default search action
Google
Google Scholar
Semantic Scholar
Internet Archive Scholar
CiteSeerX
ORCIDBibTeX records: William Fedus
@article{DBLP:journals/jmlr/ChungHLZTFL00BW24,
author = {Hyung Won Chung and
Le Hou and
Shayne Longpre and
Barret Zoph and
Yi Tay and
William Fedus and
Yunxuan Li and
Xuezhi Wang and
Mostafa Dehghani and
Siddhartha Brahma and
Albert Webson and
Shixiang Shane Gu and
Zhuyun Dai and
Mirac Suzgun and
Xinyun Chen and
Aakanksha Chowdhery and
Alex Castro{-}Ros and
Marie Pellat and
Kevin Robinson and
Dasha Valter and
Sharan Narang and
Gaurav Mishra and
Adams Yu and
Vincent Y. Zhao and
Yanping Huang and
Andrew M. Dai and
Hongkun Yu and
Slav Petrov and
Ed H. Chi and
Jeff Dean and
Jacob Devlin and
Adam Roberts and
Denny Zhou and
Quoc V. Le and
Jason Wei},
title = {Scaling Instruction-Finetuned Language Models},
journal = {J. Mach. Learn. Res.},
volume = {25},
pages = {70:1--70:53},
year = {2024},
url = {https://jmlr.org/papers/v25/23-0870.html},
timestamp = {Mon, 16 Sep 2024 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/jmlr/ChungHLZTFL00BW24.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/iclr/ShenHZ0LWCZFCVW24,
author = {Sheng Shen and
Le Hou and
Yanqi Zhou and
Nan Du and
Shayne Longpre and
Jason Wei and
Hyung Won Chung and
Barret Zoph and
William Fedus and
Xinyun Chen and
Tu Vu and
Yuexin Wu and
Wuyang Chen and
Albert Webson and
Yunxuan Li and
Vincent Y. Zhao and
Hongkun Yu and
Kurt Keutzer and
Trevor Darrell and
Denny Zhou},
title = {Mixture-of-Experts Meets Instruction Tuning: {A} Winning Combination
for Large Language Models},
booktitle = {The Twelfth International Conference on Learning Representations,
{ICLR} 2024, Vienna, Austria, May 7-11, 2024},
publisher = {OpenReview.net},
year = {2024},
url = {https://openreview.net/forum?id=6mLjDwYte5},
timestamp = {Wed, 07 Aug 2024 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/iclr/ShenHZ0LWCZFCVW24.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/jmlr/ChowdheryNDBMRBCSGSSTMRBTSPRDHPBAI23,
author = {Aakanksha Chowdhery and
Sharan Narang and
Jacob Devlin and
Maarten Bosma and
Gaurav Mishra and
Adam Roberts and
Paul Barham and
Hyung Won Chung and
Charles Sutton and
Sebastian Gehrmann and
Parker Schuh and
Kensen Shi and
Sasha Tsvyashchenko and
Joshua Maynez and
Abhishek Rao and
Parker Barnes and
Yi Tay and
Noam Shazeer and
Vinodkumar Prabhakaran and
Emily Reif and
Nan Du and
Ben Hutchinson and
Reiner Pope and
James Bradbury and
Jacob Austin and
Michael Isard and
Guy Gur{-}Ari and
Pengcheng Yin and
Toju Duke and
Anselm Levskaya and
Sanjay Ghemawat and
Sunipa Dev and
Henryk Michalewski and
Xavier Garcia and
Vedant Misra and
Kevin Robinson and
Liam Fedus and
Denny Zhou and
Daphne Ippolito and
David Luan and
Hyeontaek Lim and
Barret Zoph and
Alexander Spiridonov and
Ryan Sepassi and
David Dohan and
Shivani Agrawal and
Mark Omernick and
Andrew M. Dai and
Thanumalayan Sankaranarayana Pillai and
Marie Pellat and
Aitor Lewkowycz and
Erica Moreira and
Rewon Child and
Oleksandr Polozov and
Katherine Lee and
Zongwei Zhou and
Xuezhi Wang and
Brennan Saeta and
Mark Diaz and
Orhan Firat and
Michele Catasta and
Jason Wei and
Kathy Meier{-}Hellstern and
Douglas Eck and
Jeff Dean and
Slav Petrov and
Noah Fiedel},
title = {PaLM: Scaling Language Modeling with Pathways},
journal = {J. Mach. Learn. Res.},
volume = {24},
pages = {240:1--240:113},
year = {2023},
url = {https://jmlr.org/papers/v24/22-1144.html},
timestamp = {Wed, 11 Sep 2024 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/jmlr/ChowdheryNDBMRBCSGSSTMRBTSPRDHPBAI23.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/tmlr/SrivastavaRRSAF23,
author = {Aarohi Srivastava and
Abhinav Rastogi and
Abhishek Rao and
Abu Awal Md Shoeb and
Abubakar Abid and
Adam Fisch and
Adam R. Brown and
Adam Santoro and
Aditya Gupta and
Adri{\`{a}} Garriga{-}Alonso and
Agnieszka Kluska and
Aitor Lewkowycz and
Akshat Agarwal and
Alethea Power and
Alex Ray and
Alex Warstadt and
Alexander W. Kocurek and
Ali Safaya and
Ali Tazarv and
Alice Xiang and
Alicia Parrish and
Allen Nie and
Aman Hussain and
Amanda Askell and
Amanda Dsouza and
Ambrose Slone and
Ameet Rahane and
Anantharaman S. Iyer and
Anders Andreassen and
Andrea Madotto and
Andrea Santilli and
Andreas Stuhlm{\"{u}}ller and
Andrew M. Dai and
Andrew La and
Andrew K. Lampinen and
Andy Zou and
Angela Jiang and
Angelica Chen and
Anh Vuong and
Animesh Gupta and
Anna Gottardi and
Antonio Norelli and
Anu Venkatesh and
Arash Gholamidavoodi and
Arfa Tabassum and
Arul Menezes and
Arun Kirubarajan and
Asher Mullokandov and
Ashish Sabharwal and
Austin Herrick and
Avia Efrat and
Aykut Erdem and
Ayla Karakas and
B. Ryan Roberts and
Bao Sheng Loe and
Barret Zoph and
Bartlomiej Bojanowski and
Batuhan {\"{O}}zyurt and
Behnam Hedayatnia and
Behnam Neyshabur and
Benjamin Inden and
Benno Stein and
Berk Ekmekci and
Bill Yuchen Lin and
Blake Howald and
Bryan Orinion and
Cameron Diao and
Cameron Dour and
Catherine Stinson and
Cedrick Argueta and
C{\`{e}}sar Ferri Ram{\'{\i}}rez and
Chandan Singh and
Charles Rathkopf and
Chenlin Meng and
Chitta Baral and
Chiyu Wu and
Chris Callison{-}Burch and
Chris Waites and
Christian Voigt and
Christopher D. Manning and
Christopher Potts and
Cindy Ramirez and
Clara E. Rivera and
Clemencia Siro and
Colin Raffel and
Courtney Ashcraft and
Cristina Garbacea and
Damien Sileo and
Dan Garrette and
Dan Hendrycks and
Dan Kilman and
Dan Roth and
Daniel Freeman and
Daniel Khashabi and
Daniel Levy and
Daniel Mosegu{\'{\i}} Gonz{\'{a}}lez and
Danielle Perszyk and
Danny Hernandez and
Danqi Chen and
Daphne Ippolito and
Dar Gilboa and
David Dohan and
David Drakard and
David Jurgens and
Debajyoti Datta and
Deep Ganguli and
Denis Emelin and
Denis Kleyko and
Deniz Yuret and
Derek Chen and
Derek Tam and
Dieuwke Hupkes and
Diganta Misra and
Dilyar Buzan and
Dimitri Coelho Mollo and
Diyi Yang and
Dong{-}Ho Lee and
Dylan Schrader and
Ekaterina Shutova and
Ekin Dogus Cubuk and
