Yuxuan FAN

About

I am a Ph.D. student at the College of Computing and Data Science, Nanyang Technological University, Singapore, where I am honored to be supervised by Prof. JaeHong Yoon.

I received my M.Phil. in Artificial Intelligence from the AI Thrust, Information Hub, HKUST (Guangzhou) in 2026, supervised by Prof. Hao LIU, and my bachelor's degree from the School of Advanced Engineering, USTB in 2024. I also studied Economics at the National School of Development, Peking University.

I am passionate about contributing to large-scale, impactful open-source projects.

News

Aug 2026 Four papers were accepted by EMNLP'26, three by the Main Conference and one by Findings!
Jun 2026 One paper was accepted by ECCV'26!
Apr 2026 1 paper was selected as a Highlight paper of CVPR'26! Thanks for my co-author Jing Hao!
Feb 2026 Two papers were accepted by CVPR'26!
Jan 2026 One paper was accepted by ICLR'26!
Nov 2025 Four papers were accepted by AAAI'26!
Nov 2025 One paper was accepted by Expert Systems with Applications (JCR Q1, IF: 7.5)!
Sep 2025 Two papers were accepted by NeurIPS'25!
Jun 2025 One paper was accepted by ACM MM'25!
May 2025 One paper was accepted by IJCAI'25!

Selected Publications

* Equal contribution. See also Google Scholar.

PhoenixNest-Video: Evidence-Grounded Multimodal Agent Framework for Automated Video Interview Assessment
Yuxuan Fan, Miaojun Huang, Haimei Zhang, Jingshen Wu, Hao Liu
EMNLP 2026
MuseBench: Benchmarking Intent-Level Audiovisual Arts Understanding in MLLMs
Yuxuan Fan, Gyusik Seo, Jing Hao, Jaemin Cho, Mohit Bansal, Jaehong Yoon
Preprint
OralGPT-Plus: Learning to Use Visual Tools via Reinforcement Learning for Panoramic X-ray Analysis
Yuxuan Fan*, Jing Hao*, Hong Chen, Jiahao Bao, Yihua Shao, Yuci Liang, Kuo Feng Hung, Hao Tang
CVPR 2026 Highlight Code
ACE: Attribution-Controlled Knowledge Editing for Multi-hop Factual Recall
Jiayu Yang*, Yuxuan Fan*, Songning Lai, Shengen Wu, Jiaqi Tang, Chun Kang, Zhijiang Guo, Yutao Yue
ICLR 2026 Code
AirCopBench: A Benchmark for Multi-drone Collaborative Embodied Perception and Reasoning
Jirong Zha*, Yuxuan Fan*, Tianyu Zhang, Geng Chen, Yingfeng Chen, Chen Gao, Xinlei Chen
AAAI 2026 Code
HALLUCINATION AT A GLANCE: Controlled Visual Editing and Fine-Grained Multimodal Learning
Tianyi Bai*, Yuxuan Fan*, Jiantao Qiu, Fupeng Sun, Jiayi Song, Junlin Han, Zichen Liu, Conghui He, Wentao Zhang, Binhang Yuan
NeurIPS 2025 Code
Towards Better Dental AI: A Multimodal Benchmark and Instruction Dataset for Panoramic X-ray Analysis
Jing Hao*, Yuxuan Fan*, Yanpeng Sun, Kaixin Guo, Lizhuo Lin, Jinrong Yang, Qi Yong H. Ai, Lun M. Wong, Hao Tang, Kuo Feng Hung
NeurIPS 2025 Code
How to Enable LLM with 3D Capacity? A Survey of Spatial Reasoning in LLM
Yuxuan Fan*, Jirong Zha*, Xiao Yang, Chen Gao, Xinlei Chen
IJCAI 2025
NestedKV: Nested Memory Routing for Long-Context KV Cache Compression
Hong Chen, Xiang Liu, Yubo Gao, Yuxuan Fan, Bo Wang, Yuanlin Chu, Yuanguo Lin, Xuming Hu
EMNLP 2026
Decomposing Visual Histories with Vision-Language Agents: Hierarchical Temporal Guidance for Compositional Image Generation
Lujundong Li, Mingxu Zhang, Songning Lai, Jiayu Yang, Yuxuan Fan, Ziwei Xie, Feng Liu, Changwang Zhang, Jun Wang, Dazhong Shen, Ying Sun
EMNLP 2026
Demystifying Hidden-State Recurrence: Switchable Latent Reasoning with On-Policy Reinforcement Learning
Jiayu Yang, Chao Chen, Shengen Wu, Yinhong Liu, Yuxuan Fan, Lujundong Li, Songning Lai, Chengwei Qin, Zhijiang Guo
EMNLP 2026 Findings
DIMM: Decoupled Multi-hierarchy Kalman Filter via Reinforcement Learning
Jirong Zha, Yuxuan Fan, Kai Li, Han Li, Chen Gao, Xinlei Chen
AAAI 2026 Code

Experiences

Apr. 2026 – Jun. 2026

Tongyi Wanxiang, Alibaba Group

Research Intern

Participated in the pre-training of image generation models for Wan 3.0.

Oct. 2025 – Mar. 2026

Inclusion AI, Ant Group

Research Intern

Enhancing the visual reasoning ability of the Ming-Flash-Omni model. Participated in the post-training of Ming-flash-omni-2.0.

Jun. 2025 – Sep. 2025

CV Lab, Amap, Alibaba

Research Intern

Computer vision research.

Education

Aug. 2026 – 2030 (expected)

Ph.D. in Computer Science

Nanyang Technological University, Singapore

College of Computing and Data Science (CCDS). Advised by Prof. JaeHong Yoon.

Sep. 2024 – Jun. 2026

M.Phil. in Artificial Intelligence

HKUST(GZ), Guangzhou, China

AI Thrust, Information Hub.

Sep. 2021 – Jun. 2024

Exchange Student in Economics

Peking University, Beijing, China

National School of Development.

Sep. 2020 – Jun. 2024

B.S. in Robotics and Mechanical Engineering

USTB, Beijing, China

School of Advanced Engineering.

Professional Services

Conference Reviewer

  • CVPR
  • AAAI
  • KDD
  • IV
  • ITSC
  • ICIP

Journal Reviewer

  • International Journal of Computer Vision (IJCV)
  • ACM Transactions on Intelligent Systems and Technology (TIST)
  • Knowledge-Based Systems (KBS)
  • IEEE Journal of Biomedical and Health Informatics (JBHI)

Hobbies

I believe the meaning of life lies in experiencing a wealth of things, and in always being on the journey.

I am a big fan of Chelsea and the Oklahoma City Thunder.

I am a starry sky and astronomy enthusiast, and I love looking up at the stars at night. I am also really into science fiction.

My favorite novels are The Three-Body Problem and And Quiet Flows the Don.