Hi there! I am Xinlong Chen (陈鑫龙), a Ph.D. student at NLPR, CASIA, where I am fortunate to be advised by Prof. Tieniu Tan and co-advised by Prof. Qiang Liu. My research focuses on the training and application of MLLMs, with particular interests in video understanding and hallucination mitigation.

Currently, I am a research intern at Kling Team, Kuaishou Technology, under the guidance of Yuanxing Zhang and Weihong Lin.

I am always open to research discussions and collaboration opportunities——feel free to reach out! 😁

📝 Selected Publications (Full List)

Video Understanding

• [Preprint] | CapRiCorn-1K: A Comprehensive Benchmark for Video Captioning and Subject Referential Consistency Across Temporal Scales
  Xinlong Chen, Jiafu Tang, Yue Ding, Yizhuo Jia, Bozhou Li, Bohan Zeng, Yang Shi, Shihao Li, Yiyan Ji, Qiang Liu, Weihong Lin, Yuanxing Zhang, Pengfei Wan, Liang Wang, Tieniu Tan

• [ECCV 2026] | DiaDem: Advancing Dialogue Descriptions in Audiovisual Video Captioning for Multimodal Large Language Models
  Xinlong Chen, Weihong Lin, Jingyun Hua, Linli Yao, Yue Ding, Bozhou Li, Bohan Zeng, Yang Shi, Qiang Liu, Yuanxing Zhang, Pengfei Wan, Liang Wang, Tieniu Tan

• [ICLR 2026] | AVoCaDO: An Audiovisual Video Captioner Driven by Temporal Orchestration  
  Xinlong Chen, Yue Ding, Weihong Lin, Jingyun Hua, Linli Yao, Yang Shi, Bozhou Li, Yuanxing Zhang, Qiang Liu, Pengfei Wan, Liang Wang, Tieniu Tan

• [ICLR 2026] | VidBridge-R1: Bridging QA and Captioning for RL-based Video Understanding Models with Intermediate Proxy Tasks
  Xinlong Chen, Yuanxing Zhang, Yushuo Guan, Weihong Lin, Zekun Wang, Bohan Zeng, Yang Shi, Sihan Yang, Qiang Liu, Pengfei Wan, Liang Wang, Tieniu Tan

• [Findings of ACL 2025] | VidCapBench: A Comprehensive Benchmark of Video Captioning for Controllable Text-to-Video Generation
  Xinlong Chen, Yuanxing Zhang, Chongling Rao, Yushuo Guan, Jiaheng Liu, Fuzheng Zhang, Chengru Song, Qiang Liu, Di Zhang, Tieniu Tan

Hallucination Mitigation

• [EMNLP 2025] | Attention-guided Self-reflection for Zero-shot Hallucination Detection in Large Language Models
  Qiang Liu, Xinlong Chen, Yue Ding, Bowen Song, Weiqiang Wang, Shu Wu, Liang Wang

• [Findings of ACL 2025] | Mixture of Decoding: An Attention-Inspired Adaptive Decoding Strategy to Mitigate Hallucinations in Large Vision-Language Models
  Xinlong Chen, Yuanxing Zhang, Qiang Liu, Junfei Wu, Fuzheng Zhang, Tieniu Tan

📖 Education

• 2025.09 - 2030.06 (expected), Ph.D. Student in AI, New Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences
  • Supervisor: Prof. Tieniu Tan and Prof. Qiang Liu
• 2021.09 - 2025.06, B.Eng. in AI, School of Artificial Intelligence and Automation, Huazhong University of Science and Technology
  • Rank: 1 / 100 | Average Grade: 93.67 / 100
  • National Scholarship (2022, 2023, 2024)
  • Finalist in the Mathematical Contest in Modeling (Top 1%), serving as Team Leader

💻 Internships

• 2024.11 - Present, Kling Team, Kuaishou Technology
  • Mentor: Yuanxing Zhang and Weihong Lin
  • Focus: Multimodal understanding

Last updated: June 29, 2026