default search action
Paul Michel
Person information
Refine list
refinements active!
zoomed in on ?? of ?? records
view refined list in
export refined list as
2020 – today
- 2024
- [c20]Mathieu Rita, Florian Strub, Rahma Chaabouni, Paul Michel, Emmanuel Dupoux, Olivier Pietquin:
Countering Reward Over-Optimization in LLM with Demonstration-Guided Reinforcement Learning. ACL (Findings) 2024: 12447-12472 - [i23]Mathieu Rita, Paul Michel, Rahma Chaabouni, Olivier Pietquin, Emmanuel Dupoux, Florian Strub:
Language Evolution with Deep Learning. CoRR abs/2403.11958 (2024) - [i22]Mathieu Rita, Florian Strub, Rahma Chaabouni, Paul Michel, Emmanuel Dupoux, Olivier Pietquin:
Countering Reward Over-optimization in LLM with Demonstration-Guided Reinforcement Learning. CoRR abs/2404.19409 (2024) - [i21]Heri Zhao, Jeffrey Hui, Joshua Howland, Nam Nguyen, Siqi Zuo, Andrea Hu, Christopher A. Choquette-Choo, Jingyue Shen, Joe Kelley, Kshitij Bansal, Luke Vilnis, Mateo Wirth, Paul Michel, Peter Choy, Pratik Joshi, