Yinya Huang

Yinya Huang

Yinya Huang is a Postdoc Fellow at ETH AI Center, ETH Zürich, working with Prof. Mrinmaya Sachan and Prof. Elliot Ash. She received her Ph.D. Degree in Computer Science from Sun Yat-sen University, advised by Prof. Xiaodan Liang and Prof. Liang Lin. Her research focuses on models’ system 2 thinking, especially incorporating formal systems and methods into LLM methods for mathematical, logical, and causal reasoning. She is also interested in applicational scenarios such as industrial optimization problems and automated research assistants. She has published papers in TPAMI, ICLR, ACL, EMNLP, NAACL, AAAI, and so forth. She won the 2023 SAAI Outstanding Doctoral Dissertation Award and the 2024 ACM SIGCSE China Excellent Doctoral Dissertation Award. She serves as an area chair for ACL ARR, a program committee member for ICML, ICLR, NeurIPS, ACL, EMNLP, and AAAI, and a reviewer for TNNLS and JAIR. She is also the primary organizer for the ICML AI for Math Workshop Series (2024, 2025).

News

All Publications

(2025). FormalAlign: Automated Alignment Evaluation for Autoformalization. The Thirteenth International Conference on Learning Representations (ICLR 2025).

PDF Cite URL Code

(2024). FVEL: Interactive Formal Verification Environment with Large Language Models via Theorem Proving. The Thirty-eight Conference on Neural Information Processing Systems Datasets and Benchmarks Track (NeurIPS 2024 D&B Track).

PDF Cite URL Data Code

(2024). Proving Theorems Recursively. The Thirty-eighth Annual Conference on Neural Information Processing Systems (NeurIPS 2024).

PDF Cite URL Code

(2024). ATG: Benchmarking Automated Theorem Generation for Generative Language Models. 2024 Annual Conference of the North American Chapter of the Association for Computational Linguistics (NAACL 2024 Findings).

PDF Cite URL Data Leaderboard

(2024). AlignedCoT: Prompting Large Language Models via Native-Speaking Demonstrations. The 2024 Conference on Empirical Methods in Natural Language Processing (EMNLP 2024 Findings).

PDF Cite URL Code

(2023). TRIGO: Benchmarking Formal Mathematical Proof Reduction for Generative Language Models. Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing (EMNLP 2023), Sentosa, Singapore, December 6-10, 2023.

PDF Cite DOI URL Code

(2023). Discourse-Aware Graph Networks for Textual Logical Reasoning. IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI).

PDF Cite DOI URL

(2022). MetaLogic: Logical Reasoning Explanations with Fine-Grained Structure. Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing (EMNLP 2022), Abu Dhabi, United Arab Emirates, December 7-11, 2022.

PDF Cite DOI URL Code

(2022). REM-Net: Recursive Erasure Memory Network for Commonsense Evidence Refinement. Thirty-Fifth AAAI Conference on Artificial Intelligence (AAAI 2021), Virtual Event, February 2-9, 2021.

PDF Cite DOI URL Code

(2021). DAGN: Discourse-Aware Graph Network for Logical Reasoning. Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT 2021), Online, June 6-11, 2021.

PDF Cite DOI URL Code

Professional Service

Workshops:

Area Chair:

Program Committee Member:

  • ICML (2025)
  • ICLR (2025, 2024)
  • NeurIPS (2024, 2023)
  • ACL (2024, 2023)
  • EMNLP (2024, 2023, 2022)
  • NAACL (2024)
  • COLM (2024)
  • COLING (2020)
  • ACM MM (2024)
  • IJCAI (2024)
  • ICLR Workshop (2021)

Journal Reviewer:

Awards