CV

Education

• Ph.D in Computer Science, The University of Manchester, 2023-2026 (expected)
• MSc in Integrated Machine Learning Systems, University College London, 2019-2020. Dissertation: Understanding the Latent Space in Variational Autoenocders, Supervised by: Ehsan Shareghi
• BEng in Information Engineering, Southeast University, 2014-2018

Work experience

• Jun 2022-Jul 2023: Deep Learning Researcher
  • Cambricon Technology
  • Duties included: Car detection; Traffic light detection; Traffic lane detection; Parking slot detection; Distillation on detection models.
• Apr 2021-Aug 2021: Intern of Algorithm (NLP)
  • Beijing Sensedeal
  • Duties included: build a model for event extraction by machine reading comprehension; build a model for triplet extraction; build baseline model for coreference resolution.

Awards

Best Resource Paper Award, EMNLP 2025

Publications

Autoformalization in the Wild: Assessing LLMs on Real-World Mathematical Definitions

Lan Zhang, Marco Valentino, and Andre Freitas. 2025. Autoformalization in the Wild: Assessing LLMs on Real-World Mathematical Definitions. In Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, pages 1720–1738, Suzhou, China. Association for Computational Linguistics.

MASA: LLM-Driven Multi-Agent Systems for Autoformalization

Lan Zhang, Marco Valentino, and Andre Freitas. 2025. MASA: LLM-Driven Multi-Agent Systems for Autoformalization. In Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing: System Demonstrations, pages 615–624, Suzhou, China. Association for Computational Linguistics.

Consistent Autoformalization for Constructing Mathematical Libraries

Lan Zhang, Xin Quan, and Andre Freitas. 2024. Consistent Autoformalization for Constructing Mathematical Libraries. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pages 4020–4033, Miami, Florida, USA. Association for Computational Linguistics.

Multi-Operational Mathematical Derivations in Latent Space

Marco Valentino, Jordan Meadows, Lan Zhang, and Andre Freitas. 2024. Multi-Operational Mathematical Derivations in Latent Space. In Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers), pages 1446–1458, Mexico City, Mexico. Association for Computational Linguistics.

On the Effect of Isotropy on VAE Representations of Text

Lan Zhang, Wray Buntine, and Ehsan Shareghi. 2022. On the Effect of Isotropy on VAE Representations of Text. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), pages 694–701, Dublin, Ireland. Association for Computational Linguistics.

Unsupervised Representation Disentanglement of Text: An Evaluation on Synthetic Datasets

Lan Zhang, Victor Prokhorov, and Ehsan Shareghi. 2021. Unsupervised Representation Disentanglement of Text: An Evaluation on Synthetic Datasets. In Proceedings of the 6th Workshop on Representation Learning for NLP (RepL4NLP-2021), pages 128–140, Online. Association for Computational Linguistics.