Xi Weng

PhD student

School of Computing, National University of Singapore

Email: xi.w@u.nus.edu, xi.winci@gmail.com

[Publication] |[Education] | [Awards and Honors] | [Source Code] | [Academic Service]

My name is Xi Weng, and you can call me easily by Winci. I am currently a second-year PhD student at computer science of NUS, under the supervision of Prof. Jin-Song Dong. Prior to this, I earned both the Bachelor's and Master's degree from the School of Artificial Intelligence at Beihang University, where I was supervised by Prof. Lei Huang. My primary research interests lie in self-supervised learning, multimodal learning and LLM reasoning.

NEWS April 2026: One paper is accepted by ICME 2026.

NEWS May 2025: One paper is accepted by ICML 2025.

NEWS June 2024: One paper is accepted by TPAMI.

NEWS Jan 2024: One paper is accepted by ICLR 2024.

NEWS Sep 2022: One paper is accepted by NeurIPS 2022 (spotlight).

Publications

Self-supervised learning:

Clustering Properties of Self-Supervised Learning

Xi Weng, Jianing An, Xudong Ma, Binhang Qi, Jie Luo, Xi Yang, Jin Song Dong, Lei Huang

International Conference on Machine Learning (ICML), 2025

[Paper]

[Code]

Modulate Your Spectrum in Self-Supervised Learning

Xi Weng, Yunhao Ni, Tengwei Song, Jie Luo, Rao Muhammad Anwer, Salman Khan, Fahad Khan, Lei Huang

International Conference on Learning Representations (ICLR), 2024

[Paper]

[Code]

Understanding Whitening Loss in Self-supervised Learning

Lei Huang, Yunhao Ni, Xi Weng, Rao Muhammad Anwer, Salman Khan, Ming-Hsuan Yang, Fahad Shahbaz Khan

Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2024

[Paper]

[Code]

An Investigation into Whitening Loss for Self-supervised Learning

Xi Weng, Lei Huang, Lei Zhao, Rao Muhammad Anwer, Salman Khan, Fahad Shahbaz Khan

Advances in Neural Information Processing Systems (NeurIPS), 2022 (Spotlight)

[Paper]

[Code]

Multimodal models:

TennisExpert: Towards Expert-Level Analytical Sports Video Understanding

Zhaoyu Liu, Xi Weng, Lianyu Hu, Zhe Hou, Kan Jiang, Jin Song Dong, Yang Liu

arXiv:2603.13397

[Paper]

[Code]

TinyLLaVA-Video: Towards Smaller LMMs for Video Understanding with Group Resampler

Xingjian Zhang, Xi Weng, Yihao Yue, Zhaoxin Fan, Wenjun Wu, Lei Huang

IEEE International Conference on Multimedia and Expo (ICME), 2026

[Paper]

[Code]

TinyLLaVA Factory: A Modularized Codebase for Small-scale Large Multimodal Models

Junlong Jia, Ying Hu, Xi Weng, Yiming Shi, Miao Li, Xingjian Zhang, Baichuan Zhou, Ziyu Liu, Jie Luo, Lei Huang, Ji Wu

arXiv:2405.11788

(co-first author)

[Paper]

[Code, 900+stars]

TinyLLaVA: A Framework of Small-scale Large Multimodal Models

Baichuan Zhou, Ying Hu, Xi Weng, Junlong Jia, Jie Luo, Xien Liu, Ji Wu, Lei Huang

arXiv:2402.14289

[Paper]

[Code]

Education

Jan. 2025 - Currently
- Ph.D. in Computer Science, National University of Singapore
- Advisor: Prof. Jin-Song Dong

Sep. 2022 - Dec. 2024
- M.Sc. in Artificial Intelligence, Beihang University
- Advisor: Prof. Lei Huang

Sep. 2018 - Jun. 2022
- B.Eng. in Artificial Intelligence, Beihang University
- Advisor: Prof. Lei Huang

Awards and Honors

Excellent Graduation Thesis of Beihang University, 2024.
Outstanding Graduate of Beihang University, 2024.
China National Scholarship, 2023.
Excellent Academic Innovation Achievement Award, 2023.

Source Code

ReSA: This project is an official implementation of ReSA. (2501.18452).
INTL: This project is an official implementation of INTL. (2305.16789).
CW-RGP: This project is an official implementation of CW-RGP. (2210.03586).

Academic Service

I have served as a reviewer for ICLR, ICML, and NeurIPS (2025, 2026), ECCV 2026.

Miscellaneous

I also have great interest in fitness, singing and guitar.

Main Co-authors: [Jin-Song Dong] | [Lei Huang] | [Fahad Shahbaz Khan]