Scholar
Genglin Liu
Google Scholar ID: xTX3r0IAAAAJ
University of California, Los Angeles
Citations & Impact
Citations
125
H-index
5
i10-index
5
Publications
10
Co-authors
17
list available
Publications
Resume (English only)
Academic Achievements
- - MOSAIC: Modeling Social AI for Content Dissemination and Regulation in Multi-Agent Simulations (EMNLP 2025 Oral)
- - WebCoach: Improve Browsing Agents with Memory-Aware Guidance for Better Web Navigation (Blog Post)
- - AI Debate Aids Assessment of Controversial Claims (NeurIPS 2025)
- - X-Teaming: Multi-Turn Jailbreaks and Defenses with Adaptive Multi-Agents (COLM 2025)
- - SciCode: A Research Coding Benchmark Curated by Scientists (NeurIPS 2024 Datasets and Benchmarks track)
- - Examining LLMs’ Uncertainty Expression Towards Questions Outside Parametric Knowledge (Preprint 2023)
- - Paxion: Patching Action Knowledge in Video-Language Foundation Models (NeurIPS 2023, Spotlight)
- - An Augmented Multilingual NLI Approach Towards Online News Persuasion Techniques Detection (ACL workshop 2023)
Research Experience
- - Fall 2025: Google Research, Student Researcher, Hosts: Jad Aboudiab, Krishna Viswanathan, Ariel Fuxman
- - Summer 2025: Amazon.com, Inc., Applied Scientist Intern, Stores Foundational AI, Hosts: Shijie Geng, Zoey Li, Jimmy Liu
- - Research intern at the Information Fusion Lab and TRIPODS Institute for Theoretical Foundations of Data Science at UMass Amherst, advised by Prof. Ina Fiterau and Prof. Yulong Lu
Education
- - University of California, Los Angeles: Ph.D. in Computer Science, 2024-present, advised by Prof. Saadia Gabriel
- - University of Illinois, Urbana-Champaign: Master in Computer Science, 2022-2023, advised by Prof. Heng Ji and Prof. Hao Peng
- - University of Massachusetts, Amherst: B.S. in Computer Science & Mathematics, 2018-2022, Degree Honors: Commonwealth Honors Scholar with Greatest Distinction
Background
- Research Interests: Large Language Models and agent systems powered by them. Recently focused on web agents, self-evolving models, and memory mechanisms of LLM agents. During his PhD, he has worked on multi-agent simulation systems and LLM safety.
Miscellany
- Personal interests and hobbies not provided
