🧑‍🔬 Jun Zhu

🏛️ Affiliations

🎓Tsinghua UniversityBeijing · China2011–2026 · 25 paperscurrent🎓University of Science and Technology of ChinaHefei · China1986–2026 · 10 paperscurrent🎓Northeastern UniversityShenyang · China2006–2011 · 7 papers🔬Peng Cheng LaboratoryShenzhen · China2022 · 3 papers🎓Sichuan UniversityChengdu · China2022 · 3 papers🎓Beijing Institute of TechnologyBeijing · China2024 · 2 papers🏥The Second Affiliated Hospital of Bengbu Medical CollegeBengbu · China2022–2024 · 2 papers🔬Zhejiang LabHangzhou · China2023–2024 · 2 papers🏥West China Second University Hospital of Sichuan UniversityChengdu · China2022 · 2 papers🔬State Key Laboratory of Intelligent Technology and SystemsBeijing · China2014–2017 · 2 papers

From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. 20 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. Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection (2023 · 472 citations)
   The paper targets open-set object detection: finding objects in an image from free-form text such as category names or referring expressions, not only from a fixed label list.
2. CodeS: Towards Building Open-source Language Models for Text-to-SQL (2024 · 190 citations)
   Most leading text-to-SQL systems rely on closed LLMs such as GPT-4 and ChatGPT. That brings opaque architectures, privacy concerns from sending data to API providers, and high inference costs. The authors address this with CodeS, a family of fully open-source models with 1B to 15B parameters. CodeS was made by…
3. SageAttention: Accurate 8-Bit Attention for Plug-and-play Inference Acceleration (2024 · 74 citations)
   At long sequence lengths, attention's quadratic cost makes it the dominant source of latency in transformers.

All works

4 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. Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object DetectionarXiv:2303.05499Shilong Liu, Zhaoyang Zeng, Tianhe Ren, et al.2023 · 472 citations
2. CodeS: Towards Building Open-source Language Models for Text-to-SQLarXiv:2402.16347Haoyang Li, Jing Zhang, Hanbing Liu, et al.2024 · 190 citations
3. SageAttention: Accurate 8-Bit Attention for Plug-and-play Inference AccelerationInternational Conference on Learning Representations (ICLR)Jintao Zhang, Jia Wei, Haofeng Huang, et al.2024 · 74 citations
4. DiffusionNFT: Online Diffusion Reinforcement with Forward Process ↗arXiv (Cornell University) · no summary yetKaiwen Zheng et al.2025 · 26 citations

🤝 Co-authors here

12 of 15 co-authors with a page, the most papers together first.

• Chunyuan Li
• Cuiping Li
• Feng Li
• Hanbing Liu
• Hang Su
• Hao Zhang
• Haofeng Huang
• Haoyang Li
• Hong Chen
• Jianwei Yang
• Jie Yang
• Jing Zhang

Venues

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

• International Conference on Learning Representations (ICLR): ICLR 2024

🔗 Cited by

Papers of our library cite their works 383 times (of the 149,439 papers whose bibliographies we read); 57 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/jun-zhu/