🧑‍🔬 Yang Xiao

🏛️ Affiliations

🎓Hong Kong Polytechnic UniversityHong Kong · 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. LIMO: Less is More for Reasoning (2025 · 209 citations)
   This paper challenges the common belief that LLMs need hundreds of thousands of supervised examples to learn mathematical reasoning.
2. Towards Dynamic Theory of Mind: Evaluating LLM Adaptation to Temporal Evolution of Human States (2025 · 8 citations)
   Most Theory of Mind (ToM) benchmarks for LLMs test mental states at a single moment. In real social interaction, however, people's beliefs, feelings and goals change over time. The authors address this gap with DynToM, a benchmark that checks whether models can follow how a character's mental state develops across a…
3. AgencyBench: Benchmarking the Frontiers of Autonomous Agents in 1M-Token Real-World Contexts (2026 · 4 citations)
   Most agent benchmarks test one skill, such as tool use, coding, or web research, through short interactions.
4. SepSeq: A Training-Free Framework for Long Numerical Sequence Processing in LLMs (2026 · 1 citation)
   Modern LLMs advertise very long context windows, yet they handle long sequences of numbers poorly. Tasks such as counting, filtering, or spotting trends need exact access to every value. The authors trace this failure to attention dispersion: as inputs grow, Softmax spreads attention over many similar numeric tokens…
5. Large-Scale Multimodal Knowledge Graph about Classical Chinese Poetry: Fine-grained Method and Comprehensive Evaluation (2026)
   Research on classical Chinese poetry has relied mostly on text. The only existing text-vision knowledge graph, PKG, covers imagery alone, includes no sound, and links to many web images that no longer exist. To fill this gap, the authors build CPMK, a multimodal knowledge graph that combines textual, visual and…
6. Privacy Risks of Intermediate Representations: Attribute Inference in Distributed LLM Inference (2026)
   Distributed LLM inference splits a model across several participants. They exchange hidden states rather than raw prompts, and this is widely treated as privacy-preserving. The authors test that belief. They ask whether a single honest-but-curious node can identify which sensitive attribute, such as a drug name or a…

All works

8 works of theirs in our library, the most cited first; 6 with a page here, the others link their original until we summarise them.

1. LIMO: Less is More for ReasoningarXiv:2502.03387Yixin Ye, Zhen Huang, Yang Xiao, et al.2025 · 209 citations
2. Towards Dynamic Theory of Mind: Evaluating LLM Adaptation to Temporal Evolution of Human StatesAnnual Meeting of the Association for Computational Linguistics (ACL)Yang Xiao, Jiashuo Wang, Qiancheng Xu, et al.2025 · 8 citations
3. AgencyBench: Benchmarking the Frontiers of Autonomous Agents in 1M-Token Real-World ContextsAnnual Meeting of the Association for Computational Linguistics (ACL)Keyu Li, Junhao Shi, Yang Xiao, et al.2026 · 4 citations
4. SepSeq: A Training-Free Framework for Long Numerical Sequence Processing in LLMsFindings of the Association for Computational LinguisticsJie Sun, Yu Liu, Lu Han, et al.2026 · 1 citation
5. Large-Scale Multimodal Knowledge Graph about Classical Chinese Poetry: Fine-grained Method and Comprehensive EvaluationFindings of the Association for Computational LinguisticsShuo Wang, Qing Zhu, Yang Xiao, et al.2026
6. Privacy Risks of Intermediate Representations: Attribute Inference in Distributed LLM InferenceFindings of the Association for Computational LinguisticsYang Lyu, Jin Cao, Yang Xiao, et al.2026
7. Adapting Where It Matters: Depth-Aware Adaptation for Efficient Multilingual Speech Recognition in Low-Resource Languages ↗Findings of the Association for Computational Linguistics: ACL 2026 · no summary yetYang Xiao, Eun-Jung Holden, Ting Dang2026
8. UNIVID: Unified Vision-Language Model for Video Moderation ↗Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 6: Industry Track) · no summary yetKejuan Yang et al.2026

🤝 Co-authors here

12 of 17 co-authors with a page, the most papers together first.

• Pengfei Liu ×3
• Jie Sun ×2
• Shijie Xia ×2
• Wenjie Li ×2
• Chunpu Xu
• Dayuan Fu
• Ethan Chern
• Hui LI
• Jun Zhou
• Qiancheng Xu
• Shuo Wang
• Weiye Si

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) ×3: ACL 2026, ACL 2025
• Findings of the Association for Computational Linguistics ×3: Findings of the Association for Computational Linguistics 2026 ×3
• Findings of the Association for Computational Linguistics: ACL 2026

🔗 Cited by

Papers of our library cite their works 217 times (of the 149,439 papers whose bibliographies we read); 62 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/yang-xiao/