Elad Segal and
Eleanor Hagerman and
Elizabeth Barnes and
Elizabeth Donoway and
Ellie Pavlick and
Emanuele Rodol{\`{a}} and
Emma Lam and
Eric Chu and
Eric Tang and
Erkut Erdem and
Ernie Chang and
Ethan A. Chi and
Ethan Dyer and
Ethan J. Jerzak and
Ethan Kim and
Eunice Engefu Manyasi and
Evgenii Zheltonozhskii and
Fanyue Xia and
Fatemeh Siar and
Fernando Mart{\'{\i}}nez{-}Plumed and
Francesca Happ{\'{e}} and
Fran{\c{c}}ois Chollet and
Frieda Rong and
Gaurav Mishra and
Genta Indra Winata and
Gerard de Melo and
Germ{\'{a}}n Kruszewski and
Giambattista Parascandolo and
Giorgio Mariani and
Gloria Wang and
Gonzalo Jaimovitch{-}L{\'{o}}pez and
Gregor Betz and
Guy Gur{-}Ari and
Hana Galijasevic and
Hannah Kim and
Hannah Rashkin and
Hannaneh Hajishirzi and
Harsh Mehta and
Hayden Bogar and
Henry Shevlin and
Hinrich Sch{\"{u}}tze and
Hiromu Yakura and
Hongming Zhang and
Hugh Mee Wong and
Ian Ng and
Isaac Noble and
Jaap Jumelet and
Jack Geissinger and
Jackson Kernion and
Jacob Hilton and
Jaehoon Lee and
Jaime Fern{\'{a}}ndez Fisac and
James B. Simon and
James Koppel and
James Zheng and
James Zou and
Jan Kocon and
Jana Thompson and
Janelle Wingfield and
Jared Kaplan and
Jarema Radom and
Jascha Sohl{-}Dickstein and
Jason Phang and
Jason Wei and
Jason Yosinski and
Jekaterina Novikova and
Jelle Bosscher and
Jennifer Marsh and
Jeremy Kim and
Jeroen Taal and
Jesse H. Engel and
Jesujoba Alabi and
Jiacheng Xu and
Jiaming Song and
Jillian Tang and
Joan Waweru and
John Burden and
John Miller and
John U. Balis and
Jonathan Batchelder and
Jonathan Berant and
J{\"{o}}rg Frohberg and
Jos Rozen and
Jos{\'{e}} Hern{\'{a}}ndez{-}Orallo and
Joseph Boudeman and
Joseph Guerr and
Joseph Jones and
Joshua B. Tenenbaum and
Joshua S. Rule and
Joyce Chua and
Kamil Kanclerz and
Karen Livescu and
Karl Krauth and
Karthik Gopalakrishnan and
Katerina Ignatyeva and
Katja Markert and
Kaustubh D. Dhole and
Kevin Gimpel and
Kevin Omondi and
Kory Mathewson and
Kristen Chiafullo and
Ksenia Shkaruta and
Kumar Shridhar and
Kyle McDonell and
Kyle Richardson and
Laria Reynolds and
Leo Gao and
Li Zhang and
Liam Dugan and
Lianhui Qin and
Lidia Contreras Ochando and
Louis{-}Philippe Morency and
Luca Moschella and
Lucas Lam and
Lucy Noble and
Ludwig Schmidt and
Luheng He and
Luis Oliveros Col{\'{o}}n and
Luke Metz and
L{\"{u}}tfi Kerem Senel and
Maarten Bosma and
Maarten Sap and
Maartje ter Hoeve and
Maheen Farooqi and
Manaal Faruqui and
Mantas Mazeika and
Marco Baturan and
Marco Marelli and
Marco Maru and
Mar{\'{\i}}a Jos{\'{e}} Ram{\'{\i}}rez{-}Quintana and
Marie Tolkiehn and
Mario Giulianelli and
Martha Lewis and
Martin Potthast and
Matthew L. Leavitt and
Matthias Hagen and
M{\'{a}}ty{\'{a}}s Schubert and
Medina Baitemirova and
Melody Arnaud and
Melvin McElrath and
Michael A. Yee and
Michael Cohen and
Michael Gu and
Michael I. Ivanitskiy and
Michael Starritt and
Michael Strube and
Michal Swedrowski and
Michele Bevilacqua and
Michihiro Yasunaga and
Mihir Kale and
Mike Cain and
Mimee Xu and
Mirac Suzgun and
Mitch Walker and
Mo Tiwari and
Mohit Bansal and
Moin Aminnaseri and
Mor Geva and
Mozhdeh Gheini and
Mukund Varma T. and
Nanyun Peng and
Nathan A. Chi and
Nayeon Lee and
Neta Gur{-}Ari Krakover and
Nicholas Cameron and
Nicholas Roberts and
Nick Doiron and
Nicole Martinez and
Nikita Nangia and
Niklas Deckers and
Niklas Muennighoff and
Nitish Shirish Keskar and
Niveditha Iyer and
Noah Constant and
Noah Fiedel and
Nuan Wen and
Oliver Zhang and
Omar Agha and
Omar Elbaghdadi and
Omer Levy and
Owain Evans and
Pablo Antonio Moreno Casares and
Parth Doshi and
Pascale Fung and
Paul Pu Liang and
Paul Vicol and
Pegah Alipoormolabashi and
Peiyuan Liao and
Percy Liang and
Peter Chang and
Peter Eckersley and
Phu Mon Htut and
Pinyu Hwang and
Piotr Milkowski and
Piyush Patil and
Pouya Pezeshkpour and
Priti Oli and
Qiaozhu Mei and
Qing Lyu and
Qinlang Chen and
Rabin Banjade and
Rachel Etta Rudolph and
Raefer Gabriel and
Rahel Habacker and
Ramon Risco and
Rapha{\"{e}}l Milli{\`{e}}re and
Rhythm Garg and
Richard Barnes and
Rif A. Saurous and
Riku Arakawa and
Robbe Raymaekers and
Robert Frank and
Rohan Sikand and
Roman Novak and
Roman Sitelew and
Ronan LeBras and
Rosanne Liu and
Rowan Jacobs and
Rui Zhang and
Ruslan Salakhutdinov and
Ryan Chi and
Ryan Lee and
Ryan Stovall and
Ryan Teehan and
Rylan Yang and
Sahib Singh and
Saif M. Mohammad and
Sajant Anand and
Sam Dillavou and
Sam Shleifer and
Sam Wiseman and
Samuel Gruetter and
Samuel R. Bowman and
Samuel S. Schoenholz and
Sanghyun Han and
Sanjeev Kwatra and
Sarah A. Rous and
Sarik Ghazarian and
Sayan Ghosh and
Sean Casey and
Sebastian Bischoff and
Sebastian Gehrmann and
Sebastian Schuster and
Sepideh Sadeghi and
Shadi Hamdan and
Sharon Zhou and
Shashank Srivastava and
Sherry Shi and
Shikhar Singh and
Shima Asaadi and
Shixiang Shane Gu and
Shubh Pachchigar and
Shubham Toshniwal and
Shyam Upadhyay and
Shyamolima (Shammie) Debnath and
Siamak Shakeri and
Simon Thormeyer and
Simone Melzi and
Siva Reddy and
Sneha Priscilla Makini and
Soo{-}Hwan Lee and
Spencer Torene and
Sriharsha Hatwar and
Stanislas Dehaene and
Stefan Divic and
Stefano Ermon and
Stella Biderman and
Stephanie Lin and
Stephen Prasad and
Steven T. Piantadosi and
Stuart M. Shieber and
Summer Misherghi and
Svetlana Kiritchenko and
Swaroop Mishra and
Tal Linzen and
Tal Schuster and
Tao Li and
Tao Yu and
Tariq Ali and
Tatsu Hashimoto and
Te{-}Lin Wu and
Th{\'{e}}o Desbordes and
Theodore Rothschild and
Thomas Phan and
Tianle Wang and
Tiberius Nkinyili and
Timo Schick and
Timofei Kornev and
Titus Tunduny and
Tobias Gerstenberg and
Trenton Chang and
Trishala Neeraj and
Tushar Khot and
Tyler Shultz and
Uri Shaham and
Vedant Misra and
Vera Demberg and
Victoria Nyamai and
Vikas Raunak and
Vinay V. Ramasesh and
Vinay Uday Prabhu and
Vishakh Padmakumar and
Vivek Srikumar and
William Fedus and
William Saunders and
William Zhang and
Wout Vossen and
Xiang Ren and
Xiaoyu Tong and
Xinran Zhao and
