Lin Long

Lin Long 龙麟

CV Github G-Scholar

kylin0long AT gmail DOT com

Hi! I am a visiting scholar at the University of Wisconsin-Madison, supervised by Sharon Li. I also work closely with Boyi Li. Previously, I received my B.E. degree in Software Engineering at Zhejiang University, co-advised by Junbo Zhao and Haobo Wang.
I am interested in multimodal learning and embodied intelligence. My aspiration is to extend the boundaries of intelligence by developing autonomous multimodal agents that, grounded in perception and action, can continually learn, integrate, and generate knowledge from real-world experience.
Outside of academia, I am a big fan of all kinds of art and competitive sports.
Big shout out to my parents for always supporting me and being the greatest mom and dad of all time. 🩵

University of Wisconsin-Madison Logo

University of Wisconsin-Madison

Visiting scholar, Department of Computer Sciences.

Advisor: Sharon Li

2025-Present

ByteDance Seed Logo

ByteDance Seed

Research intern.

Advisors: Hang Li, Yuan Lin

2024-2025

Zhejiang University Logo

Zhejiang University

B.E. in Software Engineering, College of Computer Science and Technology.

Advisors: Junbo "Jake" Zhao, Haobo Wang

2020-2024

🔥 What's new?

2025.06
I am visiting the University of Wisconsin-Madison! Super honored to be hosted by Prof. Sharon Li. Excited to work with a group of amazing people here! 🤩
2025.01
One paper accepted to ICLR 2025, which delves into table-text multimodal learning, one of the core parts of TableGPT2! Stay tuned for the upcoming camera-ready paper and source code!
2024.12
I am joining the ByteDance Seed as a research intern! Looking forward to building something cool on multimodal agents with the team! 🤩

🗒️ Preprints

(* denotes equal contribution)

Research Areas:LLMMMWSLCVMLSD
ICLR 2026, Under Review
Understanding Language Prior of LVLMs by Contrasting Chain-of-Embedding
Lin Long*, Changdae Oh*, Seongheon Park, Sharon Li
MM
ICLR 2026, Under Review
Seeing, Listening, Remembering, and Reasoning: A Multimodal Agent with Long-Term Memory
Lin Long*, Yichen He*, Wentao Ye, Yiyuan Pan, Yuan Lin, Hang Li, Junbo Zhao, Wei Li
MM
arXiv
TableGPT2: A Large Multimodal Model with Tabular Data Integration
TableGPT Team (as directional lead of table encoder)
LLMMM

📝 Publications

ICLR 2025
Bridging the Semantic Gap Between Text and Table: A Case Study on NL2SQL
Lin Long*, Xijun Gu*, Xinjie Sun, Wentao Ye, Haobo Wang, Sai Wu, Gang Chen, Junbo Zhao
LLMMM
Findings of ACL 2024
On LLMs-Driven Synthetic Data Generation, Curation and Evaluation: A Survey
Lin Long, Rui Wang, Ruixuan Xiao, Junbo Zhao, Xiao Ding, Gang Chen, Haobo Wang
LLMSDWSL
CVPR 2024
Positive-Unlabeled Learning by Latent Group-Aware Meta Disambiguation
Lin Long*, Haobo Wang*, Zhijie Jiang, Lei Feng, Chang Yao, Gang Chen, Junbo Zhao
CVWSLML
USENIX '24 Fall
Property Existence Inference against Generative Models
Lijin Wang, Jingjing Wang, Jie Wan, Lin Long, Ziqi Yang, Zhan Qin
ML