🧑‍🔬 Zhenguo Li

🏛️ Affiliations

🏢Huawei TechnologiesShenzhen · China2013–2026 · 133 paperscurrent🎓Hong Kong University of Science and TechnologyHong Kong · China2023–2026 · 4 paperscurrent🎓Northwestern Polytechnical UniversityXi'an · China2020–2026 · 3 paperscurrent🏢Robotics ResearchCincinnati · United States2026 · 1 papercurrent🎓Chinese University of Hong KongHong Kong · China2006–2009 · 10 papers🎓Shandong UniversityJinan · China2011–2014 · 5 papers🎓Columbia UniversityNew York · United States2011–2013 · 5 papers🏢Huawei TechnologiesMarkham · Canada2025 · 2 papers🎓Dalian Medical UniversityDalian · China2022–2023 · 2 papers🏥Second Affiliated Hospital of Dalian Medical UniversityDalian · China2022–2023 · 2 papers

From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. 17 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. MetaMath: Bootstrap Your Own Mathematical Questions for Large Language Models (2023 · 565 citations)
   Open-source LLMs such as LLaMA-2 lag well behind closed models on multi-step maths word problems. Fine-tuning helps, but it depends on having enough varied training questions. MetaMath addresses this by growing the GSM8K and MATH training sets from the question side as well as the answer side, producing a dataset…
2. Progressive-Hint Prompting Improves Reasoning in Large Language Models (2023 · 131 citations)
   Few-shot prompting methods such as Chain-of-Thought (CoT) and self-consistency improve multi-step reasoning in LLMs, but they treat each answer as final and never feed it back to the model.
3. PixArt-α: Fast Training of Diffusion Transformer for Photorealistic Text-to-Image Synthesis (2023 · 87 citations)
   Training state-of-the-art text-to-image (T2I) diffusion models takes thousands of GPU days and hundreds of thousands of dollars.
4. LEGO-Prover: Neural Theorem Proving with Growing Libraries (2023 · 79 citations)
   Formal theorem proving is still hard for large language models. Existing LLM-based provers often fail on competition problems at middle-school level. These "plain" provers write each proof as one long monolithic block and treat the available theorem library as fixed. So a lemma proved for one problem cannot help with…
5. G-LLaVA: Solving Geometric Problem with Multi-Modal Large Language Model (2023 · 76 citations)
   Multimodal LLMs, including GPT-4-V, often misread geometric diagrams. They confuse how points and lines relate, misjudge angles and hallucinate figure contents, so they struggle with geometry problems that require visual input. Public geometry datasets are also small and lack image descriptions. The authors address…

All works

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

1. DeepFM: A Factorization-Machine based Neural Network for CTR Prediction ↗International Joint Conference on Artificial Intelligence · no summary yetHuifeng Guo et al.2017 · 2,612 citations
2. MetaMath: Bootstrap Your Own Mathematical Questions for Large Language ModelsarXiv:2309.12284Longhui Yu, Weisen Jiang, Han Shi, et al.2023 · 565 citations
3. DetCo: Unsupervised Contrastive Learning for Object Detection ↗IEEE/CVF International Conference on Computer Vision (ICCV) · no summary yetEnze Xie et al.2021 · 340 citations
4. Auto-FPN: Automatic Network Architecture Adaptation for Object Detection Beyond Classification ↗IEEE/CVF International Conference on Computer Vision (ICCV) · no summary yetHang Xu et al.2019 · 229 citations
5. DDP: Diffusion Model for Dense Visual Prediction ↗IEEE/CVF International Conference on Computer Vision (ICCV) · no summary yetYuanfeng Ji et al.2023 · 153 citations
6. Spatial-Aware Graph Relation Network for Large-Scale Object Detection ↗IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · no summary yetHang Xu et al.2019 · 141 citations
7. Progressive-Hint Prompting Improves Reasoning in Large Language ModelsarXiv:2304.09797Chuanyang Zheng, Zhengying Liu, Enze Xie, et al.2023 · 131 citations
8. Reasoning-RCNN: Unifying Adaptive Global Reasoning Into Large-Scale Object Detection ↗IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · no summary yetHang Xu et al.2019 · 107 citations
9. T2I-CompBench: A Comprehensive Benchmark for Open-world Compositional Text-to-image Generation ↗neural information processing systems · no summary yetKaiyi Huang et al.2023 · 104 citations
10. T2I-CompBench++: An Enhanced and Comprehensive Benchmark for Compositional Text-to-image Generation ↗arXiv:2307.06350 · no summary yetKaiyi Huang et al.2023 · 97 citations
11. SM-NAS: Structural-to-Modular Neural Architecture Search for Object Detection ↗arXiv:1911.09929 · no summary yetLewei Yao et al.2019 · 95 citations
12. PixArt-α: Fast Training of Diffusion Transformer for Photorealistic Text-to-Image SynthesisarXiv:2310.00426Junsong Chen, Jincheng Yu, Chongjian Ge, et al.2023 · 87 citations
13. LEGO-Prover: Neural Theorem Proving with Growing LibrariesarXiv:2310.00656Haiming Wang, Huajian Xin, Chuanyang Zheng, et al.2023 · 79 citations
14. G-LLaVA: Solving Geometric Problem with Multi-Modal Large Language ModelarXiv:2312.11370Jiahui Gao, Renjie Pi, Jipeng Zhang, et al.2023 · 76 citations
15. MetaBEV: Solving Sensor Failures for 3D Detection and Map Segmentation ↗IEEE/CVF International Conference on Computer Vision (ICCV) · no summary yetChongjian Ge et al.2023 · 67 citations
16. Exploring Geometry-aware Contrast and Clustering Harmonization for Self-supervised 3D Object Detection ↗IEEE/CVF International Conference on Computer Vision (ICCV) · no summary yetHanxue Liang et al.2021 · 60 citations
17. DT-Solver: Automated Theorem Proving with Dynamic-Tree Sampling Guided by Proof-level Value Function ↗Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · no summary yetHaiming Wang et al.2023 · 40 citations
18. MUSTARD: Mastering Uniform Synthesis of Theorem and Proof Data ↗arXiv:2402.08957 (ICLR 2024 spotlight) · no summary yetYinya Huang et al.2024 · 29 citations
19. Lyra: Orchestrating Dual Correction in Automated Theorem Proving ↗arXiv:2309.15806 · no summary yetChuanyang Zheng et al.2023 · 24 citations
20. Mathesis: Towards Formal Theorem Proving from Natural Languages ↗arXiv:2506.07047 · no summary yetYu Xuejun et al.2025 · 9 citations
21. ProofAug: Efficient Neural Theorem Proving via Fine-grained Proof Structure Analysis ↗arXiv:2501.18310 · no summary yetHaoxiong Liu et al.2025 · 4 citations

🤝 Co-authors here

12 of 27 co-authors with a page, the most papers together first.

• Enze Xie ×3
• Zhengying Liu ×3
• Chuanyang Zheng ×2
• Han Shi ×2
• James Tin-Yau Kwok ×2
• Jincheng Yu ×2
• Haiming Wang
• Hang Xu
• Huajian Xin
• Jiacheng Ye
• Jiahui Gao
• Jian Yin

Venues

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

• IEEE/CVF International Conference on Computer Vision (ICCV) ×5
• IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings ×2
• International Joint Conference on Artificial Intelligence
• Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
• neural information processing systems

🔗 Cited by

Papers of our library cite their works 1,233 times (of the 149,439 papers whose bibliographies we read); 284 citing papers with a page here →.

Updated 2 November 2026

↑ back to top

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