🧑‍🔬 Zhaoxiang Zhang

🏛️ Affiliations

🔬Institute of AutomationBeijing · China2004–2026 · 177 papersEducation 2004–2009 · Ph.D, Pattern Recognition and Intelligent SystemsEmployment since 2015 · Professor & Principal Investigator & Executive Deputy Director, New Laboratory of Pattern Recognitioncurrent🏛️Chinese Academy of SciencesBeijing · China2007–2026 · 172 paperscurrent🎓University of Chinese Academy of SciencesBeijing · China2016–2026 · 116 papersEmployment since 2016 · Professor, School of Artificial Intelligencecurrent🎓Beihang UniversityBeijing · China2009–2015 · 64 papersEmployment 2009–2015 · Vice Director, Associate Professor, Lecturer at Department of Computer Application Science🎓Center for Excellence in Brain Science and Intelligence TechnologyShanghai · China2016–2023 · 30 papers🔬Centre for Artificial Intelligence and RoboticsBengaluru · India2021–2023 · 15 papers🎓Northwestern Polytechnical UniversityXi'an · China2024–2025 · 13 papers🔬State Key Laboratory of Virtual Reality Technology and SystemsBeijing2012–2015 · 12 papers🎓University of Science and Technology of ChinaHefei · China2000–2004Education 2000–2004 · B.Sc., Electronic Science and Technology

From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. 19 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. RoleLLM: Benchmarking, Eliciting, and Enhancing Role-Playing Abilities of Large Language Models (2023 · 187 citations)
   Open-source LLMs are trained for general use and are weak at imitating specific fictional characters. Strong closed models such as GPT-4 can do this, but they are costly, cannot be fine-tuned, and need all character details placed in the prompt. RoleLLM addresses this with a four-stage pipeline. First, the authors…
2. Can Large Language Models Detect Errors in Long Chain-of-Thought Reasoning? (2025 · 30 citations)
   Reasoning models in the o1 style produce very long chains of thought (CoT). Until this paper, there was no systematic way to check how good those chains are, or whether other models can find the mistakes in them. The authors built DeltaBench to address both gaps. It contains 1,236 problems from Math, Programming, PCB…
3. Activation Steering Decoding: Mitigating Hallucination in Large Vision-Language Models through Bidirectional Hidden State Intervention (2025 · 12 citations)
   Large Vision-Language Models (LVLMs) often hallucinate, describing things that do not appear in the input image.

All works

14 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. Scale-Aware Trident Networks for Object Detection ↗IEEE/CVF International Conference on Computer Vision (ICCV) · no summary yetYanghao Li et al.2019 · 1,103 citations
2. The Devil Is in the Details: Window-based Attention for Image Compression ↗IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · no summary yetRenjie Zou, Chunfeng Song, Zhaoxiang Zhang2022 · 305 citations
3. Sequence Level Semantics Aggregation for Video Object Detection ↗IEEE/CVF International Conference on Computer Vision (ICCV) · no summary yetHaiping Wu et al.2019 · 283 citations
4. GIFT: A Real-time and Scalable 3D Shape Search Engine ↗arXiv:1604.01879 · no summary yetSong Bai et al.2016 · 279 citations
5. RangeDet: In Defense of Range View for LiDAR-based 3D Object Detection ↗IEEE/CVF International Conference on Computer Vision (ICCV) · no summary yetLue Fan et al.2021 · 265 citations
6. Sparse Instance Activation for Real-Time Instance Segmentation ↗IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · no summary yetTianheng Cheng et al.2022 · 214 citations
7. CIAN: Cross-Image Affinity Net for Weakly Supervised Semantic Segmentation ↗Proceedings of the AAAI Conference on Artificial Intelligence · no summary yetJunsong Fan et al.2018 · 214 citations
8. RoleLLM: Benchmarking, Eliciting, and Enhancing Role-Playing Abilities of Large Language ModelsarXiv:2310.00746Zekun Moore Wang, Zhongyuan Peng, Haoran Que, et al.2023 · 187 citations
9. Clothing Status Awareness for Long-Term Person Re-Identification ↗IEEE/CVF International Conference on Computer Vision (ICCV) · no summary yetYan Huang et al.2021 · 129 citations
10. Uncertainty-aware Pseudo Label Refinery for Domain Adaptive Semantic Segmentation ↗IEEE/CVF International Conference on Computer Vision (ICCV) · no summary yetYuxi Wang, Junran Peng, Zhaoxiang Zhang2021 · 102 citations
11. SuperGPQA: Scaling LLM Evaluation across 285 Graduate Disciplines ↗arXiv:2502.14739 · no summary yetM-A-P Team et al.2025 · 89 citations
12. Attention-Aware Sampling via Deep Reinforcement Learning for Action Recognition ↗Proceedings of the AAAI Conference on Artificial Intelligence · no summary yetWenkai Dong, Zhaoxiang Zhang, Tieniu Tan2019 · 53 citations
13. Can Large Language Models Detect Errors in Long Chain-of-Thought Reasoning?Annual Meeting of the Association for Computational Linguistics (ACL)Yancheng He, Shilong Li, Jiaheng Liu, et al.2025 · 30 citations
14. Activation Steering Decoding: Mitigating Hallucination in Large Vision-Language Models through Bidirectional Hidden State InterventionAnnual Meeting of the Association for Computational Linguistics (ACL)Jingran Su, Jingfan Chen, Hongxin Li, et al.2025 · 12 citations

🤝 Co-authors here

12 of 16 co-authors with a page, the most papers together first.

• Jiaheng Liu ×2
• Zhongyuan Peng ×2
• Bo Zheng
• Ge Zhang
• Haoran Que
• Jian Yang
• Li Qing
• Man Zhang
• Shilong Li
• Wangchunshu Zhou
• Weixun Wang
• Wenbo Su

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
• Annual Meeting of the Association for Computational Linguistics (ACL) ×4: ACL 2025 ×2
• IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings ×2
• Proceedings of the AAAI Conference on Artificial Intelligence ×2
• Conference on Neural Information Processing Systems (NeurIPS)

🔗 Cited by

Papers of our library cite their works 452 times (of the 149,439 papers whose bibliographies we read); 117 citing papers with a page here →.

Updated 31 October 2026

↑ back to top

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