🧑‍🔬 Hui Xue

🏛️ Affiliations

🏢Alibaba GroupHangzhou · China2026 · 3 paperscurrent

From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine.

🧭 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. Safe-SAIL: Towards a Fine-grained Safety Landscape of Large Language Models via Sparse Autoencoder Interpretation Framework (2026 · 2 citations)
   Sparse autoencoders (SAEs) can split a model's tangled activations into interpretable features. However, safety concepts are rare in typical data, and it is unclear which SAE setups produce fine-grained safety features. Explaining every feature is also expensive. Safe-SAIL is a three-stage pipeline (SAE training…
2. Seeing but Not Thinking: Routing Distraction in Multimodal Mixture-of-Experts (2026 · 1 citation)
   The paper examines a failure mode in multimodal Mixture-of-Experts (MoE) vision-language models. The authors call it "Seeing but Not Thinking": a model reads an image-rendered problem correctly but then reasons wrongly, even though it solves the same problem when given as text. Using image-rendered versions of…
3. Why Steering Works: Toward a Unified View of Language Model Parameter Dynamics (2026 · 1 citation)
   Methods for controlling LLM behaviour are usually studied separately, with different assumptions and evaluation setups.

All works

5 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. Safe-SAIL: Towards a Fine-grained Safety Landscape of Large Language Models via Sparse Autoencoder Interpretation FrameworkFindings of the Association for Computational LinguisticsJiaqi Weng, Han Zheng, Hanyu Zhang, et al.2026 · 2 citations
2. Seeing but Not Thinking: Routing Distraction in Multimodal Mixture-of-ExpertsAnnual Meeting of the Association for Computational Linguistics (ACL)Haolei Xu, Haiwen Hong, Hongxing Li, et al.2026 · 1 citation
3. Why Steering Works: Toward a Unified View of Language Model Parameter DynamicsAnnual Meeting of the Association for Computational Linguistics (ACL)Ziwen Xu, Chenyan WU, Hengyu Sun, et al.2026 · 1 citation
4. How Controllable Are Large Language Models? A Unified Evaluation across Behavioral Granularities ↗Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · no summary yetZiwen Xu et al.2026
5. LASA: Language-Agnostic Semantic Alignment at the Semantic Bottleneck for LLM Safety ↗Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · no summary yetJunxiao Yang et al.2026

🤝 Co-authors here

12 of 14 co-authors with a page, the most papers together first.

• Haiwen Hong ×2
• Longtao Huang ×2
• Zhixuan Chu ×2
• Huajun Chen
• Mengru Wang
• Ningyu Zhang
• Shumin Deng
• Weiming Lu
• Xiting Wang
• Yang Zhang
• Yongliang Shen
• Yueting Zhuang

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) ×4: ACL 2026 ×2
• Findings of the Association for Computational Linguistics: Findings of the Association for Computational Linguistics 2026

🔗 Cited by

Papers of our library cite their works 3 times (of the 149,439 papers whose bibliographies we read); 2 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/hui-xue/