Johan Obando-Ceron

Grounding Computer Use Agents on Human Demonstrations

arXiv 2025

Adaptive Computation Pruning for the Forgetting Transformer

arXiv 2025

Kaleidoscope: In-language Exams for Massively Multilingual Vision Evaluation

arXiv 2025

Mixtures of Experts Unlock Parameter Scaling for Deep RL

arXiv 2024

All Languages Matter: Evaluating LMMs on Culturally Diverse 100 Languages

CVPR 2025 1

Bigger, Better, Faster: Human-level Atari with human-level efficiency

arXiv 2023

Aaron Courville

Fabian Farestam

Mike Zhang

Pablo Samuel Castro

Aarash Feizi

Abdelrahman M Shaker

Abduragim Shtanchaev

Adriana Romero-Soriano

Ahmed Ruby

Alfonso Amayuelas