Xinyi Wu and
Xudong Shen and
Yadollah Yaghoobzadeh and
Yair Lakretz and
Yangqiu Song and
Yasaman Bahri and
Yejin Choi and
Yichi Yang and
Yiding Hao and
Yifu Chen and
Yonatan Belinkov and
Yu Hou and
Yufang Hou and
Yuntao Bai and
Zachary Seid and
Zhuoye Zhao and
Zijian Wang and
Zijie J. Wang and
Zirui Wang and
Ziyi Wu},
title = {Beyond the Imitation Game: Quantifying and extrapolating the capabilities
of language models},
journal = {Trans. Mach. Learn. Res.},
volume = {2023},
year = {2023},
url = {https://openreview.net/forum?id=uyTL5Bvosj},
timestamp = {Tue, 06 Aug 2024 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/tmlr/SrivastavaRRSAF23.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/emnlp/Tay0ACFRN0YM23,
author = {Yi Tay and
Mostafa Dehghani and
Samira Abnar and
Hyung Won Chung and
William Fedus and
Jinfeng Rao and
Sharan Narang and
Vinh Q. Tran and
Dani Yogatama and
Donald Metzler},
editor = {Houda Bouamor and
Juan Pino and
Kalika Bali},
title = {Scaling Laws vs Model Architectures: How does Inductive Bias Influence
Scaling?},
booktitle = {Findings of the Association for Computational Linguistics: {EMNLP}
2023, Singapore, December 6-10, 2023},
pages = {12342--12364},
publisher = {Association for Computational Linguistics},
year = {2023},
url = {https://doi.org/10.18653/v1/2023.findings-emnlp.825},
doi = {10.18653/V1/2023.FINDINGS-EMNLP.825},
timestamp = {Fri, 12 Apr 2024 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/emnlp/Tay0ACFRN0YM23.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2305-14705,
author = {Sheng Shen and
Le Hou and
Yanqi Zhou and
Nan Du and
Shayne Longpre and
Jason Wei and
Hyung Won Chung and
Barret Zoph and
William Fedus and
Xinyun Chen and
Tu Vu and
Yuexin Wu and
Wuyang Chen and
Albert Webson and
Yunxuan Li and
Vincent Y. Zhao and
Hongkun Yu and
Kurt Keutzer and
Trevor Darrell and
Denny Zhou},
title = {Flan-MoE: Scaling Instruction-Finetuned Language Models with Sparse
Mixture of Experts},
journal = {CoRR},
volume = {abs/2305.14705},
year = {2023},
url = {https://doi.org/10.48550/arXiv.2305.14705},
doi = {10.48550/ARXIV.2305.14705},
eprinttype = {arXiv},
eprint = {2305.14705},
timestamp = {Tue, 27 Feb 2024 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2305-14705.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/jmlr/FedusZS22,
author = {William Fedus and
Barret Zoph and
Noam Shazeer},
title = {Switch Transformers: Scaling to Trillion Parameter Models with Simple
and Efficient Sparsity},
journal = {J. Mach. Learn. Res.},
volume = {23},
pages = {120:1--120:39},
year = {2022},
url = {https://jmlr.org/papers/v23/21-0998.html},
timestamp = {Wed, 11 Sep 2024 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/jmlr/FedusZS22.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/tmlr/WeiTBRZBYBZMCHVLDF22,
author = {Jason Wei and
Yi Tay and
Rishi Bommasani and
Colin Raffel and
Barret Zoph and
Sebastian Borgeaud and
Dani Yogatama and
Maarten Bosma and
Denny Zhou and
Donald Metzler and
Ed H. Chi and
Tatsunori Hashimoto and
Oriol Vinyals and
Percy Liang and
Jeff Dean and
William Fedus},
title = {Emergent Abilities of Large Language Models},
journal = {Trans. Mach. Learn. Res.},
volume = {2022},
year = {2022},
url = {https://openreview.net/forum?id=yzkSU5zdwD},
timestamp = {Fri, 19 May 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/tmlr/WeiTBRZBYBZMCHVLDF22.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/iclr/Tay0RFACNYVM22,
author = {Yi Tay and
Mostafa Dehghani and
Jinfeng Rao and
William Fedus and
Samira Abnar and
Hyung Won Chung and
Sharan Narang and
Dani Yogatama and
Ashish Vaswani and
Donald Metzler},
title = {Scale Efficiently: Insights from Pretraining and Finetuning Transformers},
booktitle = {The Tenth International Conference on Learning Representations, {ICLR}
2022, Virtual Event, April 25-29, 2022},
publisher = {OpenReview.net},
year = {2022},
url = {https://openreview.net/forum?id=f2OYVDyfIB},
timestamp = {Sat, 20 Aug 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/iclr/Tay0RFACNYVM22.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icml/DuHDTLXKZYFZFBZ22,
author = {Nan Du and
Yanping Huang and
Andrew M. Dai and
Simon Tong and
Dmitry Lepikhin and
Yuanzhong Xu and
Maxim Krikun and
Yanqi Zhou and
Adams Wei Yu and
Orhan Firat and
Barret Zoph and
Liam Fedus and
Maarten P. Bosma and
Zongwei Zhou and
Tao Wang and
Yu Emma Wang and
Kellie Webster and
Marie Pellat and
Kevin Robinson and
Kathleen S. Meier{-}Hellstern and
Toju Duke and
Lucas Dixon and
Kun Zhang and
Quoc V. Le and
Yonghui Wu and
Zhifeng Chen and
Claire Cui},
editor = {Kamalika Chaudhuri and
Stefanie Jegelka and
Le Song and
Csaba Szepesv{\'{a}}ri and
Gang Niu and
Sivan Sabato},
title = {GLaM: Efficient Scaling of Language Models with Mixture-of-Experts},
booktitle = {International Conference on Machine Learning, {ICML} 2022, 17-23 July
2022, Baltimore, Maryland, {USA}},
series = {Proceedings of Machine Learning Research},
volume = {162},
pages = {5547--5569},
publisher = {{PMLR}},
year = {2022},
url = {https://proceedings.mlr.press/v162/du22c.html},
timestamp = {Wed, 16 Aug 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icml/DuHDTLXKZYFZFBZ22.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2202-08906,
author = {Barret Zoph and
Irwan Bello and
Sameer Kumar and
Nan Du and
Yanping Huang and
Jeff Dean and
Noam Shazeer and
William Fedus},
title = {Designing Effective Sparse Expert Models},
journal = {CoRR},
volume = {abs/2202.08906},
year = {2022},
url = {https://arxiv.org/abs/2202.08906},
eprinttype = {arXiv},
eprint = {2202.08906},
timestamp = {Thu, 17 Aug 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2202-08906.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2204-02311,
author = {Aakanksha Chowdhery and
Sharan Narang and
Jacob Devlin and
Maarten Bosma and
Gaurav Mishra and
Adam Roberts and
Paul Barham and
Hyung Won Chung and
Charles Sutton and
Sebastian Gehrmann and
