Elamur Research⌕
☰
home / authors / Yueqi Song

Yueqi Song

Yueqi Song has 3 papers in our library, in 2024–2025, most of them on Language models & pretraining, Multilingual & cross-lingual NLP, Vision & language; often with Bowen Li, Boxuan Li, Frank F. Xu.

3 papers in our library · 2024–2025

OpenAlex · ORCID · h-index 6 · 22 works · 93 citations OpenAlex, 2026-10-14

📄 3 works in our library · 🔗 Cited 344 times in our library · 7 more in our library without a page yet · ⭐ Paper Stars ranking: #5353

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 · 10 paperscurrent🎓Dalian Polytechnic UniversityDalian · China2025–2026 · 5 papersEmployment since 2025current

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 10The field of science this work belongs to (OpenAlex fields).Computer Science · 3 worksArtificial Intelligence · 3 worksInformation Systems · 1 workArts and Humanities · 2 worksLanguage and Linguistics · 2 worksComputer Vision and Pattern Recognition · 1 workCognitive Neuroscience · 1 workNeuroscience · 1 workSafety Research · 1 workSocial Sciences · 1 work

🧭 Topics 3Research subjects and languages the work is about.Language models & pretraining · 1 workMultilingual & cross-lingual NLP · 1 workVision & language · 1 work

 Works by year

2020s

20252 papers20241 paper

 Papers

The most cited first (OpenAlex and our library).

  1. OpenHands: An Open Platform for AI Software Developers as Generalist Agents (2024 · 221 citations)
    Building LLM agents that do real software work is hard. They must write and change code inside large projects, find information while debugging, and avoid damaging the user's machine. This paper presents OpenHands (formerly OpenDevin), an open, community-built platform for creating both generalist and specialist…
  2. Grounding Multilingual Multimodal LLMs With Cultural Knowledge (2025 · 11 citations)
    Multimodal LLMs tend to fail on culturally specific, long-tail entities and perform worse in low-resource languages, mainly because their training data is dominated by English and Western content.
  3. Synthetic Socratic Debates: Examining Persona Effects on Moral Decision and Persuasion Dynamics (2025 · 9 citations)
    LLMs are often given personas and asked for advice on moral questions, yet earlier studies usually varied a single trait or relied on artificial dilemmas.

All works

10 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. OpenHands: An Open Platform for AI Software Developers as Generalist AgentsarXiv:2407.16741Xingyao Wang, Boxuan Li, Yufan Song, et al.2024 · 221 citations
  2. Pangea: A Fully Open Multilingual Multimodal LLM for 39 Languages ↗arXiv:2410.16153 · no summary yetXiang Yue et al.2024 · 46 citations
  3. An image speaks a thousand words, but can everyone listen? On image transcreation for cultural relevance ↗Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing · no summary yetSimran Khanuja et al.2024 · 28 citations
  4. Beyond Browsing: API-Based Web Agents ↗Findings of the Association for Computational Linguistics: ACL 2025 · no summary yetYueqi Song et al.2025 · 25 citations
  5. SkillWeaver: Web Agents can Self-Improve by Discovering and Honing Skills ↗arXiv (Cornell University) · no summary yetZheng, Boyuan et al.2025 · 19 citations
  6. GlobalBench: A Benchmark for Global Progress in Natural Language Processing ↗Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing · no summary yetYueqi Song et al.2023 · 19 citations
  7. Grounding Multilingual Multimodal LLMs With Cultural KnowledgeConference on Empirical Methods in Natural Language Processing (EMNLP)Jean De Dieu Nyandwi, Yueqi Song, Simran Khanuja, et al.2025 · 11 citations
  8. Synthetic Socratic Debates: Examining Persona Effects on Moral Decision and Persuasion DynamicsConference on Empirical Methods in Natural Language Processing (EMNLP)Jiarui Liu, Yueqi Song, Yunze Xiao, et al.2025 · 9 citations
  9. VisualPuzzles: Decoupling Multimodal Reasoning Evaluation from Domain Knowledge ↗arXiv (Cornell University) · no summary yetYueqi Song et al.2025 · 8 citations
  10. What Is Missing in Multilingual Visual Reasoning and How to Fix It ↗Findings of the Association for Computational Linguistics: NAACL 2025 · no summary yetYueqi Song, Simran Khanuja, Graham Neubig2025 · 8 citations

 Co-authors here

12 of 13 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 344 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/yueqi-song/