Language Models). I am especially interested in Embodied Intelligence, World Models, and VLA (Vision-Language-Action). If there are opportunities in Hong Kong or Singapore, please do not hesitate to contact me!

     Multimodal Application
    Affective understanding and reasoning
Robust multimodal application under missing and noisy signals
Multimodal representation alignment, fusion, and unification

  

     RLVR-based Application
    Reinforcement Learning with Verifiable Rewards
Multimodal mathematical problem solving
Math verification and reasoning

  

     MLLM-based Application
    MLLM for Healthcare
World Model and Embodied Intelligence
Vision-Language-Action (VLA)

  

News

2026.05: 🎉🎉 One paper (ReNoRD) is accepted by ACM International Conference on Multimedia Retrieval (ICMR 2026).
2026.04: 🎉🎉 One paper (DEJA) is accepted by The 64th Annual Meeting of the Association for Computational Linguistics (ACL Main 2026).
2026.03: 🎉🎉 One paper (DHM) is accepted by Neurocomputing 2026.
2026.01: 🎉🎉 One paper (TMDC) is accepted by The 40th Annual AAAI Conference on Artificial Intelligence (AAAI 2026).
2025.09: 🎉🎉 One paper (HME) is accepted by The 38th Conference on Neural Information Processing Systems (NeurIPS 2025).
2025.07: 🎉🎉 One paper (CMAD) is accepted by The IEEE/CVF International Conference on Computer Vision (ICCV 2025).
2025.04: 🎉🎉 One paper (FAME) is accepted by ACM Multimedia 2025 (ACM MM 2025).
2025.03: 🎉🎉 One paper (IIE) is accepted by IEEE Transactions on Multimedia (IEEE-TMM 2025).
2025.02: 🎉🎉 One paper (MLCL) is accepted by IEEE Transactions on Multimedia (IEEE-TMM 2025).
2025.01: 🎉🎉 One paper (R3DG) is accepted by Research 2025.
2025.01: 🎉🎉 One paper is accepted by IEEE Transactions on Affective Computing (IEEE-TAFFC 2025).
2025.01: 🎉🎉 One paper (ETS-MM) is accepted by The Web Conference 2025 (WWW 2025).
2024.11: 🎉🎉 One paper is accepted by IEEE Transactions on Knowledge and Data Engineering (IEEE-TKDE 2025).
2024.07: 🎉🎉 One paper (GLoMo) is accepted by ACM Multimedia 2024 (ACM MM 2024).

Publications

(*denotes joint first-authors, Google Scholar)

ACL Main 2026

Beyond Explicit Refusals: Soft-Failure Attacks on Retrieval-Augmented Generation

Wentao Zhang, Yan Zhuang, Zhuhang Zheng, Mingfei Zhang, Jiawen Deng, Fuji Ren

In The 64th Annual Meeting of the Association for Computational Linguistics (ACL Main 2026)

Paper Code

AAAI 2026

TMDC: A Two-Stage Modality Denoising and Complementation Framework for Multimodal Sentiment Analysis with Missing and Noisy Modalities

Yan Zhuang*, Minhao Liu*, Yanru Zhang, Jiawen Deng, Fuji Ren

In The 40th Annual AAAI Conference on Artificial Intelligence (AAAI 2026)

Paper Code

NeurIPS 2025

Hyper-Modality Enhancement for Multimodal Sentiment Analysis with Missing Modalities

Yan Zhuang*, Minhao Liu*, Wei Bai, Yanru Zhang, Wei Li, Jiawen Deng, Fuji Ren

In The 38th Conference on Neural Information Processing Systems (NeurIPS 2025)

Paper Code

ICCV 2025

CMAD: Correlation-Aware and Modalities-Aware Distillation for Multimodal Sentiment Analysis with Missing Modalities

Yan Zhuang, Minhao Liu, Wei Bai, Yanru Zhang, Xiaoyue Zhang, Jiawen Deng, Fuji Ren

In The IEEE/CVF International Conference on Computer Vision (ICCV 2025)

Paper Code

IEEE TMM 2025

Intra-sample and Intra-modal Enhancement for Multimodal Sentiment Analysis with Missing Modalities

Yan Zhuang, Yanru Zhang, Jiawen Deng, Fuji Ren

IEEE Transactions on Multimedia (TMM 2025)

