Elamur Research⌕
☰
home / authors / Hiroki Furuta

Hiroki Furuta

Hiroki Furuta has 3 papers in our library, in 2023–2026, most of them on Code & programming languages; often with Yutaka Matsuo, Aleksandra Faust, Douglas Eck.

3 papers in our library · 2023–2026

OpenAlex · ORCID · h-index 4 · 22 works · 345 citations OpenAlex, 2026-10-14

📄 3 works in our library · 🔗 Cited 257 times in our library · 2 more in our library without a page yet · ⭐ Paper Stars ranking: #6866

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

🎓The University of TokyoTokyo · Japan2020–2026 · 14 paperscurrent🏢Google DeepMindLondon · United Kingdom2026 · 4 paperscurrent

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 8The field of science this work belongs to (OpenAlex fields).Computer Science · 3 worksArtificial Intelligence · 3 worksInformation Systems · 2 worksArts and Humanities · 1 workComputer Vision and Pattern Recognition · 1 workLanguage and Linguistics · 1 workSafety Research · 1 workSocial Sciences · 1 work

🧭 Topics 1Research subjects and languages the work is about.Code & programming languages · 1 work

 Works by year

2020s

20261 paper20241 paper20231 paper

 Papers

The most cited first (OpenAlex and our library).

  1. A Real-World WebAgent with Planning, Long Context Understanding, and Program Synthesis (2023 · 120 citations)
    Agents driven by large language models do well on simulated web environments but struggle on real websites.
  2. A Human-Inspired Reading Agent with Gist Memory of Very Long Contexts (2024 · 46 citations)
    Large language models have a hard limit on input length, and their accuracy often drops on long inputs well before that limit.
  3. Understanding Emergent Misalignment via Feature Superposition Geometry (2026)
    The paper investigates why emergent misalignment happens. This is the phenomenon where fine-tuning an LLM on narrow, apparently benign data, such as insecure code or wrong health, career or legal advice, makes it produce broadly harmful answers. The authors argue that feature superposition is the cause. Because…

All works

5 works of theirs in our library, the most cited first; 3 with a page here, the others link their original until we summarise them.

  1. Open X-Embodiment: Robotic Learning Datasets and RT-X Models ↗arXiv:2310.08864 · no summary yetEmbodiment Collaboration et al.2023 · 204 citations
  2. A Real-World WebAgent with Planning, Long Context Understanding, and Program SynthesisarXiv:2307.12856Izzeddin Gur, Hiroki Furuta, Austin Huang, et al.2023 · 120 citations
  3. A Human-Inspired Reading Agent with Gist Memory of Very Long ContextsarXiv:2402.09727Kuang-Huei Lee, Xinyun Chen, Hiroki Furuta, et al.2024 · 46 citations
  4. Improving Dynamic Object Interactions in Text-to-Video Generation with AI Feedback ↗arXiv (Cornell University) · no summary yetHiroki Furuta et al.2024 · 2 citations
  5. Understanding Emergent Misalignment via Feature Superposition GeometryAnnual Meeting of the Association for Computational Linguistics (ACL)Gouki Minegishi, Hiroki Furuta, Takeshi Kojima, et al.2026

 Co-authors here

9 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 257 times (of the 149,439 papers whose bibliographies we read); 71 citing papers with a page here →.

Updated

This page in Markdown → https://md.research.elamur.ai/free/en/authors/hiroki-furuta/