Hello World
My name is Rui Sun (Rui is pronounced as Ray). I am a CS PhD student at UCLA NLP advised by Prof. Kai-Wei Chang. My experience and research topics can be found in Experience section.
[GitHub]
[LinkedIn]
[Twitter]
[Email] (Please contact me via UCLA email address; I seldom check previous Columbia email)
If you would like to know more about me, you could view the source code of this webpage for more information. (Right-click the page and select View Page Source)
Last Update: 08/07/2026
Publications and Preprints
[Semantic Scholar] (My most up-to-date paper list)
*, ** denotes equal contribution (co-first and co-second authorship); † denotes correspondence author or equal advising
Some papers are on the way... I will update later.
EMBODIED WEB AGENTS: Bridging Physical-Digital Realms for Integrated Agent Intelligence
NeurIPS 2025 Datasets and Benchmarks Track (Spotlight, Top 3%)
Yining Hong*, Rui Sun*, Bingxuan Li**, Xingcheng Yao**, Maxine Wu**, Alexander Chien**, Da Yin, Ying Nian Wu, Zhecan James Wang, Kai-Wei Chang
[Paper]
[Project Page][Code] [Twitter]
ARMAP: Scaling Autonomous Agents via Automatic Reward Modeling And Planning
ICLR 2025
Zhenfang Chen*, Delin Chen*, Rui Sun*, Wenjun Liu*, Chuang Gan
[Paper] [Paper List of Inference/Test Time Scaling/Computing]
[Project Page][Code] [Twitter]
JourneyBench: A Challenging One-Stop Vision-Language Understanding Benchmark of Generated Images
NeurIPS 2024 Datasets and Benchmarks Track
Zhecan Wang*, Junzhang Liu*, Chia-Wei Tang, Hani Alomari, Anushka Sivakumar, Rui Sun, Wenhao Li, Md. Atabuzzaman, Hammad Ayyubi, Haoxuan You, Alvi Md Ishmam, Kai-Wei Chang, Shih-Fu Chang, Chris Thomas
[Paper] [Project Page][Code] [量子位] [Twitter]
Detecting Multimodal Situations with Insufficient Context and Abstaining from Baseless Predictions
ACM MM 2024 (long)
Junzhang Liu*, Zhecan Wang*, Hammad Ayyubi*, Haoxuan You, Chris Thomas, Rui Sun, Shih-Fu Chang, Kai-Wei Chang
[Paper][Code]
GENOME: Generative Neuro-Symbolic Visual Reasoning by Growing and Reusing Modules
ICLR 2024
Zhenfang Chen*, Rui Sun*, Wenjun Liu*, Yining Hong, Chuang Gan
[Paper] [Project Page][Video Demo][Code] [Twitter]
IdealGPT: Iteratively Decomposing Vision and Language Reasoning via Large Language Models
Findings of EMNLP 2023 (long)
Haoxuan You*, Rui Sun*, Zhecan Wang*, Long Chen, Gengyu Wang, Hammad A. Ayyubi, Kai-Wei Chang, Shih-Fu Chang
[Paper][Code]
UniFine: A Unified and Fine-grained Approach for Zero-shot Vision-Language Understanding
Findings of ACL 2023 (long)
Rui Sun*, Zhecan Wang*, Haoxuan You*, Noel Codella, Kai-Wei Chang, Shih-Fu Chang
[Paper][Code]
Find Someone Who: Visual Commonsense Understanding in Human-Centric Grounding
Findings of EMNLP 2022 (long)
Haoxuan You, Rui Sun, Zhecan Wang, Kai-Wei Chang, Shih-Fu Chang
[Paper][Code]
Technical Reports
An empirical study of QA-oriented pretraining
Rui Sun
[GitHub Repo]
A Survey of LLM Accountability in Education, Healthcare, and Human Resources
Abdolrahim Arjomand, Oscar Granadino Horvath, Rui Sun†, Weihan Qu († denotes correspondence author)
[Report] [Slide]
Experience
UCLA NLP, Research Assistant
Advisor: Prof. Kai-Wei Chang, Sep 2024 -- Present
Embodied Web Agent (Mentor: Dr. Yining Hong) (NeurIPS 2025 Datasets and Benchmarks Track (Spotlight))
Agent Topology (Accepted by COLM 2026)
Agent Memory Use
Embodied Agent Experience Learning
More are on the way...
