About Me

I am a Ph.D. student at the College of Computing and Data Science (CCDS) at Nanyang Technological University (NTU), starting in Spring 2026, where I am fortunate to be supervised by Prof. Sean Du. Previously, I obtained both my Master's and Bachelor's degrees from Southwest Jiaotong University, where I was advised by Prof. Fengmao Lv and had a close and fruitful collaboration with Prof. Wenya Wang. My research interests include the Reliability, Security, Alignment, and Reasoning of Large Language Models (LLMs) and Multimodal Large Language Models (MLLMs).

News

[07/08/2026] One paper was awarded the Journal to Conference Certificate (Top 10%) of TMLR!
[01/07/2026] Start my journey at NTU!
[09/25/2025] Honored to receive a Ph.D. offer from Prof. Sean Du to join his group at NTU!
[07/06/2025] One paper was accepted as an oral presentation at ACM Multimedia 2025.
[01/21/2025] One paper was accepted as an oral presentation at The Web Conference 2025.
[07/25/2024] One paper was accepted to ACM Multimedia 2024.
[07/25/2024] One paper was accepted as an oral presentation at CIKM 2024.

Publications

Reasoning Denoiser: Denoising Reasoning Traces for Hallucination Detection in Large Reasoning Models
Junlin Fang, Do Nguyen-Thanh, Xiaogang Xu, Zhen Fang, Sean Du
arXiv preprint arXiv:2607.22098, 2026
[PDF] [Code]

VLMGuard: Bootstrapping Malicious Prompt Detectors from Unlabeled Vision-Language Prompts in the Wild
Junlin Fang, Wenyu Chen, Reshmi Ghosh, Robert Sim, Ahmed Salem, Vitor R. Carvalho, Emily Lawton, Sharon Li, Jack W. Stokes, Sean Du
Transactions on Machine Learning Research (TMLR), 2026
Journal to Conference Certificate (Top 10%)
[PDF] [Code]

Rethinking the Effect of Unimodal Labels in Multimodal Sentiment Analysis
Lingli Zhang, Tianrui Li, Baiyu Lu, Junlin Fang, Desheng Zheng, Wei Zhou, Weide Liu, Fengmao Lv
ACM Transactions on Multimedia Computing, Communications, and Applications (TOMM), 2026
[PDF] [Code]

Modeling Deep Fusion of Intra- and Inter-Modal Incongruity for Multimodal Sarcasm Detection
Fengmao Lv, Junlin Fang, Guosheng Lin, Wenya Wang
IEEE Transactions on Knowledge and Data Engineering (TKDE), 2026
[PDF] [Code]

Why is a Bird's Caption a Good Demonstration? Towards Effective Multimodal In-Context Learning without Dedicated Data
Junlin Fang, Wenya Wang, Lingli Zhang, Fengmao Lv
ACM International Conference on Multimedia 2025 (ACM MM) Oral
[PDF] [Code]

MSTI-Plus: Introducing Non-Sarcasm Reference Materials to Enhance Multimodal Sarcasm Target Identification
Fengmao Lv, Mengting Xiong, Junlin Fang, Lingli Zhang, Tianze Luo, Weichao Liang, Tianrui Li
The ACM Web Conference 2025 (WWW) Oral
[PDF] [Code]

Sentiment-oriented Sarcasm Integration for Video Sentiment Analysis Enhancement with Sarcasm Assistance
Junlin Fang, Wenya Wang, Guosheng Lin, Fengmao Lv
ACM International Conference on Multimedia 2024 (ACM MM)
[PDF] [Code]

Progressive Multimodal Pivot Learning: Towards Semantic Discordance Understanding as Humans
Junlin Fang, Wenya Wang, Tianze Luo, Yanyong Huang, Fengmao Lv
ACM International Conference on Information and Knowledge Management 2024 (CIKM) Oral
[PDF] [Code]

Work Experience

Apodex, Apr. 2026 – Present

Education

Ph.D. in Computer Science
Nanyang Technological University, Singapore
Jan. 2026 – Present

M.S. in Computer Science and Technology
Southwest Jiaotong University, China
Sep. 2023 – Dec. 2025

B.Eng. in Computer Science and Technology
Southwest Jiaotong University, China
Sep. 2019 – Jun. 2023

Services

Senior Program Committee: International Workshop on Trustworthy Multimodal Learning for Social Media Analysis, The ACM Web Conference (WWW) 2026
Conference Reviewer: ICML (2024, 2025, 2026), ICLR (2024, 2025, 2026), NeurIPS (2024, 2025, 2026), ACM MM (2024, 2025)
Journal Reviewer: IEEE TMM, IEEE TCSVT