🧑‍🔬 Ziyu Yao

🏛️ Affiliations

🎓George Mason UniversityFairfax · United States2021–2026 · 36 papersEmploymentcurrent🎓The Ohio State UniversityColumbus · United States2018–2021 · 9 papers🎓Peking UniversityBeijing · China2023–2025 · 3 papers🎓Massachusetts Institute of TechnologyCambridge · United States2023 · 2 papers🎓Pennsylvania State UniversityState College · United States2022 · 2 papers

From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. 7 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. Can Large Language Models be Good Path Planners? A Benchmark and Investigation on Spatial-temporal Reasoning (2023 · 21 citations)
   The paper asks whether LLMs can handle tasks that combine spatial understanding with long-horizon planning.
2. Feature Extraction and Steering for Enhanced Chain-of-Thought Reasoning in Language Models (2025 · 11 citations)
   Long chain-of-thought reasoning, as in DeepSeek-R1, improves LLM performance on hard problems. Obtaining it usually requires distillation or post-training on expensive long-CoT data. The authors instead strengthen reasoning at inference time by steering residual activations, using only ordinary (vanilla) CoT.
3. All for One: LLMs Solve Mental Math at the Last Token With Information Transferred From Other Tokens (2025 · 6 citations)
   The paper asks how much of a transformer's theoretical capacity for cross-token communication LLMs actually use when they do "mental math": one-token answers to two- or three-operand arithmetic, with no chain-of-thought.

All works

7 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. Model-based Interactive Semantic Parsing: A Unified Framework and A Text-to-SQL Case Study ↗Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP) · no summary yetZiyu Yao et al.2019 · 96 citations
2. A Practical Review of Mechanistic Interpretability for Transformer-Based Language Models ↗arXiv:2407.02646 · no summary yetDaking Rai et al.2024 · 58 citations
3. Can Large Language Models be Good Path Planners? A Benchmark and Investigation on Spatial-temporal ReasoningarXiv:2310.03249Mohamed Aghzal, Erion Plaku, Ziyu Yao2023 · 21 citations
4. Learning Structural Edits via Incremental Tree Transformations ↗arXiv (Cornell University) · no summary yetZiyu Yao et al.2021 · 16 citations
5. Gentopia: A Collaborative Platform for Tool-Augmented LLMs ↗arXiv:2308.04030 · no summary yetBinfeng Xu et al.2023 · 15 citations
6. Feature Extraction and Steering for Enhanced Chain-of-Thought Reasoning in Language ModelsConference on Empirical Methods in Natural Language Processing (EMNLP)Zihao Li, Xu Wang, Yuzhe Yang, et al.2025 · 11 citations
7. All for One: LLMs Solve Mental Math at the Last Token With Information Transferred From Other TokensConference on Empirical Methods in Natural Language Processing (EMNLP)Siddarth Mamidanna, Daking Rai, Ziyu Yao, et al.2025 · 6 citations

🤝 Co-authors here

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

• Mengnan Du
• Xu Wang
• Yilun Zhou
• Zihao Li

Venues

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

• Conference on Empirical Methods in Natural Language Processing (EMNLP) ×3: EMNLP 2025 ×2
• Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)

🔗 Cited by

Papers of our library cite their works 304 times (of the 149,439 papers whose bibliographies we read); 51 citing papers with a page here →.

Updated 30 October 2026

↑ back to top

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