I am a first year Ph.D. student at Language Computing and Machine Learning Group (LANCO), Institute of Computational Linguistics (State Key Laboratory for Multimedia Information Processing) (icl), School of Computer Science, Peking University without entrance examination, supervised by Prof. Xu Sun. Before that, I got a B.E. degree from School of Computer Science and Technology, Shandong University, with a solid foundation in mathematics, strong learning ability, excellent competition results and rich research experience, advised by Prof. Xuemeng Song.

My research interests include NLP, LLM, quantitative finance and multimodal learning.

I am looking for research collaborations in the field of Multimodal NLP and Video Understanding, please feel free to contact me at Email kunouyang10ATgmailDOTcom.

🔥 News

  • 2025.05  🎉🎉 Two papers got accepted by ACL 2025.
  • 2024.12  🎉🎉 One paper got accepted by IEEE TMM.
  • 2023.05  🎉🎉 One paper got accepted by ACL 2023.

📝 Preprints

VIDEOREASONBENCH: Can MLLMs Perform Vision-Centric Complex Video Reasoning?

Yuanxin Liu, Kun Ouyang, Haoning Wu, Yi Liu, Lin Sui, Xinhao Li, Yan Zhong, Y. Charles, Xinyu Zhou, Xu Sun

SpaceR: Reinforcing MLLMs in Video Spatial Reasoning [Project]

Kun Ouyang, Yuanxin Liu, Haoning Wu, Yi Liu, Hao Zhou, Jie Zhou, Fandong Meng, Xu Sun

WONDER: Weight-Adaptive Optimization with Data Selection for Multimodal Reasoning

Yi Liu, Shicheng Li, Yuanxin Liu, Kun Ouyang, Hao Zhou, Fandong Meng, Jie Zhou, Xu Sun

TEMPO: Temporal Preference Optimization of Video LLMs via Difficulty Scheduling and Pre-SFT Alignment

Shicheng Li, Lei Li, Kun Ouyang, Shuhuai Ren, Yuanxin Liu, Yuanxing Zhang, Fuzheng Zhang, Lingpeng Kong, Qi Liu, Xu Sun

TimeChat-Online: 80% Visual Tokens are Naturally Redundant in Streaming Videos

Linli Yao, Yicheng Li, Yuancheng Wei, Lei Li, Shuhuai Ren, Yuanxin Liu, Kun Ouyang, Lean Wang, Shicheng Li, Sida Li, Lingpeng Kong, Qi Liu, Yuanxing Zhang, Xu Sun

📝 Publications

PunchBench: Benchmarking MLLMs in Multimodal Punchline Comprehension ACL 2025

Kun Ouyang, Yuanxin Liu, Shicheng Li, Yi Liu, Hao Zhou, Fandong Meng, Jie Zhou, Xu Sun

Generative Frame Sampler for Long Video Understanding ACL 2025 (findings)

Linli Yao, Haoning Wu, Kun Ouyang, Yuanxing Zhang, Caiming Xiong, Bei Chen, Xu Sun, Junnan Li

Sentiment-enhanced Graph-based Sarcasm Explanation in Dialogue IEEE TMM

Kun Ouyang, Liqiang Jing, Xuemeng Song, Meng Liu, Yupeng Hu, Liqiang Nie

Multi-source semantic graph-based multimodal sarcasm explanation generation ACL 2023

Liqiang Jing, Xuemeng Song, Kun Ouyang, Mengzhao Jia, Liqiang Nie.

📝 Technical report

Kimi-vl technical report

✨ Reviewer

ACM MM 2025; ICLR 2025

📖 Educations

  • 2024.09 - 2029.06 (expected), School of Computer Science, Peking University.
  • 2020.09 - 2024.06, Artificial Intelligence, School of Computer Science and Technology, Shandong University.

💻 Internships

  • 2024-2025, Tencent AI lab.

  • 2023.10 - 2024.02, Mizuho Securities Co., Ltd.