Personal profile
Research overview
I am a machine learning researcher with extensive experience in both academia and industry, specializing in natural language processing and machine learning. I am passionate about translating cutting-edge research into real-world applications, and I maintain a deep curiosity about fundamental scientific mysteries—particularly the emergence of human language.
See more https://lephong.github.io/
Research interests
natural language processing (large language models, syntactic and semantic parsing, information extraction, language and communication emergence); machine Learning (deep learning, reinforcement learning, weakly supervised learning); automated algorithm configuration
Profile Keywords
machine learning (deep learning, weakly supervised learning, reinforcement learning), natural language processing (LLM, language emergence), optimisation, evolutionary algorithms
Fingerprint
- 1 Similar Profiles
Collaborations and top research areas from the last five years
Research output
- 4 Conference contribution
-
An emergent communication framework for honeybee waggle dance
Siregar, N., Le, P. & G. Alhama, R., 2026, Proceedings of the 16th International Conference on the Evolution of Language (EVOLANG XVI). p. 435 8 p.Research output: Chapter in Book/Report/Conference proceeding › Conference contribution
-
Hierarchical Text Classification with LLM-Refined Taxonomies
Golde, J., Jedema, N., Krishnan, R. & Le, P., 2026, Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers). p. 214–228Research output: Chapter in Book/Report/Conference proceeding › Conference contribution
-
Multi-parameter control for the (1+(λ,λ))-GA on OneMax via deep reinforcement learning
Nguyen, T., Le, P., Doerr, C. & Dang, N., Aug 2025, Proceedings of the 18th ACM/SIGEVO Conference on Foundations of Genetic Algorithms. ACMResearch output: Chapter in Book/Report/Conference proceeding › Conference contribution
Open Access -
On the importance of reward design in reinforcement learning-based dynamic algorithm configuration: a case study on OneMax with (1+(λ,λ))-GA
Nguyen, T., Le, P., Biedenkapp, A., Doerr, C. & Dang, N., Jul 2025, Proceedings of the genetic and evolutionary computation conference 2025 (GECCO '25). New York: ACM, p. 1162 - 1171Research output: Chapter in Book/Report/Conference proceeding › Conference contribution