Home

I am a Maître de Conférences (~associate professor) at INSA Rennes. I conduct my research in the Linkmedia team of Irisa.

My research focuses on Natural Language Processing and Machine Learning. My work can be summed up as the development of novel (combinatorial) algorithms and novel learning methods for structured prediction. Lately, I've been increasingly interested in the use of machine learning for research in linguistics (or, in other words, AI for science).

Selected Works

Check the papers page for a complete list of publications.

KAD: A Framework for Proxy-based Test-time Alignment with Knapsack Approximation Deferral

Ayoub Hammal, Pierre Zweigenbaum, Caio Corro
EACL 2026 - European Chapter of the Association for Computational Linguistics
preprint - code

Bregman Conditional Random Fields: Sequence Labeling with Parallelizable Inference Algorithms

Caio Corro, Mathieu Lacroix, Joseph Le Roux
ACL 2025 - Annual Meeting of the Association for Computational Linguistics
paper - slides - code

A Fast and Sound Tagging Method for Discontinuous Named-Entity Recognition

Caio Corro
EMNLP 2024 - Conference on Empirical Methods in Natural Language Processing
paper - code

News

• (April, 2026) new paper accepted @ ACL 2026: On the Rejection Criterion for Proxy-based Test-time Alignment (Ayoub Hammal, Pierre Zweigenbaum, Caio Corro)

• (March, 2026) two new papers:

  • one accepted at LREC 2026: A Study on Building Efficient Zero-Shot Relation Extraction Models (Hugo Thomas, Caio Corro, Guillaume Gravier, Pascale Sébillot)

  • one preprint: Suffix-Constrained Greedy Search Algorithms for Causal Language Models (Ayoub Hammal, Pierre Zweigenbaum, Caio Corro)

• (February, 2026) new preprint: Fast and General Automatic Differentiation for Finite-State Methods (Lucas Ondel Yang, Tina Raissi, Martin Kocour, Pablo Riera, Caio Corro)

• (January, 2026) the bulletin of AFIA on PFIA 2025 is available on HAL

• (January, 2026) two papers accepted @ EACL 2026:

  • KAD: A Framework for Proxy-based Test-time Alignment with Knapsack Approximation Deferral (Ayoub Hammal, Pierre Zweigenbaum, Caio Corro)

  • DocPolarBERT: A Pre-trained Model for Document Understanding with Relative Polar Coordinate Encoding of Layout Structures (Benno Uthayasooriyar, Antoine Ly, Franck Vermet, Caio Corro )

Students and postdocs

Current:

• Vivien Nicolas, PhD student (jan. 2026 - …) co-supervised with Pascale Sébillot and Hicham Randrianarivo

• Ayoub Hammal, PhD student (oct. 2024 - …) co-supervised with Pierre Zweigenbaum and Miguel Couceiro

Former:

• Benno Uthayasooriyar, PhD student (sept. 2022 - 2025) co-supervised with Franck Vermet and Antoine Ly

• Lilas Pastre, master student (2025) co-supervised with Laurent Amsaleg

• Ayoub Hammal, Master intern (2024)

• Alban Petit, PhD student (oct. 2020 - feb. 2024), co-supervised with François Yvon

• Yara Khater, Master intern (2022 & 2023)

• Emile Chapuis, postdoc (jan. 2022 - dec. 2023) co-advised with Nadi Tomeh

• Lili Lu, Master intern (2022)

• Lynda Attouche, Undergrad intern (2021)

• Alban Petit, Master intern (2020), now PhD student

• Nicolas Devatine, Master intern (2020), now Phd student @ IRIT