Elamur Research⌕
☰
home / authors / Jing Yu Koh

Jing Yu Koh

Jing Yu Koh has 2 papers in our library, in 2024, most of them on Vision & language; often with Daniel Fried, Graham Neubig, Robert Lo.

2 papers in our library · 2024

OpenAlex · h-index 13 · 31 works · 1,165 citations OpenAlex, 2026-10-14

📄 2 works in our library · 🔗 Cited 330 times in our library · 9 more in our library without a page yet · ⭐ Paper Stars ranking: #6011

The profile is the library's match of the name; two people with one name are not always told apart.

Elsewhere: Google Scholar · Semantic Scholar · dblp · ACL Anthology

 Affiliations

🎓Carnegie Mellon UniversityPittsburgh · United States2023–2026 · 13 paperscurrent🎓Singapore University of Technology and DesignSingapore · Singapore2016–2020 · 6 papers🏢GoogleMountain View · United States2021–2023 · 5 papers

From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine.

 Fields, topics and concepts

Of its works in our library, with the number of works on each.

📚 Shelves 6The field of science this work belongs to (OpenAlex fields).Computer Science · 2 worksArtificial Intelligence · 2 worksInformation Systems · 2 worksArts and Humanities · 1 workComputer Vision and Pattern Recognition · 1 workLanguage and Linguistics · 1 work

🧭 Topics 1Research subjects and languages the work is about.Vision & language · 1 work

 Works by year

2020s

20242 papers

 Papers

The most cited first (OpenAlex and our library).

  1. VisualWebArena: Evaluating Multimodal Agents on Realistic Visual Web Tasks (2024 · 184 citations)
    Most benchmarks for autonomous web agents rely on text alone. Many everyday web tasks, however, depend on what a page or a reference picture looks like. VisualWebArena addresses this gap. It is a benchmark that extends the WebArena framework with tasks that cannot be solved without visual understanding.
  2. Tree Search for Language Model Agents (2024 · 61 citations)
    Language-model web agents still fall far short of people on realistic browsing tasks. Humans solve 78% of WebArena tasks and 89% of VisualWebArena tasks, while agents usually stay under 20%. The authors argue that a major cause is that agents commit to one action at a time and cannot spend extra inference compute…

All works

11 works of theirs in our library, the most cited first; 2 with a page here, the others link their original until we summarise them.

  1. VisualWebArena: Evaluating Multimodal Agents on Realistic Visual Web TasksAnnual Meeting of the Association for Computational Linguistics (ACL)Jing Yu Koh, Robert Lo, Lawrence Jang, et al.2024 · 184 citations
  2. Grounding Language Models to Images for Multimodal Inputs and Outputs ↗arXiv (Cornell University) · no summary yetJing Yu Koh, Ruslan Salakhutdinov, Daniel Fried2023 · 82 citations
  3. Tree Search for Language Model AgentsarXiv:2407.01476Jing Yu Koh, Stephen McAleer, Daniel Fried, et al.2024 · 61 citations
  4. OmniACT: A Dataset and Benchmark for Enabling Multimodal Generalist Autonomous Agents for Desktop and Web ↗Lecture notes in computer science · no summary yetRaghav Kapoor et al.2024 · 60 citations
  5. Dissecting Adversarial Robustness of Multimodal LM Agents ↗arXiv (Cornell University) · no summary yetChen Henry Wu et al.2024 · 20 citations
  6. Odysseys: Benchmarking Web Agents on Realistic Long Horizon Tasks ↗arXiv (Cornell University) · no summary yetLawrence Jang et al.2026 · 3 citations
  7. Multimodal Graph Learning for Generative Tasks ↗arXiv (Cornell University) · no summary yetMinji Yoon et al.2023 · 2 citations
  8. iOSWorld: A Benchmark for Personally Intelligent Phone Agents ↗arXiv (Cornell University) · no summary yetLawrence Jang et al.2026 · 1 citation
  9. MyPCBench: A Benchmark for Personally Intelligent Computer-Use Agents ↗arXiv (Cornell University) · no summary yetLawrence Jang et al.2026 · 1 citation
  10. cua-speedrun: Standardized Benchmarking of the Speed of Computer-Use Agents ↗arXiv (Cornell University) · no summary yetPranjal Aggarwal et al.2026
  11. Multi-Agent Computer Use ↗arXiv (Cornell University) · no summary yetJing Yu Koh, Ruslan Salakhutdinov, Daniel Fried2026

 Co-authors here

6 co-authors with a page, the most papers together first.

Venues

Where their works here were published, the most works first, with the editions of those that have a page.

 Cited by

Papers of our library cite their works 330 times (of the 149,439 papers whose bibliographies we read); 81 citing papers with a page here →.

Updated

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/authors/jing-yu-koh/