Scholar
Jixuan Chen
Google Scholar ID: kmBSlgEAAAAJ
UC San Diego
Multimodal agents
Natural language processing
Machine learning
Follow
Homepage
↗
Google Scholar
↗
Citations & Impact
All-time
Citations
747
H-index
6
i10-index
6
Publications
9
Co-authors
6
list available
Contact
Email
jic182@ucsd.edu
Twitter
Open ↗
GitHub
Open ↗
LinkedIn
Open ↗
Publications
11 items
DeliveryBench: Can Agents Earn Profit in Real World?
2025
Cited
0
VideoAgentTrek: Computer Use Pretraining from Unlabeled Videos
2025
Cited
0
OpenCUA: Open Foundations for Computer-Use Agents
2025
Cited
0
MMBench-GUI: Hierarchical Multi-Platform Evaluation Framework for GUI Agents
2025
Cited
0
OPT-BENCH: Evaluating LLM Agent on Large-Scale Search Spaces Optimization Problems
2025
Cited
0
Scaling Computer-Use Grounding via User Interface Decomposition and Synthesis
2025
Cited
0
Wan: Open and Advanced Large-Scale Video Generative Models
2025
Cited
1
What Is a Good Caption? A Comprehensive Visual Caption Benchmark for Evaluating Both Correctness and Coverage of MLLMs
2025
Cited
0
Load more
Resume (English only)
Academic Achievements
- Publications:
* Spider 2.0: Evaluating Language Models on Real-World Enterprise Text-to-SQL Workflows (ICLR'25, Oral Presentation)
* OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments (NeurIPS'24 D&B Track)
* COMMA : A Communicative Multimodal Multi-Agent Benchmark (Preprint'24, Under Review)
* Spider2-V: How Far Are Multimodal Agents From Automating Data Science and Engineering Workflows? (NeurIPS'24 D&B Track, Spotlight Presentation)
- Awards: Merit Student of Jiangsu Province
Research Experience
- Lab: XLANG Lab @ HKU
- Position: Research Intern
- Duration: 2023.08 - present
- Advisor: Prof. Tao Yu
- Research Areas: Executable language grounding, tool usage, code generation, and multimodal LLMs
Education
- Degree: B.E. in Software Engineering
- University: Nanjing University
- Duration: 2021.09 - 2025.07
- GPA: 91.60 / 100.0 (4.58/5.00)
- Ranking: 1/259
- Exchange Program: The Hong Kong University of Science and Technology
- Exchange Duration: 2024.01 - 2024.05
- Scholarship: Full scholarship
Background
- Research Interests: ML and NLP
- Current Research Focus: Multimodal LLM reasoning and Embodied agents
Miscellany
- Personal Interests: Not provided
Co-authors
6 total
Tao Yu
Assistant Professor, Computer Science, University of Hong Kong
Tianbao Xie
University of Hong Kong
Fangyu Lei
Institute of Automation, Chinese Academy of Sciences
Caiming Xiong
Salesforce Research
Siheng Zhao
University of Southern California
Victor Zhong
Assistant Professor at Cheriton School of Computer Science, University of Waterloo
×
Welcome back
Sign in to Agora
Welcome back! Please sign in to continue.
Email address
Password
Forgot password?
Continue
Do not have an account?
Sign up