Apple Foundation Model (AFM) Team (Apple AI/ML), Research Funding Collaboration and Research Intern
Dec 2025 - Jun 2026, Jun 2026 -- Present
AWS GenAI, Research Funding Collaboration
Mentor: Dr. Md Mofijul Islam, Oct 2025 -- Jun 2026
Multimodal Search Agent (will be released)
Microsoft Research, Redmond (Deep Learning Group), Research Intern
Mentor: Dr. Hao Cheng, Jun 2025 -- Sep 2025
Memory Use for Computer Use Agent
MIT-IBM Watson AI Lab, Research Assistant
Advisor & Mentor: Dr. Zhenfang Chen, Prof. Chuang Gan, Jun 2023 -- Oct 2024
Inference Time Scaling for Language Agent with Monte Carlo Tree Search (ICLR 2025)
Neuro-Symbolic Visual Reasoning (ICLR 2024)
Digital Video and Multimedia (DVMM) Lab, Columbia University, Research Assistant
Advisor & Mentor: Dr. Haoxuan You, Prof. Long Chen, Prof. Kai-Wei Chang,Prof. Shih-Fu Chang, Oct 2021 -- Jun 2023, Oct 2023 -- Jun 2024
Vision and Language Understanding Evaluation (NeurIPS 2024 Datasets and Benchmarks Track)
Vision Language Models Hallucination Mitigation (ACM MM 2024)
Large Language Model Aided Visual Reasoning (Findings of EMNLP 2023)
Zero-shot Vision-Language Understanding (Findings of ACL 2023)
Human-centric Visual Commonsense Grounding Dataset (Findings of EMNLP 2022)
Task-oriented Pretraining (Second-stage Pretraining) of Vision-Language Pretrained Models (Technical Report)
Columbia NLP, Research Assistant
Advisor: Prof. Zhou Yu, Sep 2023 -- Mar 2024
Fine-grained and Explainable Visual Categorization (More details can be found in this paper)
Rehab Engineering Alliance & Center Transforming Low Vision, NYU Langone Health, Research Assistant
Advisor: Prof. JohnRoss Rizzo, Prof. Zhou Yu, Jun 2023 -- Aug 2023
AI for Social Good: Deploy Vision-Language & Large Language Models in wearable devices for Blindness and Low Vision People (More details can be found in this page)
Intelligent Information Processing (IIP) Lab, Xidian University, Research Assistant
Advisor: Prof. Nannan Wang, Sep 2020 -- Jul 2021
Human Face Frontalization and Hallucination (More details can be found here)
Collaborations
Sponsors
Honors & Awards
Research fund from Amazon Science Hub (with Prof. Kai-Wei Chang), 2025
Research fund from Google Research Scholar Program (with Prof. Chris Thomas), 2025
Interdisciplinary Contest in Modeling (ICM), Meritorious Winner, 2018
Service
Reviewer
NLP: EMNLP, EACL, NAACL, ACL Rolling Review (ARR), ACL
AI: AAAI
Multimedia: ACM MM
ML: ICLR, NeurIPS Dataset & Benchmark Track, NeurIPS Postion Paper Track, NeurIPS
Computer Vision: CVPR, ECCV
Journal: JAIR, JMLR
Workshop: Scaling Environments for Agents (SEA), NeurIPS 2025 Workshop
Trust Before Use: Building Foundation Models that You Can Trust (T2FM), ICCV 2025 Workshop
Student Research Workshop (SRW), ACL 2026
The 2nd Workshop on Lifelong Agents: Learning, Aligning, and Evolving, COLM 2026
DocInsights Workshop, EMNLP 2026
Conference Volunteer
NeruIPS 2025
Teaching Assistant at UCLA
CS 31 Introduction to Computer Science, worked with Prof. David Smallberg, Spring 2026
CS M146 Introduction to Machine Learning, working with Prof. Kai-Wei Chang, Fall 2025
Teaching Assistant at Columbia
EECS 6699 Mathematics of Deep Learning, worked with Prof. Predrag Jelenkovic, Spring 2024
COMS 4995 Deep Learning for Computer Vision, worked with Prof. Peter Belhumeur, Fall 2023
ELEN 4815 Random Signals and Noise, worked with Prof. Irving Kalet, Spring 2023
COMS 4995 Neural Networks & Deep Learning, worked with Prof. Richard Zemel, Fall 2022
COMS 4732 Computer Vision II, worked with Prof. Carl Vondrick, Spring 2022
Misc
Students worked/working with me (I feel fortunate to work with these talented students)
Maxine Wu (co-mentor with Dr. Yining Hong, UCLA Undergraduate Student)
Alexander Chien (co-mentor with Dr. Yining Hong, UCLA Undergraduate Student -> UCLA CS Master's Student)
Junhua Huang (UCLA CS Master's Student)
Photos
Los Angeles, CA, 2024 Fall, Royce Hall
Los Angeles, CA, 2024 Fall, Getty Center
Drake Stadium, CA, 2024 Fall, My Best 10KM Record
Old Photos