BabyLM Challenge

AI & ML interests

Pretraining data constrained and cognitively relevant baby LLMs

Recent Activity

LinyangHe  authored a paper 5 days ago

XCOMPS: A Multilingual Benchmark of Conceptual Minimal Pairs

LinyangHe  authored a paper 5 days ago

AVMeme Exam: A Multimodal Multilingual Multicultural Benchmark for LLMs' Contextual and Cultural Knowledge and Thinking

LinyangHe  authored a paper 5 days ago

SightSound-R1: Cross-Modal Reasoning Distillation from Vision to Audio Language Models

View all activity

Papers

BabyBabelLM: A Multilingual Benchmark of Developmentally Plausible Training Data

View all Papers

Team members 29