I’m a CS Ph.D. student @University of Southern California, advised by Prof. Jieyu Zhao. Before that, I was a M.Eng student at Graduated School of Creative Science and Engineering @Waseda University (早稲田大学), Tokyo, supervised by Prof. Masayuki Goto (Japanese only). I also spent my time as a research assistant @University of Maryland, advised by Prof.Tianyi Zhou, and University of Tokyo (東京大学), advised by Prof.Irene Li. I also work closely with Jieyu Zhang, who focuses on interactive and data-centric AI/ML.
Research Interests: My research interest lies in the realm of natural language processing and synthetic data. Specifically, I’m trying to answer the following questions:
- How can we comprehensively evaluate an LLM/VLM in different domains?
- How can we extend ability of LLM/VLM with minimal costs?
- How can we let LLM/VLMs collaborate safely, efficiently, and effectively to solve real-world problems?
📢 News
[12/10/2024] Two new preprints are released!
[05/31/2024] A new preprint is released. Check Adaptive In-conversation Team Building for Language Model Agents for more details!
[04/10/2024] I will join CS@USC as a PhD student this fall!
📝 Selected Publications
(* denotes equal contribution)
Preprint
- Template Matters: Understanding the Role of Instruction Templates in Multimodal Language Model Evaluation and Training
Shijian Wang*, Linxin Song*, Jieyu Zhang, Ryotaro Shimizu, Ao Luo, Li Yao, Cunjian Chen, Julian McAuley, Haiqian Wu - ProVision: Programmatically Scaling Vision-centric Instruction Data for Multimodal Language Models
Jieyu Zhang, Le Xue, Linxin Song, Jun Wang, Weikai Huang, Manli Shu, An Yan, Zixian Ma, Juan Carlos Niebles, silvio savarese, Caiming Xiong, Zeyuan Chen, Ranjay Krishna, Ran Xu.
Posted by: VentureBeat | MarkTechPost - Rethinking LLM-based Preference Evaluation
Zhengyu Hu, Linxin Song, Jieyu Zhang, Zheyuan Xiao, Jingang Wang, Zhenyu Chen, Hui Xiong - Adaptive In-conversation Team Building for Language Model Agents
Linxin Song*, Jiale Liu*, Jieyu Zhang, Shaokun Zhang, Ao Luo, Shijian Wang, Qingyun Wu, Chi Wang
Peer-reviewed
- Offline Training of Language Model Agents with Functions as Learnable Weights
Shaokun Zhang*, Jieyu Zhang*, Jiale Liu, Linxin Song, Chi Wang, Ranjay Krishna, Qingyun Wu
ICML 2024. - Better Explain Transformers by Illuminating Important Information
Linxin Song, Yan Cui, Ao Luo, Freddy Lecue, Irene Li
EACL 2024 (findings). - NLPBench: Evaluating Large Language Models on Solving NLP Problems
Linxin Song, Jieyu Zhang, Lechao Cheng, Pengyuan Zhou, Tianyi Zhou, Irene Li
ITIF @ NeurIPS 2023. - Leveraging Instance Features for Label Aggregation in Programmatic Weak Supervision
Jieyu Zhang*, Linxin Song*, Alexander Ratner
AISTATS 2023. - Adaptive Ranking-based Sample Selection for Weakly Supervised Class-imbalanced Text Classification
Linxin Song, Jieyu Zhang, Tianxiang Yang, Masayuki Goto
EMNLP 2022 (findings).
🧑🏫 Teaching
- (TA) DSCI-250: Introduction to Data Science, 2024 Fall
- (TA) DSCI-566: Deep Learning and its Applications, 2025 Spring
👨💻 Internships (Before PhD)
- University of Tokyo - Research Assistant
2023.02-2024.02
Advised by Irene Li - University of Maryland, College Park - Research Assistant
2022.07-2023.10
Advised by Tianyi Zhou - University of Washington - Research Intern
2022.03-2022.11
Advised by Alex Ratner and Jieyu Zhang
🏅 Professional Services
- Maintainer of AG2 (Autogen).
- Reviewer: WACV 2023, ECML-PKDD 2023, NeurIPS 2023, DMLR 2023, ICLR 2024, AISTATS 2024, ACL 2024 (ARR Feb), NeurIPS 2024, EMNLP 2024 (ARR June), ICLR 2025, KDD 2025