Parker Schuh and
Kensen Shi and
Sasha Tsvyashchenko and
Joshua Maynez and
Abhishek Rao and
Parker Barnes and
Yi Tay and
Noam Shazeer and
Vinodkumar Prabhakaran and
Emily Reif and
Nan Du and
Ben Hutchinson and
Reiner Pope and
James Bradbury and
Jacob Austin and
Michael Isard and
Guy Gur{-}Ari and
Pengcheng Yin and
Toju Duke and
Anselm Levskaya and
Sanjay Ghemawat and
Sunipa Dev and
Henryk Michalewski and
Xavier Garcia and
Vedant Misra and
Kevin Robinson and
Liam Fedus and
Denny Zhou and
Daphne Ippolito and
David Luan and
Hyeontaek Lim and
Barret Zoph and
Alexander Spiridonov and
Ryan Sepassi and
David Dohan and
Shivani Agrawal and
Mark Omernick and
Andrew M. Dai and
Thanumalayan Sankaranarayana Pillai and
Marie Pellat and
Aitor Lewkowycz and
Erica Moreira and
Rewon Child and
Oleksandr Polozov and
Katherine Lee and
Zongwei Zhou and
Xuezhi Wang and
Brennan Saeta and
Mark Diaz and
Orhan Firat and
Michele Catasta and
Jason Wei and
Kathy Meier{-}Hellstern and
Douglas Eck and
Jeff Dean and
Slav Petrov and
Noah Fiedel},
title = {PaLM: Scaling Language Modeling with Pathways},
journal = {CoRR},
volume = {abs/2204.02311},
year = {2022},
url = {https://doi.org/10.48550/arXiv.2204.02311},
doi = {10.48550/ARXIV.2204.02311},
eprinttype = {arXiv},
eprint = {2204.02311},
timestamp = {Wed, 16 Aug 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2204-02311.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2206-04615,
author = {Aarohi Srivastava and
Abhinav Rastogi and
Abhishek Rao and
Abu Awal Md Shoeb and
Abubakar Abid and
Adam Fisch and
Adam R. Brown and
Adam Santoro and
Aditya Gupta and
Adri{\`{a}} Garriga{-}Alonso and
Agnieszka Kluska and
Aitor Lewkowycz and
Akshat Agarwal and
Alethea Power and
Alex Ray and
Alex Warstadt and
Alexander W. Kocurek and
Ali Safaya and
Ali Tazarv and
Alice Xiang and
Alicia Parrish and
Allen Nie and
Aman Hussain and
Amanda Askell and
Amanda Dsouza and
Ambrose Slone and
Ameet Rahane and
Anantharaman S. Iyer and
Anders Andreassen and
Andrea Madotto and
Andrea Santilli and
Andreas Stuhlm{\"{u}}ller and
Andrew M. Dai and
Andrew La and
Andrew K. Lampinen and
Andy Zou and
Angela Jiang and
Angelica Chen and
Anh Vuong and
Animesh Gupta and
Anna Gottardi and
Antonio Norelli and
Anu Venkatesh and
Arash Gholamidavoodi and
Arfa Tabassum and
Arul Menezes and
Arun Kirubarajan and
Asher Mullokandov and
Ashish Sabharwal and
Austin Herrick and
Avia Efrat and
Aykut Erdem and
Ayla Karakas and
B. Ryan Roberts and
Bao Sheng Loe and
Barret Zoph and
Bartlomiej Bojanowski and
Batuhan {\"{O}}zyurt and
Behnam Hedayatnia and
Behnam Neyshabur and
Benjamin Inden and
Benno Stein and
Berk Ekmekci and
Bill Yuchen Lin and
Blake Howald and
Bryan Orinion and
Cameron Diao and
Cameron Dour and
Catherine Stinson and
Cedrick Argueta and
C{\`{e}}sar Ferri Ram{\'{\i}}rez and
Chandan Singh and
Charles Rathkopf and
Chenlin Meng and
Chitta Baral and
Chiyu Wu and
Chris Callison{-}Burch and
Chris Waites and
Christian Voigt and
Christopher D. Manning and
Christopher Potts and
Cindy Ramirez and
Clara E. Rivera and
Clemencia Siro and
Colin Raffel and
Courtney Ashcraft and
Cristina Garbacea and
Damien Sileo and
Dan Garrette and
Dan Hendrycks and
Dan Kilman and
Dan Roth and
Daniel Freeman and
Daniel Khashabi and
Daniel Levy and
Daniel Mosegu{\'{\i}} Gonz{\'{a}}lez and
Danielle Perszyk and
Danny Hernandez and
Danqi Chen and
Daphne Ippolito and
Dar Gilboa and
David Dohan and
David Drakard and
David Jurgens and
Debajyoti Datta and
Deep Ganguli and
Denis Emelin and
Denis Kleyko and
Deniz Yuret and
Derek Chen and
Derek Tam and
Dieuwke Hupkes and
Diganta Misra and
Dilyar Buzan and
Dimitri Coelho Mollo and
Diyi Yang and
Dong{-}Ho Lee and
Dylan Schrader and
Ekaterina Shutova and
Ekin Dogus Cubuk and
Elad Segal and
Eleanor Hagerman and
Elizabeth Barnes and
Elizabeth Donoway and
Ellie Pavlick and
Emanuele Rodol{\`{a}} and
Emma Lam and
Eric Chu and
Eric Tang and
Erkut Erdem and
Ernie Chang and
Ethan A. Chi and
Ethan Dyer and
Ethan J. Jerzak and
Ethan Kim and
Eunice Engefu Manyasi and
Evgenii Zheltonozhskii and
Fanyue Xia and
Fatemeh Siar and
Fernando Mart{\'{\i}}nez{-}Plumed and
Francesca Happ{\'{e}} and
Fran{\c{c}}ois Chollet and
Frieda Rong and
Gaurav Mishra and
Genta Indra Winata and
Gerard de Melo and
Germ{\'{a}}n Kruszewski and
Giambattista Parascandolo and
Giorgio Mariani and
Gloria Wang and
Gonzalo Jaimovitch{-}L{\'{o}}pez and
Gregor Betz and
Guy Gur{-}Ari and
Hana Galijasevic and
Hannah Kim and
Hannah Rashkin and
Hannaneh Hajishirzi and
Harsh Mehta and
Hayden Bogar and
Henry Shevlin and
Hinrich Sch{\"{u}}tze and
Hiromu Yakura and
Hongming Zhang and
Hugh Mee Wong and
Ian Ng and
Isaac Noble and
Jaap Jumelet and
Jack Geissinger and
Jackson Kernion and
Jacob Hilton and
Jaehoon Lee and
Jaime Fern{\'{a}}ndez Fisac and
James B. Simon and
James Koppel and
James Zheng and
James Zou and
Jan Kocon and
Jana Thompson and
Janelle Wingfield and
Jared Kaplan and
Jarema Radom and
Jascha Sohl{-}Dickstein and
Jason Phang and
Jason Wei and
Jason Yosinski and
Jekaterina Novikova and
Jelle Bosscher and
Jennifer Marsh and
Jeremy Kim and
Jeroen Taal and
Jesse H. Engel and
Jesujoba Alabi and
Jiacheng Xu and
Jiaming Song and
Jillian Tang and
Joan Waweru and
John Burden and
John Miller and
John U. Balis and
Jonathan Batchelder and
Jonathan Berant and
J{\"{o}}rg Frohberg and
Jos Rozen and
Jos{\'{e}} Hern{\'{a}}ndez{-}Orallo and
Joseph Boudeman and
Joseph Guerr and
Joseph Jones and
Joshua B. Tenenbaum and
Joshua S. Rule and
Joyce Chua and
Kamil Kanclerz and
Karen Livescu and
Karl Krauth and
Karthik Gopalakrishnan and
Katerina Ignatyeva and
Katja Markert and
Kaustubh D. Dhole and
Kevin Gimpel and
Kevin Omondi and
Kory Mathewson and
Kristen Chiafullo and
Ksenia Shkaruta and
Kumar Shridhar and
Kyle McDonell and
Kyle Richardson and
Laria Reynolds and
Leo Gao and
Li Zhang and
Liam Dugan and
Lianhui Qin and
Lidia Contreras Ochando and
Louis{-}Philippe Morency and
Luca Moschella and
Lucas Lam and
