Shulin Tian

Ph.D. Student · MMLab@NTU

I study how multimodal agents turn visual experience into grounded reasoning and purposeful action. I build systems that understand long-horizon visual experiences, use tools to seek and verify evidence, and adapt across physical and digital environments.

Scholar GitHub X LinkedIn Email

About

Shulin Tian is a Ph.D. student in Computer Science at Nanyang Technological University, advised by Prof. Ziwei Liu and Dr. Hongyuan Zhu. Her research centers on multimodal agents and visual reasoning, with an emphasis on long-horizon multimodal understanding and tool-augmented reasoning. Previously, she worked with Prof. Ranjay Krishna at the University of Washington on vision-language reasoning, and with Prof. Bihan Wen at NTU on computational imaging. She received her B.Eng. in Electrical and Electronic Engineering with Honours (Highest Distinction) from NTU and is supported by the A*STAR Computing and Information Science Scholarship.

News

  • 08/2026 V-Rubrics is accepted to EMNLP 2026 Main; Demo-ICL is accepted to Findings.
  • 08/2026 We release Open Evaluation Agent including EA-CoT-10K and EA-3B for open-source, promptable evaluation of visual generative models.
  • 06/2026 We release S-Agent, a spatial tool-use agent for continuous multi-view image and video reasoning.
  • 06/2026 HippoCamp and PerceptionComp are accepted to ECCV 2026. Congrats to all coauthors!
  • 05/2026 I am recognized as an outstanding reviewer for CVPR 2026. News link: here.
  • 05/2026 Ego-R1 is accepted to TPAMI. Congrats to all coauthors!
  • 04/2026 We release SimpleStream, a simple baseline for streaming video understanding.
  • 04/2026 We release HippoCamp and FileGram, two papers related to the file-system agentic memory.
  • 03/2026 We release Insight-V++, towards advanced long-chain visual reasoning with multimodal large language models.
  • 02/2026 We release Demo-ICL, in-context learning for procedural video knowledge acquisition.
  • 06/2025 Evaluation Agent was selected for an oral presentation and SAC Highlight Award (43/8350) 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, † project lead, corresponding author)

V-Rubrics example showing a visual question and its fine-grained visual grounding and reasoning rubrics
V-Rubrics: Visual Faithfulness via Rubric-Based Reinforcement Learning
Shulin Tian*, Minglun Li*, Yuhao Dong*†, Hao Ding*, Jiarui Yao, Haiwen Diao, Jingkang Yang, Hongyuan Zhu, Ziwei Liu

EMNLP 2026 (Main) 
Paper  /  Project Page  /  Code  /  Data

Area: Visual reasoning, RL, rubrics

Open Evaluation Agent: Efficient and Promptable Evaluation of Visual Generative Models - Research paper illustration
Open Evaluation Agent: Efficient and Promptable Evaluation of Visual Generative Models
Shulin Tian, Ziqi Huang, Fan Zhang, Hongyuan Zhu, Yu Qiao, Ziwei Liu

arXiv, 2026 
Paper  /  Code  /  Models & Data

Area: Visual model evaluation, autonomous agents, visual generation

S-Agent: Spatial Tool-Use Elicits Reasoning for Spatial Intelligence - Research paper illustration
S-Agent: Spatial Tool-Use Elicits Reasoning for Spatial Intelligence
Yalun Dai*, Hao Li*, Shulin Tian, Runmao Yao, Yuhao Dong, Fangzhou Hong, Zhaoxi Chen, Fangfu Liu, Baoliang Tian, Dingwen Zhang, Tao Wang, Kim-Hui Yap, Ziwei Liu

arXiv, 2026 
Paper  /  Project Page  /  Code

Area: Spatial intelligence, tool-use agents, spatial reasoning

Demo-ICL: In-Context Learning for Procedural Video Knowledge Acquisition - Research paper illustration
Demo-ICL: In-Context Learning for Procedural Video Knowledge Acquisition
Yuhao Dong*, Shulin Tian*, Shuai Liu, Shuangrui Ding, Yuhang Zang, Xiaoyi Dong, Yuhang Cao, Jiaqi Wang, Ziwei Liu

EMNLP 2026 (Findings) 
Paper  /  Code

Area: Video reasoning, in-context learning

HippoCamp: Benchmarking Contextual Agents on Personal Computers - Research paper illustration
HippoCamp: Benchmarking Contextual Agents on Personal Computers
Zhe Yang, Shulin Tian, Kairui Hu, Shuai Liu, Hoang-Nhat Nguyen, Yichi Zhang, Zujin Guo, Mengying Yu, Zinan Zhang, Jingkang Yang, Chen Change Loy, Ziwei Liu

