Hugo Malard — accepted AI-conference papers

2026

Multiple Choice Learning of Low-Rank Adapters for Language Modeling

Victor Letzelter, Hugo Malard, Mathieu Fontaine, Gaël Richard, Slim Essid, Andrei Bursuc +1

ICML 2026poster

We propose LoRA-MCL, a training scheme that extends next-token prediction in language models with a method designed to decode diverse, plausible sentence continuations at inference time. Traditional language modeling is an intrinsically ill-posed problem: given a context, multiple ``futures'' may be…

Cited by 0 Source ↗Scholar ↗

2024

An eye for an ear: zero-shot audio description leveraging an image captioner with audio-visual token distribution matching

Hugo Malard, Michel Olvera, Stéphane Lathuilière, Slim Essid

NeurIPS 2024poster

Multimodal large language models have fueled progress in image captioning. These models, fine-tuned on vast image datasets, exhibit a deep understanding of semantic concepts. In this work, we show that this ability can be re-purposed for audio captioning, where the joint image-language decoder can b…

Cited by 1 Source ↗PDF ↗Scholar ↗