Paper Code

ICMR 2026 ReNoRD: Learning from Relations under Noisy Pseudo Labels via Relational Distillation for Multimodal Sentiment. Tiantai Zhai, Yan Zhuang, Fuji Ren, Jiawen Deng, Liang Luo.
Neurocomputing 2026 Decoupled Hypergraph Modeling for Multimodal Sentiment Analysis. Yanping Huang, Jiawen Deng, Yan Zhuang, Jiali You, Qian Liu, Fuji Ren.
ACM MM 2025 FAME: Fusion-Aware Multi-modal Ensemble for Social Media Popularity Prediction. Yan Zhuang, Wei Bai, Yanru Zhang, Minhao Liu, Jiawen Deng, Fuji Ren.
IEEE TAFFC 2025 Enhanced Emotion Recognition in Conversations through Hybrid Context Encoding and Latent Dependency Mining. Zheng Hu, Jiawen Deng, Satoshi Nakagawa, Yan Zhuang, Xiaoyue Zhang, Shimin Cai, Fuji Ren.
IEEE TMM 2025 Multi-Level Contrastive Learning for Multimodal Sentiment Analysis. Yan Zhuang, Wei Bai, Yanru Zhang, Jiawen Deng, Zheng Hu, Xiaoyue Zhang, Fuji Ren.
Research 2025 R3DG: Retrieve, Rank and Reconstruction with Different Granularities for Multimodal Sentiment Analysis. Yan Zhuang, Yanru Zhang, Jiawen Deng, Fuji Ren.
WWW 2025 ETS-MM: A Multi-Modal Social Bot Detection Model Based on Enhanced Textual Semantic Representation. Wei Li, Jiawen Deng, Jiali You, Yuanyuan He, Yan Zhuang, Fuji Ren.
ACM MM 2024 GLoMo: Global-local modal fusion for multimodal sentiment analysis. Yan Zhuang, Yanru Zhang, Zheng Hu, Xiaoyue Zhang, Jiawen Deng, Fuji Ren.
IEEE TKDE 2024 Hierarchical denoising for robust social recommendation. Zheng Hu, Satoshi Nakagawa, Yan Zhuang, Jiawen Deng, Shimin Cai, Tao Zhou, Fuji Ren.
EMNLP 2022 WS Yet at the FinNLP-2022 ERAI Task: Modified models for evaluating the Rationales of Amateur Investors. Yan Zhuang, Fuji Ren.
COLING 2022 WS Yet@smm4h’22: Improved bert-based classification models with rdrop and polyloss. Yan Zhuang, Yanru Zhang.
AAAI 2022 WS Yet at Memotion 2.0 2022: Hate speech detection combining bilstm and fully connected layers. Yan Zhuang, Yanru Zhang.
AAAI 2022 WS Yet at Factify 2022: Unimodal and bimodal roberta-based models for fact checking. Yan Zhuang, Yanru Zhang.

Educations

Present: 🔍 Actively seeking a postdoctoral position in Hong Kong or Singapore, focusing on MLLM, World Models, AI for Healthcare, or Embodied Intelligence.
2022.09 - 2026.06: Ph.D. in Computer Science and Technology, University of Electronic Science and Technology of China. Advisor: Prof. Fuji Ren.
2019.09 - 2022.06: M.S. in Computer Technology, University of Electronic Science and Technology of China. Advisor: Prof. Yanru Zhang.
2015.09 - 2019.06: B.S. in Information and Computing Science, Anhui Science and Technology University.

Internships

2026.01 - Present: Intern, Tencent: Multimodal Mathematical Reasoning using Reinforcement Learning.
2022.01 - 2022.06: Research Intern, NetEase FUXI Laboratory: LLM pre-training.

Honors and Awards

2025: ACM MM 2025 Social Media Prediction (SMP) Challenge - Image Track: Best Performance Award.
2025: National Scholarship (Ph.D.).
2021: The 7th China International College Students’ “Internet+” Innovation and Entrepreneurship Competition: Silver Award.
2020: “Huawei Cup” The 17th China Post-Graduate Mathematical Contest in Modeling (GMCM): Second Prize.
2017: National Scholarship (B.S.).

Professional Service

Journal Reviewer: IEEE Transactions on Multimedia (IEEE-TMM), IEEE Transactions on Affective Computing (IEEE-TAFFC), IEEE Transactions on Circuits and Systems for Video Technology (IEEE-TCSVT), IEEE Transactions on Vehicular Technology (IEEE-TVT)
Conference Reviewer: CVPR 2026, ICML 2026 (Gold Reviewer Award, Top 25%), NeurIPS 2026