collaborators

7 papers

cs.CR2026

TextSeal: A Localized LLM Watermark for Provenance & Distillation Protection

Tom Sander, Hongyan Chang, Tomáš Souček +10

We introduce TextSeal, a state-of-the-art watermark for large language models. Building on Gumbel-max sampling, TextSeal introduces dual-key generation to restore output diversity,…

cs.LG2026

EgoBabyVLM: Benchmarking Cross-Modal Learning from Naturalistic Egocentric Video Data

Dongyan Lin, Phillip Rust, Angel Villar Corrales +19

Children acquire language grounding with remarkable robustness from limited visuo-linguistic input in ways that surpass today's best large multimodal models. Recent research sugges…

cs.CL2026

Omnilingual MT: Machine Translation for 1,600 Languages

Omnilingual MT Team, Belen Alastruey, Niyati Bafna +29

High-quality machine translation (MT) can scale to hundreds of languages, setting a high bar for multilingual systems. However, compared to the world's 7,000 languages, current sys…

cs.CL2026

SpidR-Adapt: A Universal Speech Representation Model for Few-Shot Adaptation

Mahi Luthra, Jiayi Shen, Maxime Poli +14

Human infants, with only a few hundred hours of speech exposure, acquire basic units of new languages, highlighting a striking efficiency gap compared to the data-hungry self-super…

cs.CL2025

Omnilingual ASR: Open-Source Multilingual Speech Recognition for 1600+ Languages

Omnilingual ASR team, Gil Keren, Artyom Kozhevnikov +30

Automatic speech recognition (ASR) has advanced in high-resource languages, but most of the world's 7,000+ languages remain unsupported, leaving thousands of long-tail languages be…

cs.CL2025

LongTail-Swap: benchmarking language models' abilities on rare words

Robin Algayres, Charles-Éric Saint-James, Mahi Luthra +6

Children learn to speak with a low amount of data and can be taught new words on a few-shot basis, making them particularly data-efficient learners. The BabyLM challenge aims at ex…