Publications
BabyBabelLM: A Multilingual Benchmark of Developmentally Plausible Training Data
EACL 2026 — Main Conference (Rabat, Morocco) J Jumelet, … S Salhan, … A Warstadt, L Choshen
MultilingualBabyLM
Teacher Demonstrations in a BabyLM's Zone of Proximal Development for Contingent Multi-Turn Interaction
🏆 Outstanding Paper Award · BabyLM Workshop, EMNLP 2025 (Suzhou, China) S Salhan, H Gu, D Rooein, D Galvan-Sosa, G Gaudeau, A Caines, Z Yuan, P Buttery
AwardBabyLMInteraction
Looking to Learn: Token-wise Dynamic Gating for Low-Resource Vision-Language Modelling
🏆 Outstanding Paper Award · BabyLM Workshop, EMNLP 2025 (Suzhou, China) B-M Ganescu, S Salhan, A Caines, P Buttery
AwardMultimodalBabyLM
Pico: A Modular Framework for Hypothesis-Driven Small Language Model Research
EMNLP 2025 — Systems Demonstrations (Suzhou, China) RD Martinez, DD Africa, Y Weiss, S Salhan, R Daniels, P Buttery
Small Language ModelFramework
Meta-Pretraining for Zero-Shot Cross-Lingual Named Entity Recognition in Low-Resource Philippine Languages
MRL Workshop, EMNLP 2025 (Suzhou, China) DD Africa, S Salhan, Y Weiss, P Buttery, RD Martinez
Multilingual
ByteSpan: Information-Driven Subword Tokenisation
ICML Tokenization Workshop (TokShop), ICML 2025 (Vancouver, Canada) Z Goriely, S Salhan, P Lesci, J Cheng, P Buttery
Tokenization
The Distribution of Phonemes across Languages: Chance, costs, and integration across linguistic tiers
The 13th International Conference on the Mental Lexicon (Montréal, Québec, Canada) F Moscoso del Prado Martín, S Salhan
Linguistics
Measuring Grammatical Diversity from Small Corpora: Derivational Entropy Rates, Mean Length of Utterances, and Annotation Invariance
ACL 2025 (Vienna, Austria) – Main Conference, CL Journal F Moscoso del Prado Martín, S Salhan
Linguistics
Less is More: Pre-Training Cross-Lingual Small-Scale Language Models with Cognitively-Plausible Curriculum Learning Strategies
BabyLM Workshop, CoNLL 2024, EMNLP (Miami, FL, USA) S Salhan, RD Martinez, Z Goriely, P Buttery
BabyLMMultilingual