About me

I am a Postdoctoral Fellow in Bioinformatics at Houston Methodist, Weill Cornell Medicine, USA. I received my Ph.D. in Computer Science from Fudan University in 2025. My overarching research theme is Models that Live in the World: Grounded Multimodal Intelligence for Real-World Interaction, spanning reliable question answering, socially-aware responses in everyday life, and scientific discovery. My research interests include large language models, multimodal large models, computational social science, game theory, information economics, and AI-based interdisciplinary research, with a focus on bioinformatics.

I ask what capabilities enable models to operate in the world and create real value. Rather than passive instruction-following agents or generic emotional chatbots, I study models as reliable experts, collaborators, and supportive partners. I organize this agenda around four distinct worlds: Physical, Objective, Subjective, and Scientific. My current work focuses on the objective and subjective worlds, with ongoing efforts in the scientific world through genomics foundation models. I plan to expand into the physical world through embodied AI to enable deeper real-world interaction. [CV]

💡Highlights

34 publications including 23 as first author in top conferences.
Active academic service including over 100 peer reviews for top conferences and journals.
Innovation outputs including 49 patents filed with 30 granted.
Industry experience at Microsoft Research Asia, TikTok.
Founded two AI-driven consultation systems, ProAdvisor and VerbalValue, and built the AI-powered emotional companion platform DeepSupport.

News

🧬 [Apr 20, 2026] Released DeltaMap — a paired scRNA-seq pipeline that constructs immune-state evidence representations from longitudinal delta signals. [Code]
🔐 [Apr 12, 2026] Released GateKeeper — a cryptographic access control layer for AI agents. Agents operate on opaque object IDs instead of real filesystem paths. [Code]
🧬 [Apr 8, 2026] Released CUT&Tag Agent — an AI-powered epigenomic pipeline assistant that converts CUT&Tag tutorials into interactive agentic workflows. [Code] [Demo]
🏥 [Mar 18, 2026] Released CTIAgent — an active evidence acquisition agent for clinical trial intelligence. [Code]
💬 [Feb 19, 2026] Launched MischiefClub demo — a cathartic, role-based venting interface with reality-blocking guardrails. [Code] [Demo]
🔐 [Feb 18, 2026] Released PolitePoison — a real-world implicit toxicity dialogue dataset for detecting polite but harmful utterances. [Dataset]
💬 [Feb 18, 2026] Introduced three new DeepSupport personas: Tsukkomi, Real, and Gonzo, and provided runnable examples. [Tsukkomi] [Real] [Gonzo]
💼 [Jan 07, 2026] Launched ProAdvisor and VerbalValue demos — my entrepreneurial projects. Welcome to connect and collaborate! [ProAdvisor] [VerbalValue]
🔐 [Jan 05, 2026] Released GPU Watchdog — a tiny HPC-friendly GPU usage watcher with email alerts. [Code]
💬 [Jan 04, 2026] Introduced another mode of DeepSupport: DeepSupport Warm — an emotional-holding companion, and released the Warm LoRA adapter. [Warm] [Model]
💬 [Dec 23, 2025] Proposed DeepSupport and released its first mode: DeepSupport Coach — a problem-clarification and action-planning companion. [Code] [Coach]
🔐 [Dec 18, 2025] Released mmqlint — a lightweight quality gate for LLM and VLM training and inference datasets. [Code]
🛠️ [Dec 16, 2025] Released 3D↔2D Toolkit — a generic 3D↔2D slicing and multiview fusion pipeline. [Code]
💬 [Dec 12, 2025] Released MoodTrace — a longitudinal emotion dialogue benchmark scaffold. [Dataset]

Representative Publications

Understanding, Explanation, Reasoning, and High-Quality Answering with Large Models

[2025] Yuyan Chen, Jiyuan Jia, Jiaxin Lu, Siyue Li, Yu Guan, Ming Yang, Qingpei Guo. VQAGuider: Guiding Multimodal Large Language Models to Answer Complex Video Questions. Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (ACL). 2025. [pdf] [code] [bib]
[2023] Yuyan Chen, Yanghua Xiao, Bang Liu, Zhixu Li. XMQAs: Constructing Complex-Modified Question-Answering Dataset for Robust Question Understanding. IEEE Transactions on Knowledge and Data Engineering (TKDE). 2023. [pdf] [code] [bib]
[2025] Yuyan Chen, Zehao Li, Shuangjie You, Zhengyu Chen, Jingwen Chang, Yi Zhang, Weinan Dai, Qingpei Guo, Yanghua Xiao. Attributive Reasoning for Hallucination Diagnosis of Large Language Models. Proceedings of the 39th AAAI Conference on Artificial Intelligence (AAAI). 2025. [pdf] [code] [bib]
[2023] Yuyan Chen, Qiang Fu, Yichen Yuan, Zhihao Wen, Ge Fan, Dayiheng Liu, Dongmei Zhang, Zhixu Li, Yanghua Xiao. Hallucination Detection: Discerning Reliable Responses in Large Language Models. Proceedings of the ACM International Conference on Information and Knowledge Management (CIKM). 2023. [pdf] [bib]

Social Cognition and Interaction Modeling with Large Models

[2025] Yuyan Chen, Yifan Jiang, Li Zhou, Jinghan Cao, Yu Guan, Ming Yang, Qingpei Guo. Engage for All: Making Ordinary Image Descriptions Appealing Again! Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV). 2025. [pdf] [code] [bib]
[2024] Yuyan Chen, Yichen Yuan, Panjun Liu, Dayiheng Liu, Qinghao Guan, Mengfei Guo, Haiming Peng, Zhixu Li, Yanghua Xiao, Bang Liu. Talk Funny! A Large-Scale Humor Response Dataset with Chain-of-Humor Interpretation. Proceedings of the 38th AAAI Conference on Artificial Intelligence (AAAI). 2024. [pdf] [code] [bib]
[2024] Yuyan Chen, Yiwen Qian, Songzhou Yan, Jiyuan Jia, Zhixu Li, Yanghua Xiao, Xiaobo Li, Ming Yang, Qingpei Guo. HOTVCOM: Generating Buzzworthy Comments for Videos. Findings of the Annual Meeting of the Association for Computational Linguistics (ACL). 2024. [pdf] [code] [bib]
[2024] Yuyan Chen, Songzhou Yan, Zhixu Li, Yanghua Xiao. XMeCap: Meme Caption Generation with Sub-Image Adaptability. Proceedings of the ACM International Conference on Multimedia (ACM MM). 2024. [pdf] [bib]

Representative Patents

[2024] Yuyan Chen, Yueze Li, Jiaqing Liang, Yanghua Xiao. Evaluation Device for Questioning Capabilities in Education for Large Language Models. ZL202410780038.9.
[2024] Yuyan Chen, Yueze Li, Jiaqing Liang, Yanghua Xiao. Evaluation Device for Emotional Cognition Capabilities of Large Language Models. ZL202410780037.4.
[2024] Yuyan Chen, Yueze Li, Jiaqing Liang, Yanghua Xiao. Evaluation Device for Problem-Solving Capabilities under Incomplete Information for Large Language Models. ZL202410780036.X.
[2023] Yuyan Chen, Yanghua Xiao, Zhixu Li. Solution Generation Method and Device for Nonlinear Reasoning Tasks. ZL202311856150.8.
[2023] Yuyan Chen, Zhixu Li, Jiaqing Liang, Yanghua Xiao. Method for Exploring Humor Understanding Capabilities of Pre-trained Language Models. ZL202310098163.7.