Lucy Noble and
Ludwig Schmidt and
Luheng He and
Luis Oliveros Col{\'{o}}n and
Luke Metz and
L{\"{u}}tfi Kerem Senel and
Maarten Bosma and
Maarten Sap and
Maartje ter Hoeve and
Maheen Farooqi and
Manaal Faruqui and
Mantas Mazeika and
Marco Baturan and
Marco Marelli and
Marco Maru and
Mar{\'{\i}}a Jos{\'{e}} Ram{\'{\i}}rez{-}Quintana and
Marie Tolkiehn and
Mario Giulianelli and
Martha Lewis and
Martin Potthast and
Matthew L. Leavitt and
Matthias Hagen and
M{\'{a}}ty{\'{a}}s Schubert and
Medina Baitemirova and
Melody Arnaud and
Melvin McElrath and
Michael A. Yee and
Michael Cohen and
Michael Gu and
Michael I. Ivanitskiy and
Michael Starritt and
Michael Strube and
Michal Swedrowski and
Michele Bevilacqua and
Michihiro Yasunaga and
Mihir Kale and
Mike Cain and
Mimee Xu and
Mirac Suzgun and
Mitch Walker and
Mo Tiwari and
Mohit Bansal and
Moin Aminnaseri and
Mor Geva and
Mozhdeh Gheini and
Mukund Varma T. and
Nanyun Peng and
Nathan A. Chi and
Nayeon Lee and
Neta Gur{-}Ari Krakover and
Nicholas Cameron and
Nicholas Roberts and
Nick Doiron and
Nicole Martinez and
Nikita Nangia and
Niklas Deckers and
Niklas Muennighoff and
Nitish Shirish Keskar and
Niveditha Iyer and
Noah Constant and
Noah Fiedel and
Nuan Wen and
Oliver Zhang and
Omar Agha and
Omar Elbaghdadi and
Omer Levy and
Owain Evans and
Pablo Antonio Moreno Casares and
Parth Doshi and
Pascale Fung and
Paul Pu Liang and
Paul Vicol and
Pegah Alipoormolabashi and
Peiyuan Liao and
Percy Liang and
Peter Chang and
Peter Eckersley and
Phu Mon Htut and
Pinyu Hwang and
Piotr Milkowski and
Piyush Patil and
Pouya Pezeshkpour and
Priti Oli and
Qiaozhu Mei and
Qing Lyu and
Qinlang Chen and
Rabin Banjade and
Rachel Etta Rudolph and
Raefer Gabriel and
Rahel Habacker and
Ramon Risco and
Rapha{\"{e}}l Milli{\`{e}}re and
Rhythm Garg and
Richard Barnes and
Rif A. Saurous and
Riku Arakawa and
Robbe Raymaekers and
Robert Frank and
Rohan Sikand and
Roman Novak and
Roman Sitelew and
Ronan LeBras and
Rosanne Liu and
Rowan Jacobs and
Rui Zhang and
Ruslan Salakhutdinov and
Ryan Chi and
Ryan Lee and
Ryan Stovall and
Ryan Teehan and
Rylan Yang and
Sahib Singh and
Saif M. Mohammad and
Sajant Anand and
Sam Dillavou and
Sam Shleifer and
Sam Wiseman and
Samuel Gruetter and
Samuel R. Bowman and
Samuel S. Schoenholz and
Sanghyun Han and
Sanjeev Kwatra and
Sarah A. Rous and
Sarik Ghazarian and
Sayan Ghosh and
Sean Casey and
Sebastian Bischoff and
Sebastian Gehrmann and
Sebastian Schuster and
Sepideh Sadeghi and
Shadi Hamdan and
Sharon Zhou and
Shashank Srivastava and
Sherry Shi and
Shikhar Singh and
Shima Asaadi and
Shixiang Shane Gu and
Shubh Pachchigar and
Shubham Toshniwal and
Shyam Upadhyay and
Shyamolima (Shammie) Debnath and
Siamak Shakeri and
Simon Thormeyer and
Simone Melzi and
Siva Reddy and
Sneha Priscilla Makini and
Soo{-}Hwan Lee and
Spencer Torene and
Sriharsha Hatwar and
Stanislas Dehaene and
Stefan Divic and
Stefano Ermon and
Stella Biderman and
Stephanie Lin and
Stephen Prasad and
Steven T. Piantadosi and
Stuart M. Shieber and
Summer Misherghi and
Svetlana Kiritchenko and
Swaroop Mishra and
Tal Linzen and
Tal Schuster and
Tao Li and
Tao Yu and
Tariq Ali and
Tatsu Hashimoto and
Te{-}Lin Wu and
Th{\'{e}}o Desbordes and
Theodore Rothschild and
Thomas Phan and
Tianle Wang and
Tiberius Nkinyili and
Timo Schick and
Timofei Kornev and
Titus Tunduny and
Tobias Gerstenberg and
Trenton Chang and
Trishala Neeraj and
Tushar Khot and
Tyler Shultz and
Uri Shaham and
Vedant Misra and
Vera Demberg and
Victoria Nyamai and
Vikas Raunak and
Vinay V. Ramasesh and
Vinay Uday Prabhu and
Vishakh Padmakumar and
Vivek Srikumar and
William Fedus and
William Saunders and
William Zhang and
Wout Vossen and
Xiang Ren and
Xiaoyu Tong and
Xinran Zhao and
Xinyi Wu and
Xudong Shen and
Yadollah Yaghoobzadeh and
Yair Lakretz and
Yangqiu Song and
Yasaman Bahri and
Yejin Choi and
Yichi Yang and
Yiding Hao and
Yifu Chen and
Yonatan Belinkov and
Yu Hou and
Yufang Hou and
Yuntao Bai and
Zachary Seid and
Zhuoye Zhao and
Zijian Wang and
Zijie J. Wang and
Zirui Wang and
Ziyi Wu},
title = {Beyond the Imitation Game: Quantifying and extrapolating the capabilities
of language models},
journal = {CoRR},
volume = {abs/2206.04615},
year = {2022},
url = {https://doi.org/10.48550/arXiv.2206.04615},
doi = {10.48550/ARXIV.2206.04615},
eprinttype = {arXiv},
eprint = {2206.04615},
timestamp = {Mon, 05 Aug 2024 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2206-04615.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2206-07682,
author = {Jason Wei and
Yi Tay and
Rishi Bommasani and
Colin Raffel and
Barret Zoph and
Sebastian Borgeaud and
Dani Yogatama and
Maarten Bosma and
Denny Zhou and
Donald Metzler and
Ed H. Chi and
Tatsunori Hashimoto and
Oriol Vinyals and
Percy Liang and
Jeff Dean and
William Fedus},
title = {Emergent Abilities of Large Language Models},
journal = {CoRR},
volume = {abs/2206.07682},
year = {2022},
url = {https://doi.org/10.48550/arXiv.2206.07682},
doi = {10.48550/ARXIV.2206.07682},
eprinttype = {arXiv},
eprint = {2206.07682},
timestamp = {Tue, 21 Jun 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2206-07682.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2207-10551,
author = {Yi Tay and
Mostafa Dehghani and
Samira Abnar and
Hyung Won Chung and
William Fedus and
Jinfeng Rao and
Sharan Narang and
Vinh Q. Tran and
Dani Yogatama and
Donald Metzler},
title = {Scaling Laws vs Model Architectures: How does Inductive Bias Influence
Scaling?},
journal = {CoRR},
volume = {abs/2207.10551},
year = {2022},
url = {https://doi.org/10.48550/arXiv.2207.10551},
doi = {10.48550/ARXIV.2207.10551},
eprinttype = {arXiv},
eprint = {2207.10551},
timestamp = {Mon, 25 Jul 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2207-10551.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2209-01667,
author = {William Fedus and
Jeff Dean and
Barret Zoph},
title = {A Review of Sparse Expert Models in Deep Learning},
journal = {CoRR},
