Grégoire Dhimoïla — accepted AI-conference papers

2026

Cross-Modal Redundancy and the Geometry of Vision–Language Embeddings

Grégoire DHIMOÏLA, Thomas Fel, Victor Boutin, Agustin Martin Picard

ICLR 2026poster

Vision–language models (VLMs) align images and text with remarkable success, yet the geometry of their shared embedding space remains poorly understood. To probe this geometry, we begin from the Iso-Energy Assumption, which exploits cross-modal redundancy: a concept that is truly shared should exhi…

Cited by 0 Source ↗Scholar ↗

2024

Cluster-Norm for Unsupervised Probing of Knowledge

Walter Laurito, Sharan Maiya, Grégoire Dhimoïla, Owen Ho Wan Yeung, Kaarel Hänni

EMNLP 2024main

The deployment of language models brings challenges in generating reliable text, especially when these models are fine-tuned with human preferences. To extract the encoded knowledge in these models without (potentially) biased human labels, unsupervised probing techniques like Contrast-Consistent Se…

Cited by 2 Source ↗PDF ↗code ↗Scholar ↗