Lin Long ( 龍麟)

kylinllong AT gmail DOT com

Hi! I am a second-year master student in Computer Science at Zhejiang University, advised by Junbo Zhao. Previously, I recieved my B.E. degree in Software Engineering at Zhejiang University. I am currently devoted to the field of multimodal and embodied intelligence. My aspiration is to uncover the secrets of human cognition, and develop AI systems that learn and think more like humans. Outside of academia, I am a big fan of art, design, and all kinds of competitive sports. I am also a sneaker head! 😋
Big shout out to my parents for always supporting me and being the greatest mom and dad of all time. 🩵

🔬 Research Experience

Inclusion AI, Ant Group

Research intern. Working on unified multimodal models.

Advisors: Junbo "Jake" Zhao

2026-Present

University of Wisconsin-Madison

Visiting scholar at the Department of Computer Sciences.

Advisors: Sharon Li

2025-2026

ByteDance Seed

Research intern. Working on multimodal agent.

Advisors: Yuan Lin, Hang Li

2024-2025

🎓 Education

Zhejiang University

M.S. in Computer Science, College of Computer Science and Technology.

Advisors: Junbo "Jake" Zhao, Haobo Wang

2024-2026

Zhejiang University

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

Advisors: Junbo "Jake" Zhao, Haobo Wang

2020-2024

🔥 What's new?

2025.01

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 Research AI-Lab as a research intern! Looking forward to building something cool on multimodal agents with the team! 🤩

2024.11

We release TableGPT2, an open-source table expert that excels in table-centric tasks while maintaining strong general language and coding abilities! Try out our brand new 7B model on 🤗HuggingFace!

2024.05

One paper accpeted to ACL 2024 Findings! (Which also marks my personal milestone in the field of NLP! Let's keep going! 🤩)

2024.02

My FIRST paper as the FIRST author, Positive-Unlabeled Learning by Latent Group-Aware Meta Disambiguation, was accepted by CVPR 2024! That's just the beginning!

2024.02

A paper that I have contributed to, Property Existence Inference against Generative Models, was accepted by USENIX Security '24 Fall.

📝 Publications & Preprints

(* denotes equal contribution)

ICLR 2026

Understanding Language Prior of LVLMs by Contrasting Chain-of-Embedding
Lin Long*, Changdae Oh*, Seongheon Park, Sharon Li

ICLR 2026

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

arXiv

TableGPT2: A Large Multimodal Model with Tabular Data Integration
TableGPT Team (as directional lead of table encoder)

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

ACL 2024 Findings

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

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

USENIX Security '24 Fall

Property Existence Inference against Generative Models
Lijin Wang, Jingjing Wang, Jie Wan, Lin Long, Ziqi Yang, Zhan Qin