🧑‍🔬 Yingbo Zhou

🏛️ Affiliations

🏢SalesforceSan Francisco · United States2018–2026 · 54 paperscurrent🎓East China Normal UniversityShanghai · China2023–2026 · 13 papersEducationcurrent🎓University at Buffalo, State University of New YorkBuffalo · United States2011–2017 · 13 papers🎓Hong Kong Polytechnic UniversityHong Kong · China2009–2011 · 6 papers🎓Hunan UniversityChangsha · China2010–2016 · 4 papers🎓The University of Texas at AustinAustin · United States2022–2025 · 2 papers🏢GoogleMountain View · United States2013–2023 · 2 papers🏢State Grid Corporation of ChinaBeijing · China2021–2022 · 2 papers🏛️Chinese Academy of SciencesBeijing · China2021 · 2 papers🔬Shanghai Advanced Research InstitutePudong · China2021 · 2 papers

From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. 12 more institutions on single bylines are not listed.

🧭 Fields, topics and concepts

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

📅 Works by year

2020s

📄 Papers

The most cited first (OpenAlex and our library).

1. LLMs Get Lost In Multi-Turn Conversation (2025 · 82 citations)
   Most LLM benchmarks give the model a complete instruction in a single turn. Real users, however, often begin vaguely and add details as the conversation goes on. Laban et al. measure how much this gap matters. They build a "sharded simulation" environment from existing high-quality single-turn benchmarks such as…
2. L2CEval: Evaluating Language-to-Code Generation Capabilities of Large Language Models (2024 · 27 citations)
   Large language models trained on code can turn natural-language requests into executable programs, but earlier evaluations covered isolated tasks, single model families or particular learning setups.
3. CodeTree: Agent-guided Tree Search for Code Generation with Large Language Models (2025 · 21 citations)
   Hard programming tasks have a huge space of possible solutions. Older methods either sample many independent candidates or repeatedly refine one early attempt, which can trap them in a local optimum. CodeTree addresses this by organizing code generation as a tree search run by cooperating LLM agents. A Thinker agent…
4. AnchorSeg: Language Grounded Query Banks for Reasoning Segmentation (2026)
   Reasoning segmentation asks a model to produce a pixel mask for a target described only indirectly, for example by its function rather than its name.

All works

20 works of theirs in our library, the most cited first; 4 with a page here, the others link their original until we summarise them.

1. End-to-End Dense Video Captioning with Masked Transformer ↗IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · no summary yetLuowei Zhou et al.2018 · 636 citations
2. RNG-KBQA: Generation Augmented Iterative Ranking for Knowledge Base Question Answering ↗Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · no summary yetXi Ye et al.2022 · 198 citations
3. CodeGen2: Lessons for Training LLMs on Programming and Natural Languages ↗arXiv:2305.02309 · no summary yetErik Nijkamp et al.2023 · 94 citations
4. Learn to Grow: A Continual Structure Learning Framework for Overcoming Catastrophic Forgetting ↗arXiv (Cornell University) · no summary yetXilai Li et al.2019 · 94 citations
5. LLMs Get Lost In Multi-Turn ConversationarXiv:2505.06120Philippe Laban, Hiroaki Hayashi, Yingbo Zhou, et al.2025 · 82 citations
6. WOAD: Weakly Supervised Online Action Detection in Untrimmed Videos ↗IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · no summary yetMingfei Gao et al.2021 · 55 citations
7. Focused Attention Improves Document-Grounded Generation ↗Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies · no summary yetShrimai Prabhumoye et al.2021 · 55 citations
8. Unsupervised Paraphrasing with Pretrained Language Models ↗Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing · no summary yetTong Niu et al.2021 · 48 citations
9. A Multi-Discriminator CycleGAN for Unsupervised Non-Parallel Speech Domain Adaptation ↗Interspeech (USB) · no summary yetEhsan Hosseini-Asl et al.2018 · 46 citations
10. Augmented Cyclic Adversarial Learning for Low Resource Domain Adaptation ↗arXiv (Cornell University) · no summary yetEhsan Hosseini-Asl et al.2018 · 43 citations
11. Improving End-to-End Speech Recognition with Policy Learning ↗IEEE International Conference on Acoustics Speech and Signal Processing · no summary yetYingbo Zhou, Caiming Xiong, Richard Socher2018 · 43 citations
12. UniControl: A Unified Diffusion Model for Controllable Visual Generation In the Wild ↗arXiv (Cornell University) · no summary yetCan Qin et al.2023 · 36 citations
13. An Investigation of Phone-Based Subword Units for End-to-End Speech Recognition ↗Interspeech (USB) · no summary yetWeiran Wang et al.2020 · 31 citations
14. L2CEval: Evaluating Language-to-Code Generation Capabilities of Large Language ModelsTransactions of the Association for Computational Linguistics (TACL)Ansong Ni, Pengcheng Yin, Yilun Zhao, et al.2024 · 27 citations
15. CodeTree: Agent-guided Tree Search for Code Generation with Large Language ModelsConference of the North American Chapter of the Association for Computational Linguistics (NAACL)Jierui Li, Hung Le, Yingbo Zhou, et al.2025 · 21 citations
16. Improved Regularization Techniques for End-to-End Speech Recognition ↗arXiv (Cornell University) · no summary yetYingbo Zhou, Caiming Xiong, Richard Socher2017 · 11 citations
17. Converse: A Tree-Based Modular Task-Oriented Dialogue System ↗arXiv (Cornell University) · no summary yetTian Xie et al.2022 · 10 citations
18. Online Structured Meta-learning ↗arXiv (Cornell University) · no summary yetHuaxiu Yao et al.2020 · 9 citations
19. AnchorSeg: Language Grounded Query Banks for Reasoning SegmentationAnnual Meeting of the Association for Computational Linguistics (ACL)Rui Qian, Chuanhang Deng, Qiang Huang, et al.2026
20. Continual Learning via Explicit Structure Learning ↗no summary yetXilai Li et al.2018

🤝 Co-authors here

12 of 17 co-authors with a page, the most papers together first.

• Caiming Xiong ×2
• Ansong Ni
• Dejing Dou
• Hiroaki Hayashi
• Hung Le
• Jierui Li
• Jintao Chen
• Martin Riddell
• Mingxuan Li
• Pengcheng Yin
• Philippe Laban
• Rui Qian

Venues

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

• Annual Meeting of the Association for Computational Linguistics (ACL) ×2: ACL 2026
• IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings ×2
• Interspeech (USB) ×2
• Conference of the North American Chapter of the Association for Computational Linguistics (NAACL): NAACL 2025
• Transactions of the Association for Computational Linguistics (TACL): Transactions of the Association for Computational Linguistics (TACL) 2024
• IEEE International Conference on Acoustics Speech and Signal Processing
• Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
• Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing

🔗 Cited by

Papers of our library cite their works 408 times (of the 149,439 papers whose bibliographies we read); 62 citing papers with a page here →.

Updated 1 November 2026

↑ back to top

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