volume = {abs/2209.01667},
year = {2022},
url = {https://doi.org/10.48550/arXiv.2209.01667},
doi = {10.48550/ARXIV.2209.01667},
eprinttype = {arXiv},
eprint = {2209.01667},
timestamp = {Mon, 26 Sep 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2209-01667.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2210-11416,
author = {Hyung Won Chung and
Le Hou and
Shayne Longpre and
Barret Zoph and
Yi Tay and
William Fedus and
Eric Li and
Xuezhi Wang and
Mostafa Dehghani and
Siddhartha Brahma and
Albert Webson and
Shixiang Shane Gu and
Zhuyun Dai and
Mirac Suzgun and
Xinyun Chen and
Aakanksha Chowdhery and
Sharan Narang and
Gaurav Mishra and
Adams Yu and
Vincent Y. Zhao and
Yanping Huang and
Andrew M. Dai and
Hongkun Yu and
Slav Petrov and
Ed H. Chi and
Jeff Dean and
Jacob Devlin and
Adam Roberts and
Denny Zhou and
Quoc V. Le and
Jason Wei},
title = {Scaling Instruction-Finetuned Language Models},
journal = {CoRR},
volume = {abs/2210.11416},
year = {2022},
url = {https://doi.org/10.48550/arXiv.2210.11416},
doi = {10.48550/ARXIV.2210.11416},
eprinttype = {arXiv},
eprint = {2210.11416},
timestamp = {Mon, 04 Dec 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2210-11416.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/emnlp/NarangCTFFMMFSL21,
author = {Sharan Narang and
Hyung Won Chung and
Yi Tay and
Liam Fedus and
Thibault F{\'{e}}vry and
Michael Matena and
Karishma Malkan and
Noah Fiedel and
Noam Shazeer and
Zhenzhong Lan and
Yanqi Zhou and
Wei Li and
Nan Ding and
Jake Marcus and
Adam Roberts and
Colin Raffel},
editor = {Marie{-}Francine Moens and
Xuanjing Huang and
Lucia Specia and
Scott Wen{-}tau Yih},
title = {Do Transformer Modifications Transfer Across Implementations and Applications?},
booktitle = {Proceedings of the 2021 Conference on Empirical Methods in Natural
Language Processing, {EMNLP} 2021, Virtual Event / Punta Cana, Dominican
Republic, 7-11 November, 2021},
pages = {5758--5773},
publisher = {Association for Computational Linguistics},
year = {2021},
url = {https://doi.org/10.18653/v1/2021.emnlp-main.465},
doi = {10.18653/V1/2021.EMNLP-MAIN.465},
timestamp = {Fri, 16 Feb 2024 08:27:36 +0100},
biburl = {https://dblp.org/rec/conf/emnlp/NarangCTFFMMFSL21.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nips/BelloFDCSLSZ21,
author = {Irwan Bello and
William Fedus and
Xianzhi Du and
Ekin Dogus Cubuk and
Aravind Srinivas and
Tsung{-}Yi Lin and
Jonathon Shlens and
Barret Zoph},
editor = {Marc'Aurelio Ranzato and
Alina Beygelzimer and
Yann N. Dauphin and
Percy Liang and
Jennifer Wortman Vaughan},
title = {Revisiting ResNets: Improved Training and Scaling Strategies},
booktitle = {Advances in Neural Information Processing Systems 34: Annual Conference
on Neural Information Processing Systems 2021, NeurIPS 2021, December
6-14, 2021, virtual},
pages = {22614--22627},
year = {2021},
url = {https://proceedings.neurips.cc/paper/2021/hash/bef4d169d8bddd17d68303877a3ea945-Abstract.html},
timestamp = {Tue, 03 May 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/nips/BelloFDCSLSZ21.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2101-03961,
author = {William Fedus and
Barret Zoph and
Noam Shazeer},
title = {Switch Transformers: Scaling to Trillion Parameter Models with Simple
and Efficient Sparsity},
journal = {CoRR},
volume = {abs/2101.03961},
year = {2021},
url = {https://arxiv.org/abs/2101.03961},
eprinttype = {arXiv},
eprint = {2101.03961},
timestamp = {Thu, 21 Jan 2021 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2101-03961.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2102-11972,
author = {Sharan Narang and
Hyung Won Chung and
Yi Tay and
William Fedus and
Thibault F{\'{e}}vry and
Michael Matena and
Karishma Malkan and
Noah Fiedel and
Noam Shazeer and
Zhenzhong Lan and
Yanqi Zhou and
Wei Li and
Nan Ding and
Jake Marcus and
Adam Roberts and
Colin Raffel},
title = {Do Transformer Modifications Transfer Across Implementations and Applications?},
journal = {CoRR},
volume = {abs/2102.11972},
year = {2021},
url = {https://arxiv.org/abs/2102.11972},
eprinttype = {arXiv},
eprint = {2102.11972},
timestamp = {Wed, 24 Nov 2021 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2102-11972.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2103-07579,
author = {Irwan Bello and
William Fedus and
Xianzhi Du and
Ekin D. Cubuk and
Aravind Srinivas and
Tsung{-}Yi Lin and
Jonathon Shlens and
Barret Zoph},
title = {Revisiting ResNets: Improved Training and Scaling Strategies},
journal = {CoRR},
volume = {abs/2103.07579},
year = {2021},
url = {https://arxiv.org/abs/2103.07579},
eprinttype = {arXiv},
eprint = {2103.07579},
timestamp = {Tue, 23 Mar 2021 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2103-07579.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2109-10686,
author = {Yi Tay and
Mostafa Dehghani and
Jinfeng Rao and
William Fedus and
Samira Abnar and
Hyung Won Chung and
Sharan Narang and
Dani Yogatama and
Ashish Vaswani and
Donald Metzler},
title = {Scale Efficiently: Insights from Pre-training and Fine-tuning Transformers},
journal = {CoRR},
volume = {abs/2109.10686},
year = {2021},
url = {https://arxiv.org/abs/2109.10686},
eprinttype = {arXiv},
eprint = {2109.10686},
timestamp = {Mon, 27 Sep 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2109-10686.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2109-11052,
author = {Adrien Ali Ta{\"{\i}}ga and
William Fedus and
Marlos C. Machado and
Aaron C. Courville and
Marc G. Bellemare},
title = {On Bonus-Based Exploration Methods in the Arcade Learning Environment},
journal = {CoRR},
volume = {abs/2109.11052},
year = {2021},
url = {https://arxiv.org/abs/2109.11052},
eprinttype = {arXiv},
eprint = {2109.11052},
timestamp = {Mon, 27 Sep 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2109-11052.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2112-06905,
author = {Nan Du and
Yanping Huang and
Andrew M. Dai and
Simon Tong and
