@inproceedings{DBLP:conf/nips/GadreIFHSNMWGZO23,
author = {Samir Yitzhak Gadre and
Gabriel Ilharco and
Alex Fang and
Jonathan Hayase and
Georgios Smyrnis and
Thao Nguyen and
Ryan Marten and
Mitchell Wortsman and
Dhruba Ghosh and
Jieyu Zhang and
Eyal Orgad and
Rahim Entezari and
Giannis Daras and
Sarah M. Pratt and
Vivek Ramanujan and
Yonatan Bitton and
Kalyani Marathe and
Stephen Mussmann and
Richard Vencu and
Mehdi Cherti and
Ranjay Krishna and
Pang Wei Koh and
Olga Saukh and
Alexander J. Ratner and
Shuran Song and
Hannaneh Hajishirzi and
Ali Farhadi and
Romain Beaumont and
Sewoong Oh and
Alex Dimakis and
Jenia Jitsev and
Yair Carmon and
Vaishaal Shankar and
Ludwig Schmidt},
editor = {Alice Oh and
Tristan Naumann and
Amir Globerson and
Kate Saenko and
Moritz Hardt and
Sergey Levine},
title = {DataComp: In search of the next generation of multimodal datasets},
booktitle = {Advances in Neural Information Processing Systems 36: Annual Conference
on Neural Information Processing Systems 2023, NeurIPS 2023, New Orleans,
LA, USA, December 10 - 16, 2023},
year = {2023},
url = {http://papers.nips.cc/paper\_files/paper/2023/hash/56332d41d55ad7ad8024aac625881be7-Abstract-Datasets\_and\_Benchmarks.html},
timestamp = {Fri, 01 Mar 2024 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/nips/GadreIFHSNMWGZO23.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2304-14108,
author = {Samir Yitzhak Gadre and
Gabriel Ilharco and
Alex Fang and
Jonathan Hayase and
Georgios Smyrnis and
Thao Nguyen and
Ryan Marten and
Mitchell Wortsman and
Dhruba Ghosh and
Jieyu Zhang and
Eyal Orgad and
Rahim Entezari and
Giannis Daras and
Sarah M. Pratt and
Vivek Ramanujan and
Yonatan Bitton and
Kalyani Marathe and
Stephen Mussmann and
Richard Vencu and
Mehdi Cherti and
Ranjay Krishna and
Pang Wei Koh and
Olga Saukh and
Alexander Ratner and
Shuran Song and
Hannaneh Hajishirzi and
Ali Farhadi and
Romain Beaumont and
Sewoong Oh and
Alex Dimakis and
Jenia Jitsev and
Yair Carmon and
Vaishaal Shankar and
Ludwig Schmidt},
title = {DataComp: In search of the next generation of multimodal datasets},
journal = {CoRR},
volume = {abs/2304.14108},
year = {2023},
url = {https://doi.org/10.48550/arXiv.2304.14108},
doi = {10.48550/ARXIV.2304.14108},
eprinttype = {arXiv},
eprint = {2304.14108},
timestamp = {Wed, 03 May 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2304-14108.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nips/SchuhmannBVGWCC22,
author = {Christoph Schuhmann and
Romain Beaumont and
Richard Vencu and
Cade Gordon and
Ross Wightman and
Mehdi Cherti and
Theo Coombes and
Aarush Katta and
Clayton Mullis and
Mitchell Wortsman and
Patrick Schramowski and
Srivatsa Kundurthy and
Katherine Crowson and
Ludwig Schmidt and
Robert Kaczmarczyk and
Jenia Jitsev},
editor = {Sanmi Koyejo and
S. Mohamed and
A. Agarwal and
Danielle Belgrave and
K. Cho and
A. Oh},
title = {{LAION-5B:} An open large-scale dataset for training next generation
image-text models},
booktitle = {Advances in Neural Information Processing Systems 35: Annual Conference
on Neural Information Processing Systems 2022, NeurIPS 2022, New Orleans,
LA, USA, November 28 - December 9, 2022},
year = {2022},
url = {http://papers.nips.cc/paper\_files/paper/2022/hash/a1859debfb3b59d094f3504d5ebb6c25-Abstract-Datasets\_and\_Benchmarks.html},
timestamp = {Mon, 08 Jan 2024 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/nips/SchuhmannBVGWCC22.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2210-08402,
author = {Christoph Schuhmann and
Romain Beaumont and
Richard Vencu and
Cade Gordon and
Ross Wightman and
Mehdi Cherti and
Theo Coombes and
Aarush Katta and
Clayton Mullis and
Mitchell Wortsman and
Patrick Schramowski and
Srivatsa Kundurthy and
Katherine Crowson and
Ludwig Schmidt and
Robert Kaczmarczyk and
Jenia Jitsev},
title = {{LAION-5B:} An open large-scale dataset for training next generation
image-text models},
journal = {CoRR},
volume = {abs/2210.08402},
year = {2022},
url = {https://doi.org/10.48550/arXiv.2210.08402},
doi = {10.48550/ARXIV.2210.08402},
eprinttype = {arXiv},
eprint = {2210.08402},
timestamp = {Wed, 19 Oct 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2210-08402.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2111-02114,
author = {Christoph Schuhmann and
Richard Vencu and
Romain Beaumont and
Robert Kaczmarczyk and
Clayton Mullis and
Aarush Katta and
Theo Coombes and
Jenia Jitsev and
Aran Komatsuzaki},
title = {{LAION-400M:} Open Dataset of CLIP-Filtered 400 Million Image-Text
Pairs},
journal = {CoRR},
volume = {abs/2111.02114},
year = {2021},
url = {https://arxiv.org/abs/2111.02114},
eprinttype = {arXiv},
eprint = {2111.02114},
timestamp = {Fri, 05 Nov 2021 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2111-02114.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
