Nanjing University of Aeronautics and Astronautics (NUAA)
I am a Ph.D. candidate in Artificial Intelligence at Nanjing University of Aeronautics and Astronautics (NUAA), advised by Prof. Jie Qin and co-advised by Prof. Limin Wang (NJU). I also collaborate closely with Assoc. Prof. Wentong Li (NUAA), Dr. Wei Ji (Yale), and Dr. Fei Shen (NUS). I am currently a research intern at Tencent WeChat (Rhino-Bird Elite Talent Program), working with Dr. Qiang Chen.
I will be joining the National University of Singapore (NUS) as a CSC-funded visiting Ph.D. student for two years, supervised by Prof. Tat-Seng Chua (Academician).
My research interests include Latent Knowledge, Video Understanding, Multimodal Large Language Models, and Embodied Agents.
News
Selected Publications (* equal contribution) (view all )
Explainable Forensics of Manipulated Segments in Untrimmed Long Videos
Y. Feng*, J. Li*, Q. Lu*, W. Ji, J. Zhang, F. Shen, X. Li, Y. Jia, Q. Chen, L. Wang, W. Li, J. Qin
International Conference on Machine Learning (ICML) 2026 CCF-A
We propose a framework for explainable forensics of AI-manipulated segments in untrimmed long videos, providing temporal localization and natural language explanations.
Explainable Forensics of Manipulated Segments in Untrimmed Long Videos
Y. Feng*, J. Li*, Q. Lu*, W. Ji, J. Zhang, F. Shen, X. Li, Y. Jia, Q. Chen, L. Wang, W. Li, J. Qin
International Conference on Machine Learning (ICML) 2026 CCF-A
We propose a framework for explainable forensics of AI-manipulated segments in untrimmed long videos, providing temporal localization and natural language explanations.
SAM3-I: Segment Anything with Instructions
J. Li*, Y. Feng*, Y. Guo*, J. Huang*, Y. Piao, Q. Bi, M. Zhang, X. Zhao, Q. Chen, S. Zou, W. Ji, H. Lu, L. Cheng
Annual Meeting of the Association for Computational Linguistics (ACL) 2026 CCF-A
We present SAM3-I, an instruction-guided segmentation model that extends SAM to handle diverse segmentation tasks through natural language instructions.
SAM3-I: Segment Anything with Instructions
J. Li*, Y. Feng*, Y. Guo*, J. Huang*, Y. Piao, Q. Bi, M. Zhang, X. Zhao, Q. Chen, S. Zou, W. Ji, H. Lu, L. Cheng
Annual Meeting of the Association for Computational Linguistics (ACL) 2026 CCF-A
We present SAM3-I, an instruction-guided segmentation model that extends SAM to handle diverse segmentation tasks through natural language instructions.
MoniTor: Exploiting Large Language Models with Instruction for Online Video Anomaly Detection
S. Yang*, Y. Feng*, Y. Liu, J. Zhang, J. Qin
Annual Conference on Neural Information Processing Systems (NeurIPS) 2025 CCF-A
We propose MoniTor, which leverages LLMs with instruction tuning for online video anomaly detection in streaming scenarios.
MoniTor: Exploiting Large Language Models with Instruction for Online Video Anomaly Detection
S. Yang*, Y. Feng*, Y. Liu, J. Zhang, J. Qin
Annual Conference on Neural Information Processing Systems (NeurIPS) 2025 CCF-A
We propose MoniTor, which leverages LLMs with instruction tuning for online video anomaly detection in streaming scenarios.
MUVR: A Multi-Modal Untrimmed Video Retrieval Benchmark with Multi-Level Visual Correspondence
Y. Feng, J. Hu, Q. Lu, J. Niu, L. Tan, S. Yuan, Z. Yan, Y. Jia, Q. He, S. Ge, E.Q. Chen, W. Li, L. Wang, J. Qin
Annual Conference on Neural Information Processing Systems (NeurIPS) 2025 CCF-A
We introduce MUVR, a large-scale benchmark for multi-modal untrimmed video retrieval with multi-level visual correspondence annotations.
MUVR: A Multi-Modal Untrimmed Video Retrieval Benchmark with Multi-Level Visual Correspondence
Y. Feng, J. Hu, Q. Lu, J. Niu, L. Tan, S. Yuan, Z. Yan, Y. Jia, Q. He, S. Ge, E.Q. Chen, W. Li, L. Wang, J. Qin
Annual Conference on Neural Information Processing Systems (NeurIPS) 2025 CCF-A
We introduce MUVR, a large-scale benchmark for multi-modal untrimmed video retrieval with multi-level visual correspondence annotations.
RefineTAD: Learning Proposal-free Refinement for Temporal Action Detection
Y. Feng, Z. Zhang, R. Quan, L. Wang, J. Qin
ACM International Conference on Multimedia (ACM MM) 2023 CCF-A Honorable Mention Award (Top 1‰)
We propose RefineTAD, a proposal-free framework for temporal action detection that achieves state-of-the-art performance with a novel refinement mechanism.
RefineTAD: Learning Proposal-free Refinement for Temporal Action Detection
Y. Feng, Z. Zhang, R. Quan, L. Wang, J. Qin
ACM International Conference on Multimedia (ACM MM) 2023 CCF-A Honorable Mention Award (Top 1‰)
We propose RefineTAD, a proposal-free framework for temporal action detection that achieves state-of-the-art performance with a novel refinement mechanism.
All publications
Education
Ph.D. Candidate in Artificial Intelligence
Advisor: Prof. Jie Qin | Co-Advisor: Prof. Limin Wang
B.S. in Computer Science (Rank 1st) | GPA: 4.1/5.0 | Average: 91/100
Experience
Research Intern (Rhino-Bird Elite Talent Program)
Advisor: Dr. Qiang Chen
CSC-funded Visiting Ph.D. Student
Advisor: Prof. Tat-Seng Chua (Academician)