Vaishaal Shankar

OpenThoughts: Data Recipes for Reasoning Models

arXiv 2025

Language models scale reliably with over-training and on downstream tasks

arXiv 2024

Dataset Decomposition: Faster LLM Training with Variable Sequence Length Curriculum

arXiv 2024

DataComp: In search of the next generation of multimodal datasets

NeurIPS 2023 11

TiC-CLIP: Continual Training of CLIP Models

arXiv 2023

Do ImageNet Classifiers Generalize to ImageNet?

NeurIPS Workshop ImageNet_PPF 2021 12

Ludwig Schmidt

professor

Georgios Smyrnis

grad-student

Jenia Jitsev

Achal Dave

Alex Fang

Alexandros G. Dimakis

Gabriel Ilharco

Hadi Pouransari

Jean Mercat

researcher

Jeffrey Li