Ludwig Schmidt
Stanford / Anthropic researcher known for LAION, OpenCLIP, DataComp, and core empirical work on robustness and data curation for foundation models.
- Role
- professor
- Currently at
- Stanford University
- twitter.com/lschmidt3
- GitHub
- github.com/ludwigschmidt
- Scholar
- scholar.google.com/citations
- Papers
- 30
Cite
Notes
Only stored in your browser.
Authored papers
30Terminal-Bench: Benchmarking Agents on Hard, Realistic Tasks in Command Line Interfaces
arXiv 2026
V-GRPO: Online Reinforcement Learning for Denoising Generative Models Is Easier than You Think
arXiv 2026
NitroGen: An Open Foundation Model for Generalist Gaming Agents
arXiv 2026
OpenThoughts: Data Recipes for Reasoning Models
arXiv 2025
SWE-smith: Scaling Data for Software Engineering Agents
arXiv 2025
Project Alexandria: Towards Freeing Scientific Knowledge from Copyright Burdens via LLMs
arXiv 2025
Automated Generation of Challenging Multiple-Choice Questions for Vision Language Model Evaluation
CVPR 2025 1
MINT-1T: Scaling Open-Source Multimodal Data by 10x: A Multimodal Dataset with One Trillion Tokens
arXiv 2024
Why are Visually-Grounded Language Models Bad at Image Classification?
arXiv 2024
Getting it Right: Improving Spatial Consistency in Text-to-Image Models
arXiv 2024
Language models scale reliably with over-training and on downstream tasks
arXiv 2024
Large Scale Transfer Learning for Tabular Data via Language Modeling
arXiv 2024
Resolving Discrepancies in Compute-Optimal Scaling of Language Models
arXiv 2024
Stable and low-precision training for large-scale vision-language models
NeurIPS 2023 11
DataComp: In search of the next generation of multimodal datasets
NeurIPS 2023 11
GenEval: An Object-Focused Framework for Evaluating Text-to-Image Alignment
NeurIPS 2023 11
OpenFlamingo: An Open-Source Framework for Training Large Autoregressive Vision-Language Models
arXiv 2023
Multimodal C4: An Open, Billion-scale Corpus of Images Interleaved with Text
multimodal-c4-an-open-billion-scale-corpus-of
VisIT-Bench: A Benchmark for Vision-Language Instruction Following Inspired by Real-World Use
arXiv 2023
Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models
TMLR
Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time
arXiv 2022
CoWs on Pasture: Baselines and Benchmarks for Language-Driven Zero-Shot Object Navigation
CVPR 2023 1
Editing Models with Task Arithmetic
arXiv 2022
Measuring and Narrowing the Compositionality Gap in Language Models
arXiv 2022
Reproducible scaling laws for contrastive language-image learning
CVPR 2023 1
Quality Not Quantity: On the Interaction between Dataset Design and Robustness of CLIP
arXiv 2022
Robust fine-tuning of zero-shot models
robust-fine-tuning-of-zero-shot-models-1
Retiring Adult: New Datasets for Fair Machine Learning
NeurIPS 2021 12
Do ImageNet Classifiers Generalize to ImageNet?
NeurIPS Workshop ImageNet_PPF 2021 12
Towards Deep Learning Models Resistant to Adversarial Attacks
towards-deep-learning-models-resistant-to-1
Tool contributions
1Affiliations
Frequent co-authors
10from 30 papers
Mitchell Wortsman
Gabriel Ilharco
Jenia Jitsev
Ali Farhadi
CEO
Anas Awadalla
Hannaneh Hajishirzi
professor
Samir Yitzhak Gadre
Yejin Choi
professor
Dhruba Ghosh
Niklas Muennighoff
grad-student