GeezerVison

Hi! I’m currently a researcher at Shanghai AI Lab mentored by Dr. Peng Gao. Previously I was a MSc student at National University of Singapore, and I became extreme passionate about AI since Sep. 2023. And I was luckily advised by Prof. Alan L. Yuille at CCVL@Johns Hopkins University. Previously, I also spent a wonderful time with Prof. Bharadwaj Veeravalli, Prof. Roger Zimmermann@NUS. Prior to that, I received my BSc degree in Physics, focusing on Nonlinear Dynamics & Chaos Theory and Bio-Physics.
My current research interests lie in Reasoning LLMs, Reinforcement learning, Multimodal learning, spanning video, image, action, audio, planning, etc., with a broader focus on Diffusion Models and Physics-Informed learning; Additionally, I am also keen on exploring why these models work and how to make them more interpretable and robust.

News

• [Mar. 2025] We release Lex-Art, a visual text generation framework 🎨.
• [Mar. 2025] We release FLASH, Few-shot Learning to Animate and Steer Humans 🎬.
• [Jan. 2025] First to reproduce TinyZero with report. Find my fork: .
• [Jan. 2025] One paper is accepted by NAACL 2025 Findings 🎉!
• [Jan. 2025] One paper is accepted by ICLR 2025 Poster 🎉!
• [Jan. 2025] One paper is accepted by IEEE ISBI 2025 🎉!
• [Jan. 2025] We release SusGen-GPT, LLMs for report generation and finance NLP 📈.
• [Dec. 2024] We release ScaleMAI, iterative system to scale up Medical AI 🏥.
• [Dec. 2024] We release MuMu-LLaMA for multi-modal music Understanding and Gen 🎸.
• [Dec. 2024] We release TextoMorph, text-driven tumor synthesis 🏥.
• [Nov. 2024] We release Label Critic, VLM pipeline to detect medical images data errors 🕵️.

Publications & Preprints

* Equal contribution, † Corresponding author

LeX-Art: Rethinking Text Generation via Scalable High-Quality Data Synthesis

Shitian Zhao*, Qilong Wu*, Xinyue Li*, Bo Zhang, Ming Li, Qi Qin, Dongyang Liu, Kaipeng Zhang, Hongsheng Li, Yu Qiao, Peng Gao, Bin Fu†, Zhen Li†
Preprint, 2025 | Paper | | Project Page | BibTeX

Learning to Animate Images from A Few Videos to Portray Delicate Human Actions

Haoxin Li, Yingchen Yu, Qilong Wu, Hanwang Zhang, Song Bai, Boyang Li
Preprint, 2025 | Paper | Project Page | BibTeX

Generalized Video Moment Retrieval

You Qin*, Qilong Wu*, Yicong Li†, Wei Ji†, Li Li, Pengcheng Cai, Lina Wei, Roger Zimmermann
Accepted by ICLR, 2025 | Paper | Poster | BibTeX

SusGen-GPT: A Data-Centric LLM for Financial NLP and Sustainability Report Generation

Qilong Wu†, Xiaoneng Xiang, Huang Hejia, Xuan Wang, Yeo Wei Jie, Ranjan Satapathy, Ricardo Shirota Filho, and Bharadwaj Veeravalli
Accepted by NAACL Findings, 2025 | Paper | | HuggingFace | Video Demo | BibTeX

MuMu-LLaMA: Multi-modal Music Understanding and Generation via Large Language Models

Shansong Liu*†, Atin Sakkeer Hussain*, Qilong Wu*, Sun Chenshuo, Ying Shan
Preprint, Under Review, 2025 | Paper | | Video | Website | BibTeX

Text-Driven Tumor Synthesis

Xinran Li, Yi Shuai, Chen Liu, Qi Chen, Qilong Wu, Pengfei Guo, Dong Yang, Can Zhao, Pedro R. A. S. Bassi, Daguang Xu, Kang Wang, Yang Yang, Alan Yuille, Zongwei Zhou†
Preprint, 2025 | Paper | | BibTeX

Label Critic: Design Data Before Models

Pedro R. A. S. Bassi, Qilong Wu, Wenxuan Li, Sergio Decherchi, Andrea Cavalli, Alan Yuille, Zongwei Zhou†
Accepted by IEEE ISBI, 2025 | Paper | | BibTeX

ScaleMAI: Accelerating the Development of Trusted Datasets and AI Models

Wenxuan Li, Pedro R. A. S. Bassi, Tianyu Lin, Yu-Cheng Chou, Xinze Zhou, Yucheng Tang, Fabian Isensee, Kang Wang, Qi Chen, Xiaowei Xu, Xiaoxi Chen, Lizhou Wu, Qilong Wu, Yannick Kirchhoff, Maximilian Rokuss, Saikat Roy, Yuxuan Zhao, Dexin Yu, Kai Ding, Constantin Ulrich, Klaus Maier-Hein, Yang Yang, Alan L. Yuille, Zongwei Zhou†
Preprint, 2025 | Paper | | BibTeX

Academic Services

• Reviewer of International Conference on Machine Learning (ICML), 2025.
• Reviewer of International Conference on Learning Representations (ICLR), 2025.
• Reviewer of International Conference on Artificial Intelligence and Statistics (AISTATS), 2025.
• Reviewer of Conference on Neural Information Processing Systems (NIPS), 2024 & 2025.
• Reviewer of ACM International Conference on Multimedia (ACM MM), 2024.

Miscellaneous

• President of the Student Union in Physics Department, 2020-2021.
• Prepared to be a professional mobile game player in SanGuoSha Mobile in my Bachelor period but failed, finally ranked 243th Nationally over 10,000,000 players, 2021-2022.
• Accomplished the First Peak of Mount Siguniang (5,038m) [news] and the Main peak of Que’er Mountain (6,168m) [news], 2019.
• Coded in Quick-Basic45 language for two years and won the Champion in the Java/C++/Basic Programing Competition in Beijing Shunyi District over more than a thousand participants when I was 12 in elementary school, 2012. [code]

GitHub Stats