ECCV 2026 
Paper  /  Project Page  /  Code  /  Data

Area: Contextual agents, personal AI assistants, multimodal memory

FileGram: Grounding Agent Personalization in File-System Behavioral Traces - Research paper illustration
FileGram: Grounding Agent Personalization in File-System Behavioral Traces
Shuai Liu, Shulin Tian, Kairui Hu, Yuhao Dong, Zhe Yang, Bo Li, Jingkang Yang, Chen Change Loy, Ziwei Liu

arXiv, 2026 
Paper  /  Project Page  /  Code  /  Data

Area: Agent personalization, file-system memory, behavioral traces

SimpleStream: A Simple Baseline for Streaming Video Understanding - Research paper illustration
SimpleStream: A Simple Baseline for Streaming Video Understanding
Yujiao Shen, Shulin Tian, Jingkang Yang, Ziwei Liu

arXiv, 2026 
Paper  /  Project Page  /  Code

Area: Streaming video understanding, VLM

PerceptionComp: A Video Benchmark for Complex Perception-Centric Reasoning - Research paper illustration
PerceptionComp: A Video Benchmark for Complex Perception-Centric Reasoning
Shaoxuan Li*, Zhixuan Zhao*, Hanze Deng*, Zirun Ma*, Shulin Tian, Zuyan Liu, Yushi Hu, Haoning Wu, Yuhao Dong†, Benlin Liu†, Ziwei Liu, Ranjay Krishna

ECCV 2026 
Paper  /  Project Page  /  Code  /  Data

Area: Video benchmark, perception-centric reasoning, multimodal LLM

Insight-V++: Towards Advanced Long-Chain Visual Reasoning with Multimodal Large Language Models - Research paper illustration
Insight-V++: Towards Advanced Long-Chain Visual Reasoning with Multimodal Large Language Models
Yuhao Dong, Zuyan Liu, Shulin Tian, Yongming Rao, Ziwei Liu

arXiv, 2026 
Paper

Area: Visual reasoning, multimodal LLM

Ego-R1: Chain-of-Tool-Thought for Ultra-Long Egocentric Video Reasoning - Research paper illustration
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

TPAMI | ICCV MMRAgI Workshop 2025 
Paper  /  Project Page  /  Code  /  Data

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

Uni-MMMU: A Massive Multi-discipline Multimodal Unified Benchmark - Research paper illustration
Uni-MMMU: A Massive Multi-discipline Multimodal Unified Benchmark
Kai Zou, Ziqi Huang, Yuhao Dong, Shulin Tian, Dian Zheng, Hongbo Liu, Jingwen He, Bin Liu, Yu Qiao, Ziwei Liu

ACL 2026 (Main) 
Paper  /  Project Page  /  Code

Area: Multimodal benchmark, understanding & generation

Evaluation Agent: Efficient and Promptable Evaluation Framework for Visual Generative Models
Fan Zhang*, Shulin Tian*, Ziqi Huang*†, Yu Qiao, Ziwei Liu

ACL 2025 (Main) (Oral) 🏆 SAC Highlight Award 
Paper  /  Project Page  /  Code

Area: Agent, GenAI

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

ACL 2025 (Findings) 
Paper  /  Project Page  /  Code  /  Data

Area: Multimodal agent benchmark on long-horizon reasoning

Image
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  /  Code

Area: Robotics, VLM

Enhancing Low-light Images Using Infrared Encoded Images - Research paper illustration
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 logo

Nanyang Technological University

Ph.D. in Computer Science

Aug. 2024 — Present

Nanyang Technological University logo

Nanyang Technological University

B.Eng. in Electrical and Electronic Engineering
Honours (Highest Distinction)

Aug. 2020 — May 2024

Honors & Awards

Professional Service

  • Talk Organizer: The AI Talks
  • Program Committee: AAAI 2027
  • Conference Reviewer: NeurIPS 2026; ACL 2025-26; ICLR 2026; CVPR 2026; ECCV 2026; ICRA 2025; EMNLP 2025; NAACL 2025
  • Journal Reviewer: IJCV; Neurocomputing
  • Workshop Reviewer: SCOPE @ ICLR 2025; LangRob @ CoRL 2024

Beyond Research

Music

Outdoors

  • PADI Open Water (2022) & Advanced Open Water Diver (2024).
  • Badminton, hiking, and always trying something new.

Last updated: August 2026