forked from ChiaXinLiang/MLLM-book
-
Notifications
You must be signed in to change notification settings - Fork 0
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
Merge pull request ChiaXinLiang#18 from Thetoicxdude/patch-4
chap8_ref.bib
- Loading branch information
Showing
1 changed file
with
62 additions
and
0 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,62 @@ | ||
@article{choromanski2021rethinking, | ||
title={Rethinking attention with performers}, | ||
author={Choromanski, Krzysztof and Likhosherstov, Valerii and Dohan, David and Song, Xingyou and Gane, Andreea and Sarlós, Tamás and Hawkins, Peter and Davis, Jared and Mohiuddin, Afroz and Kaiser, Łukasz and Belanger, David and Colwell, Lucy and Weller, Adrian}, | ||
journal={arXiv preprint arXiv:2009.14794}, | ||
year={2021} | ||
} | ||
|
||
@article{kim2021vilt, | ||
title={ViLT: Vision-and-Language Transformer Without Convolution or Region Supervision}, | ||
author={Kim, Wonjae and Son, Bokyung and Kim, Ildoo}, | ||
journal={arXiv preprint arXiv:2102.03334}, | ||
year={2021} | ||
} | ||
|
||
@article{beltagy2020longformer, | ||
title={Longformer: The long-document transformer}, | ||
author={Beltagy, Iz and Peters, Matthew E. and Cohan, Arman}, | ||
journal={arXiv preprint arXiv:2004.05150}, | ||
year={2020} | ||
} | ||
|
||
@article{radford2021learning, | ||
title={Learning Transferable Visual Models From Natural Language Supervision}, | ||
author={Radford, Alec and Kim, Jong Wook and Hallacy, Aditya and Ramesh, Aditya and Goh, Gabriel and Agarwal, Sandhini and Sastry, Girish and Askell, Amanda and Mishkin, Pamela and Clark, Jack and Krueger, Gretchen and Sutskever, Ilya}, | ||
journal={arXiv preprint arXiv:2103.00020}, | ||
year={2021} | ||
} | ||
|
||
@article{ramesh2021zero, | ||
title={Zero-Shot Text-to-Image Generation}, | ||
author={Ramesh, Aditya and Pavlov, Mikhail and Goh, Gabriel and Gray, Scott and Voss, Chelsea and Radford, Alec and Chen, Mark and Sutskever, Ilya}, | ||
journal={arXiv preprint arXiv:2102.12092}, | ||
year={2021} | ||
} | ||
|
||
@article{lu2022unified, | ||
title={Unified-IO: A Unified Model for Vision, Language, and Multi-Modal Tasks}, | ||
author={Lu, Jiasen and Batra, Dhruv and Yang, Jianwei and Parikh, Devi and Lee, Stefan}, | ||
journal={arXiv preprint arXiv:2206.10658}, | ||
year={2022} | ||
} | ||
|
||
@article{kaplan2020scaling, | ||
title={Scaling Laws for Neural Language Models}, | ||
author={Kaplan, Jared and McCandlish, Sam and Henighan, Tom and Brown, Tom and Chess, Benjamin and Child, Rewon and Gray, Scott and Radford, Alec and Wu, Jeffrey and Amodei, Dario}, | ||
journal={arXiv preprint arXiv:2001.08361}, | ||
year={2020} | ||
} | ||
|
||
@article{zhai2022scaling, | ||
title={Scaling Vision Transformers}, | ||
author={Zhai, Xiaohua and Kolesnikov, Alexander and Beyer, Lucas and Unterthiner, Thomas and Steiner, Andreas and Keysers, Daniel and Uszkoreit, Jakob and Houlsby, Neil and Dosovitskiy, Alexey and Heigold, Georg}, | ||
journal={arXiv preprint arXiv:2012.12877}, | ||
year={2022} | ||
} | ||
|
||
@article{bommasani2021opportunities, | ||
title={Opportunities and risks of foundation models}, | ||
author={Bommasani, Rishi and Hudson, Drew A and Adeli, Ehsan and Altman, Russ and Arora, Simran and von Arx, Sydney and Bernstein, Michael S and Bohg, Jeannette and Bosselut, Antoine and Brunskill, Emma and others}, | ||
journal={arXiv preprint arXiv:2108.07258}, | ||
year={2021} | ||
} |