profile photo

Shulin Tian

shulin002 [at] ntu.edu.sg

   

I am a PhD student at Nanyang Technological University (NTU), Singapore, supervised by Prof. Ziwei Liu and Dr. Hongyuan Zhu.

Previously, I obtained my Bachelor's Degree from NTU, and I spent a wonderful time working with Prof. Ranjay Krishna at University of Washington on vision-language model reasoning, and Prof. Bihan Wen at NTU on low-light image enhancement.


News

  • [06/2025] Evaluation Agent was selected for an oral presentation at ACL 2025. Congrats to all coauthors!
  • [06/2025] We release the Ego-R1: Chain-of-Tool-Thought for Ultra-Long Egocentric Video Reasoning. Code and data can be found here.
  • [05/2025] MMInA leaderboard is now live at MMInA Proj Page.
  • [05/2025] Two papers are accepted to ACL 2025 (one main and one findings).
  • [03/2025] I am acknowledged as an outstanding reviewer for ICLR 2025 [SCOPE Workshop].
  • [01/2025] Our paper "AHA: A Vision-Language-Model for Detecting and Reasoning Over Failures in Robotic Manipulation" is accepted to ICLR 2025.
  • [12/2024] Our paper "Evaluation Agent: Efficient and Promptable Evaluation Framework for Visual Generative Models" is released.
  • [08/2024] Starting my PhD at MMLab@NTU.
  • [04/2024] Our paper "MMInA: Benchmarking Multihop Multimodal Internet Agents" is released.
  • [06/2023] Our paper "Enhancing Low-Light Images Using Infrared-Encoded Images" is accepted to ICIP 2023.

Publications

(* equal contributions)

Ego-R1: Chain-of-Tool-Thought for Ultra-Long Egocentric Video Reasoning
Shulin Tian*, Ruiqi Wang*, Hongming Guo, Penghao Wu, Yuhao Dong, Xiuying Wang, Jingkang Yang, Hao Zhang, Hongyuan Zhu, Ziwei Liu

arXiv, 2025 
Paper  /  Project Page  /  Code  /  Data

Area: Agentic tool-use, long video reasoning, egocentric

MMInA: Benchmarking Multihop Multimodal Internet Agents
Shulin Tian*, Ziniu Zhang*, Liangyu Chen*, Ziwei Liu

ACL Findings, 2025 
Paper  /  Project Page  /  Code  /  Data

Area: Multimodal agent benchmark on long-horizon reasoning

Evaluation Agent: Efficient and Promptable Evaluation Framework for Visual Generative Models
Fan Zhang*, Shulin Tian*, Ziqi Huang*, Yu Qiaoโ€ , Ziwei Liuโ€ 

ACL Main, 2025 (Oral) 
Paper  /  Project Page  /  Code

Area: Agent, GenAI

AHA: A Vision-Language-Model for Detecting and Reasoning Over Failures in Robotic Manipulation
Jiafei Duan, Wilbert Pumacay, Nishanth Kumar, Yi Ru Wang, Shulin Tian, Wentao Yuan, Ranjay Krishna, Dieter Fox, Ajay Mandlekar*, Yijie Guo*,

ICLR, 2025 
Paper  /  Project Page

Area: Robotics, VLM

Enhancing Low-light Images Using Infrared Encoded Images
Shulin Tian*, Yufei Wang*, Renjie Wan, Wenhan Yang, Alex C. Kot, Bihan Wen

ICIP, 2023 
Paper  /  Code  /  Data

Area: Low-light image enhancement


Education


Nanyang Technological University

PhD in Computer Science
Aug. 2024 - Present

Nanyang Technological University

BEng in Electrical & Electronic Engineering (Highest Distinction)
Aug. 2020 - May 2024

Honors & Awards


Miscellanea

When it comes to music, I do:

When it comes to sports, I always try new things and do:

  • ๐Ÿคฟ Diving: PADI Certificated Open Water (2022) & Advanced Open Water Diver (2024)
  • ๐Ÿงท Others: badminton, hiking...


Last updated: Dec. 2024 Thanks Jon Barron and Jiayuan Mao for their awesome website templates!