Dmitry Lepikhin and
Yuanzhong Xu and
Maxim Krikun and
Yanqi Zhou and
Adams Wei Yu and
Orhan Firat and
Barret Zoph and
Liam Fedus and
Maarten Bosma and
Zongwei Zhou and
Tao Wang and
Yu Emma Wang and
Kellie Webster and
Marie Pellat and
Kevin Robinson and
Kathy Meier{-}Hellstern and
Toju Duke and
Lucas Dixon and
Kun Zhang and
Quoc V. Le and
Yonghui Wu and
Zhifeng Chen and
Claire Cui},
title = {GLaM: Efficient Scaling of Language Models with Mixture-of-Experts},
journal = {CoRR},
volume = {abs/2112.06905},
year = {2021},
url = {https://arxiv.org/abs/2112.06905},
eprinttype = {arXiv},
eprint = {2112.06905},
timestamp = {Wed, 16 Aug 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2112-06905.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/aaai/JainFLPB20,
author = {Vishal Jain and
William Fedus and
Hugo Larochelle and
Doina Precup and
Marc G. Bellemare},
title = {Algorithmic Improvements for Deep Reinforcement Learning Applied to
Interactive Fiction},
booktitle = {The Thirty-Fourth {AAAI} Conference on Artificial Intelligence, {AAAI}
2020, The Thirty-Second Innovative Applications of Artificial Intelligence
Conference, {IAAI} 2020, The Tenth {AAAI} Symposium on Educational
Advances in Artificial Intelligence, {EAAI} 2020, New York, NY, USA,
February 7-12, 2020},
pages = {4328--4336},
publisher = {{AAAI} Press},
year = {2020},
url = {https://doi.org/10.1609/aaai.v34i04.5857},
doi = {10.1609/AAAI.V34I04.5857},
timestamp = {Mon, 04 Sep 2023 12:29:24 +0200},
biburl = {https://dblp.org/rec/conf/aaai/JainFLPB20.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/iclr/CacciaCFLPC20,
author = {Massimo Caccia and
Lucas Caccia and
William Fedus and
Hugo Larochelle and
Joelle Pineau and
Laurent Charlin},
title = {Language GANs Falling Short},
booktitle = {8th International Conference on Learning Representations, {ICLR} 2020,
Addis Ababa, Ethiopia, April 26-30, 2020},
publisher = {OpenReview.net},
year = {2020},
url = {https://openreview.net/forum?id=BJgza6VtPB},
timestamp = {Thu, 07 May 2020 17:11:47 +0200},
biburl = {https://dblp.org/rec/conf/iclr/CacciaCFLPC20.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/iclr/TaigaFMCB20,
author = {Adrien Ali Ta{\"{\i}}ga and
William Fedus and
Marlos C. Machado and
Aaron C. Courville and
Marc G. Bellemare},
title = {On Bonus Based Exploration Methods In The Arcade Learning Environment},
booktitle = {8th International Conference on Learning Representations, {ICLR} 2020,
Addis Ababa, Ethiopia, April 26-30, 2020},
publisher = {OpenReview.net},
year = {2020},
url = {https://openreview.net/forum?id=BJewlyStDr},
timestamp = {Sat, 30 Sep 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/iclr/TaigaFMCB20.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icml/FedusRABLRD20,
author = {William Fedus and
Prajit Ramachandran and
Rishabh Agarwal and
Yoshua Bengio and
Hugo Larochelle and
Mark Rowland and
Will Dabney},
title = {Revisiting Fundamentals of Experience Replay},
booktitle = {Proceedings of the 37th International Conference on Machine Learning,
{ICML} 2020, 13-18 July 2020, Virtual Event},
series = {Proceedings of Machine Learning Research},
volume = {119},
pages = {3061--3071},
publisher = {{PMLR}},
year = {2020},
url = {http://proceedings.mlr.press/v119/fedus20a.html},
timestamp = {Tue, 15 Dec 2020 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/icml/FedusRABLRD20.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2002-12499,
author = {William Fedus and
Dibya Ghosh and
John D. Martin and
Marc G. Bellemare and
Yoshua Bengio and
Hugo Larochelle},
title = {On Catastrophic Interference in Atari 2600 Games},
journal = {CoRR},
volume = {abs/2002.12499},
year = {2020},
url = {https://arxiv.org/abs/2002.12499},
eprinttype = {arXiv},
eprint = {2002.12499},
timestamp = {Tue, 05 May 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2002-12499.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2007-06700,
author = {William Fedus and
Prajit Ramachandran and
Rishabh Agarwal and
Yoshua Bengio and
Hugo Larochelle and
Mark Rowland and
Will Dabney},
title = {Revisiting Fundamentals of Experience Replay},
journal = {CoRR},
volume = {abs/2007.06700},
year = {2020},
url = {https://arxiv.org/abs/2007.06700},
eprinttype = {arXiv},
eprint = {2007.06700},
timestamp = {Tue, 21 Jul 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2007-06700.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/iclr/GoyalBFSLLLB19,
author = {Anirudh Goyal and
Philemon Brakel and
William Fedus and
Soumye Singhal and
Timothy P. Lillicrap and
Sergey Levine and
Hugo Larochelle and
Yoshua Bengio},
title = {Recall Traces: Backtracking Models for Efficient Reinforcement Learning},
booktitle = {7th International Conference on Learning Representations, {ICLR} 2019,
New Orleans, LA, USA, May 6-9, 2019},
publisher = {OpenReview.net},
year = {2019},
url = {https://openreview.net/forum?id=HygsfnR9Ym},
timestamp = {Thu, 25 Jul 2019 13:03:15 +0200},
biburl = {https://dblp.org/rec/conf/iclr/GoyalBFSLLLB19.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/iclr/VelickovicFHLBH19,
author = {Petar Velickovic and
William Fedus and
William L. Hamilton and
Pietro Li{\`{o}} and
Yoshua Bengio and
R. Devon Hjelm},
title = {Deep Graph Infomax},
booktitle = {7th International Conference on Learning Representations, {ICLR} 2019,
New Orleans, LA, USA, May 6-9, 2019},
publisher = {OpenReview.net},
year = {2019},
url = {https://openreview.net/forum?id=rklz9iAcKQ},
timestamp = {Thu, 25 Jul 2019 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/iclr/VelickovicFHLBH19.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1902-06865,
author = {William Fedus and
Carles Gelada and
Yoshua Bengio and
Marc G. Bellemare and
Hugo Larochelle},
title = {Hyperbolic Discounting and Learning over Multiple Horizons},
journal = {CoRR},
volume = {abs/1902.06865},
year = {2019},
url = {http://arxiv.org/abs/1902.06865},
eprinttype = {arXiv},
eprint = {1902.06865},
