🧑‍🔬 Shu-Tao Xia

🏛️ Affiliations

🎓Tsinghua UniversityBeijing · China2005–2026 · 456 paperscurrent🎓Tsinghua Shenzhen International Graduate SchoolShenzhen · China2006–2026 · 347 paperscurrent🔬Peng Cheng LaboratoryShenzhen · China2019–2026 · 166 paperscurrent🔬Tsinghua–Berkeley Shenzhen InstituteShenzhen · China2017–2026 · 3 paperscurrent🎓Harbin Institute of TechnologyHarbin · China2026 · 1 papercurrent🎓Southeast UniversityNanjing · China2007–2013 · 6 papers🎓Nankai UniversityTianjin · China1997–2002 · 4 papers🎓Hubei UniversityWuhan · China2020–2022 · 3 papers🔬State Key Laboratory of Biocatalysis and Enzyme EngineeringWuhan · China2020–2022 · 3 papers🎓Naval Aeronautical and Astronautical UniversityYantai · China2025 · 2 papers

From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. 10 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. Benchmarking Open-ended Audio Dialogue Understanding for Large Audio-Language Models (2025 · 12 citations)
   Large Audio-Language Models (LALMs) such as GPT-4o can now hold spoken conversations directly with users. Until this work, however, no benchmark tested how well they understand open-ended audio dialogue. Earlier evaluations covered basic audio tasks, audio QA driven by text instructions, or general-purpose chat only.
2. C-ReD: A Comprehensive Chinese Benchmark for AI-Generated Text Detection Derived from Real-World Prompts (2026)
   Most existing benchmarks for detecting machine-written text are built on English. The few that cover Chinese tend to rely on ChatGPT alone, use mostly QA-style texts, and pair them with artificial prompts. C-ReD addresses these gaps with a Chinese benchmark.
3. Infinite Babble: Inflating 3D Vision-Language Model Inference Overhead via Adversarial Geometric Perturbation (2026)
   The paper examines a resource-exhaustion threat to 3D Vision-Language Models (3D-VLMs). These models decode text autoregressively and often take in untrusted 3D assets downloaded from the internet. The authors present Inflate3D, which they describe as the first attack of this type that works only in the point cloud…
4. When Efficiency Meets Safety: A Benchmark Security Analysis of KV Cache Compression in Large Language Models (2026)
   KV cache compression is now common in LLM serving because it saves memory and time, but its effect on safety alignment has received little attention.

All works

9 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. Second-Order Attention Network for Single Image Super-Resolution ↗IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · no summary yetTao Dai et al.2019 · 1,915 citations
2. TokenPose: Learning Keypoint Tokens for Human Pose Estimation ↗IEEE/CVF International Conference on Computer Vision (ICCV) · no summary yetYanjie Li et al.2021 · 425 citations
3. Adversarial Weight Perturbation Helps Robust Generalization ↗neural information processing systems · no summary yetDongxian Wu, Shu‐Tao Xia, Yisen Wang2020 · 225 citations
4. Unsupervised Surface Anomaly Detection with Diffusion Probabilistic Model ↗IEEE/CVF International Conference on Computer Vision (ICCV) · no summary yetXinyi Zhang et al.2023 · 134 citations
5. Hilbert-Based Generative Defense for Adversarial Examples ↗IEEE/CVF International Conference on Computer Vision (ICCV) · no summary yetYang Bai et al.2019 · 52 citations
6. Benchmarking Open-ended Audio Dialogue Understanding for Large Audio-Language ModelsAnnual Meeting of the Association for Computational Linguistics (ACL)Kuofeng Gao, Shu-Tao Xia, Ke Xu, et al.2025 · 12 citations
7. C-ReD: A Comprehensive Chinese Benchmark for AI-Generated Text Detection Derived from Real-World PromptsFindings of the Association for Computational LinguisticsChenxi Qing, Junxi Wu, Zheng Liu, et al.2026
8. Infinite Babble: Inflating 3D Vision-Language Model Inference Overhead via Adversarial Geometric PerturbationFindings of the Association for Computational LinguisticsShuoyang Sun, Jiaxin Hong, Yv Zhang, et al.2026
9. When Efficiency Meets Safety: A Benchmark Security Analysis of KV Cache Compression in Large Language ModelsAnnual Meeting of the Association for Computational Linguistics (ACL)Xiaoxiao Ma, Kuofeng Gao, Zeyi Lu, et al.2026

🤝 Co-authors here

9 co-authors with a page, the most papers together first.

• Bin Chen ×3
• Kuofeng Gao ×3
• Hao Fang ×2
• Hao Wu ×2
• Jindong Gu
• Ke Xu
• Philip H. S. Torr
• Xiaoxiao Ma
• Zheng Liu

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) ×3
• Annual Meeting of the Association for Computational Linguistics (ACL) ×2: ACL 2026, ACL 2025
• Findings of the Association for Computational Linguistics ×2: Findings of the Association for Computational Linguistics 2026 ×2
• IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings
• neural information processing systems

🔗 Cited by

Papers of our library cite their works 51 times (of the 149,439 papers whose bibliographies we read); 4 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/shu-tao-xia/