Song Duong

About Me

I am a final year Ph.D. student at Criteo and CNRS-ISIR, Sorbonne University, under the supervision of Patrick Gallinari and Alberto Lumbreras. I will be finishing my PhD thesis in July 2025 and will be on the job market, looking for research opportunities in industry.

My PhD research revolves around the design of models that can generate text from structured data, such as tables or knowledge graphs. Lately, I have worked on the development of efficient architectures. I currently work on LLMs and their applications to various NLP tasks.

Research Interests

• Natural Language Processing: large language models, efficient architectures, data-to-text generation.

News

• [Jan. 2025] Our new paper ‘SCOPE’ is accepted at ICLR 2025.
• [Mar. 2024] Our paper ‘LOCOST’ is honored with the Best Paper Award.
• [Feb. 2024] Our paper ‘LOCOST’ is accepted and selected for an oral presentation at EACL 2024.
• [July. 2023] Attending virtually the OxML 2023 summer school.
• [Feb. 2023] Our paper on learning from multiple sources is accepted at AISTATS 2023.
• [Jan. 2023] Attending virtually the ALPS 2023 winter school.

Publications

Services

Conference Reviewers

• 13th International Conference on Learning Representations (ICLR) 2025
• 12th International Conference on Learning Representations (ICLR) 2024
• 37th Annual Conference on Neural Information Processing Systems (NeurIPS) 2023

Powered by Jekyll and Minimal Light theme.