timestamp = {Tue, 21 May 2019 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1902-06865.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1908-02388,
author = {Adrien Ali Ta{\"{\i}}ga and
William Fedus and
Marlos C. Machado and
Aaron C. Courville and
Marc G. Bellemare},
title = {Benchmarking Bonus-Based Exploration Methods on the Arcade Learning
Environment},
journal = {CoRR},
volume = {abs/1908.02388},
year = {2019},
url = {http://arxiv.org/abs/1908.02388},
eprinttype = {arXiv},
eprint = {1908.02388},
timestamp = {Fri, 09 Aug 2019 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1908-02388.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1911-12511,
author = {Vishal Jain and
William Fedus and
Hugo Larochelle and
Doina Precup and
Marc G. Bellemare},
title = {Algorithmic Improvements for Deep Reinforcement Learning applied to
Interactive Fiction},
journal = {CoRR},
volume = {abs/1911.12511},
year = {2019},
url = {http://arxiv.org/abs/1911.12511},
eprinttype = {arXiv},
eprint = {1911.12511},
timestamp = {Wed, 08 Jan 2020 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-1911-12511.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/iclr/FedusGD18,
author = {William Fedus and
Ian J. Goodfellow and
Andrew M. Dai},
title = {MaskGAN: Better Text Generation via Filling in the {\_}{\_}{\_}{\_}{\_}{\_}{\_}},
booktitle = {6th International Conference on Learning Representations, {ICLR} 2018,
Vancouver, BC, Canada, April 30 - May 3, 2018, Conference Track Proceedings},
publisher = {OpenReview.net},
year = {2018},
url = {https://openreview.net/forum?id=ByOExmWAb},
timestamp = {Thu, 25 Jul 2019 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/iclr/FedusGD18.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/iclr/FedusRLDMG18,
author = {William Fedus and
Mihaela Rosca and
Balaji Lakshminarayanan and
Andrew M. Dai and
Shakir Mohamed and
Ian J. Goodfellow},
title = {Many Paths to Equilibrium: GANs Do Not Need to Decrease a Divergence
At Every Step},
booktitle = {6th International Conference on Learning Representations, {ICLR} 2018,
Vancouver, BC, Canada, April 30 - May 3, 2018, Conference Track Proceedings},
publisher = {OpenReview.net},
year = {2018},
url = {https://openreview.net/forum?id=ByQpn1ZA-},
timestamp = {Thu, 25 Jul 2019 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/iclr/FedusRLDMG18.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1801-07736,
author = {William Fedus and
Ian J. Goodfellow and
Andrew M. Dai},
title = {MaskGAN: Better Text Generation via Filling in the {\_}{\_}{\_}{\_}{\_}{\_}},
journal = {CoRR},
volume = {abs/1801.07736},
year = {2018},
url = {http://arxiv.org/abs/1801.07736},
eprinttype = {arXiv},
eprint = {1801.07736},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1801-07736.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1802-09484,
author = {Valentin Thomas and
Emmanuel Bengio and
William Fedus and
Jules Pondard and
Philippe Beaudoin and
Hugo Larochelle and
Joelle Pineau and
Doina Precup and
Yoshua Bengio},
title = {Disentangling the independently controllable factors of variation
by interacting with the world},
journal = {CoRR},
volume = {abs/1802.09484},
year = {2018},
url = {http://arxiv.org/abs/1802.09484},
eprinttype = {arXiv},
eprint = {1802.09484},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1802-09484.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1804-00379,
author = {Anirudh Goyal and
Philemon Brakel and
William Fedus and
Timothy P. Lillicrap and
Sergey Levine and
Hugo Larochelle and
Yoshua Bengio},
title = {Recall Traces: Backtracking Models for Efficient Reinforcement Learning},
journal = {CoRR},
volume = {abs/1804.00379},
year = {2018},
url = {http://arxiv.org/abs/1804.00379},
eprinttype = {arXiv},
eprint = {1804.00379},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1804-00379.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1809-10341,
author = {Petar Velickovic and
William Fedus and
William L. Hamilton and
Pietro Li{\`{o}} and
Yoshua Bengio and
R. Devon Hjelm},
title = {Deep Graph Infomax},
journal = {CoRR},
volume = {abs/1809.10341},
year = {2018},
url = {http://arxiv.org/abs/1809.10341},
eprinttype = {arXiv},
eprint = {1809.10341},
timestamp = {Fri, 05 Oct 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1809-10341.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1811-02549,
author = {Massimo Caccia and
Lucas Caccia and
William Fedus and
Hugo Larochelle and
Joelle Pineau and
Laurent Charlin},
title = {Language GANs Falling Short},
journal = {CoRR},
volume = {abs/1811.02549},
year = {2018},
url = {http://arxiv.org/abs/1811.02549},
eprinttype = {arXiv},
eprint = {1811.02549},
timestamp = {Thu, 22 Nov 2018 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-1811-02549.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1710-08446,
author = {William Fedus and
Mihaela Rosca and
Balaji Lakshminarayanan and
Andrew M. Dai and
Shakir Mohamed and
Ian J. Goodfellow},
title = {Many Paths to Equilibrium: GANs Do Not Need to Decrease a Divergence
At Every Step},
journal = {CoRR},
volume = {abs/1710.08446},
year = {2017},
url = {http://arxiv.org/abs/1710.08446},
eprinttype = {arXiv},
eprint = {1710.08446},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1710-08446.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
manage site settings
To protect your privacy, all features that rely on external API calls from your browser are turned off by default. You need to opt-in for them to become active. All settings here will be stored as cookies with your web browser. For more information see our F.A.Q.
last updated on 2024-09-18 01:12 CEST by the dblp team
all metadata released as open data under CC0 1.0 license
see also: Terms of Use | Privacy Policy | Imprint
dblp was originally created in 1993 at:
since 2018, dblp has been operated and maintained by:
the dblp computer science bibliography is funded and supported by:
