My name is Yan Zhuang. I am a Research Engineer at Tencent, where I work on Large Multimodal Models (LMMs) for Healthcare Intelligence and Neural Search. Previously, I received my Ph.D. in Computer Science and Technology from University of Electronic Science and Technology of China (UESTC), advised by Prof. Fuji Ren. Before that, I obtained my M.S. in Computer Technology from UESTC, under the supervision of Prof. Yanru Zhang, and my B.S. in Information and Computing Science from Anhui Science and Technology University.

My research focuses on Large Multimodal Models (LMMs) and their real-world applications. My interests include Multimodal Affective Computing, Multimodal Mathematical Reasoning, and Healthcare Intelligence. More broadly, I am interested in developing reliable, efficient, and trustworthy multimodal intelligent systems capable of understanding, reasoning, and interacting in complex real-world environments.

Multimodal Affective Intelligence

  • Multimodal sentiment and emotion understanding
  • Robust multimodal learning under missing, noisy, and incomplete modalities
  • Representation learning, multimodal alignment, and efficient fusion

Multimodal Reasoning & Foundation Models

  • Large multimodal models (LMMs)
  • Multimodal mathematical reasoning and self-verifiable inference
  • Reasoning, planning, and reinforcement learning for multimodal agents

Healthcare Intelligence

  • Medical multimodal intelligence
  • Clinical decision support and healthcare applications with LMMs

Recent News

Recent research updates, publications, awards, and professional activities.

  • May 2026 · 🎉 ReNoRD has been accepted to ACM International Conference on Multimedia Retrieval (ICMR 2026).
  • Apr. 2026 · 🎉 DEJA has been accepted to ACL Main 2026, marking our recent work on trustworthy reasoning for retrieval-augmented generation.
  • Mar. 2026 · 🎉 Our work DHM has been accepted by Neurocomputing.
  • Jan. 2026 · 🎉 TMDC has been accepted to AAAI 2026.
  • Sep. 2025 · 🎉 HME has been accepted to NeurIPS 2025.
  • Jul. 2025 · 🎉 CMAD has been accepted to ICCV 2025.
  • Apr. 2025 · 🎉 FAME has been accepted to ACM Multimedia 2025.
  • Mar. 2025 · 🎉 IIE has been accepted by IEEE Transactions on Multimedia (TMM).

Featured Publications

(*denotes joint first-authors. Representative publications on multimodal representation learning, robust multimodal intelligence, large multimodal models, and trustworthy reasoning. Full publication list is available on Google Scholar.)

ACL Main 2026
DEJA Framework

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

Wentao Zhang,Yan Zhuang,Zhuhang Zheng,Mingfei Zhang,Jiawen Deng,Fuji Ren
Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (ACL Main 2026)
Our work investigates previously overlooked soft-failure behaviors in retrieval-augmented generation systems and introduces a new benchmark for evaluating trustworthy multimodal reasoning.
AAAI 2026
TMDC Framework

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)
NeurIPS 2025
HME Framework

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)
ICCV 2025
CMAD Framework

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)
IEEE TMM 2025
IIE Framework

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)

Research Projects

My research has evolved around three interconnected directions: multimodal representation learning, robust multimodal intelligence, and large multimodal models for reasoning and real-world applications.

Robust Multimodal Intelligence

Building robust multimodal learning frameworks capable of handling missing modalities, noisy observations, and incomplete multimodal information. This research line focuses on modality denoising, adaptive fusion, representation enhancement, and knowledge distillation.

Representative works: TMDC (AAAI 2026), HME (NeurIPS 2025), CMAD (ICCV 2025)

Multimodal Representation Learning

Developing effective multimodal representation learning methods through contrastive learning, cross-modal alignment, global-local interaction, and relational modeling to improve multimodal understanding.

Representative works: GLoMo (ACM MM 2024), MLCL (TMM 2025), IIE (TMM 2025), ReNoRD (ICMR 2026)

Large Multimodal Models

Exploring reasoning, verification, and practical deployment of large multimodal models, with applications to mathematical reasoning, healthcare intelligence, and trustworthy AI systems.

Current topics include: RLVR, Medical LMMs, Trustworthy Reasoning

Professional Experience

My research experience spans both academia and industry, with a primary focus on multimodal intelligence, large multimodal models, and real-world AI systems.

Jul. 2026 – Present Research Engineer: Tencent

Working on large multimodal models for healthcare intelligence and next-generation AI search systems. My current research focuses on multimodal reasoning, trustworthy AI, reinforcement learning for reasoning, and practical deployment of multimodal foundation models in real-world applications.

Jan. 2026 – Jun. 2026 Research Intern: Tencent

Conducted research on reinforcement learning for multimodal mathematical reasoning and trustworthy large multimodal models, with applications to healthcare intelligence.

Jan. 2022 – Jun. 2022 Research Intern: NetEase FUXI Laboratory

Conducted research on large language model pre-training and efficient language representation learning, laying the foundation for subsequent research on multimodal foundation models.

Education

  • Sep. 2022 – Jun. 2026 Ph.D. in Computer Science and Technology
    University of Electronic Science and Technology of China (UESTC), Advisor: Prof. Fuji Ren

  • Sep. 2019 – Jun. 2022 M.S. in Computer Technology
    University of Electronic Science and Technology of China (UESTC),Advisor: Prof. Yanru Zhang

  • Sep. 2015 – Jun. 2019 B.S. in Information and Computing Science
    Anhui Science and Technology University

Honors and Awards

Academic Honors

  • UESTC Outstanding Graduate, 2026
  • UESTC Academic Newcomer Award, 2026
  • National Scholarship (Ph.D.), 2025
  • National Scholarship (B.S.), 2017

Competition Awards

  • Best Performance Award, ACM Multimedia 2025 Social Media Prediction Challenge (Image Track)
  • Silver Award, China International College Students’ “Internet+” Innovation and Entrepreneurship Competition, 2021
  • Second Prize, China Postgraduate Mathematical Contest in Modeling (Huawei Cup), 2020

Professional Activities

Journal Reviewing

  • IEEE Transactions on Multimedia (TMM 2025-2026)
  • IEEE Transactions on Affective Computing (TAFFC 2026)
  • IEEE Transactions on Circuits and Systems for Video Technology (TCSVT 2026)
  • Transactions on Machine Learning Research (TMLR 2026)
  • Knowledge-Based Systems (KBS 2026)
  • IEEE Transactions on Vehicular Technology (TVT 2023-2024)

Conference Reviewing

  • CVPR 2026
  • ICML 2026 (Gold Reviewer Award, Top 25%)
  • NeurIPS 2026

Thank you for visiting my homepage. I am always happy to discuss research collaborations, academic exchanges, and opportunities related to multimodal intelligence, large multimodal models, and trustworthy AI.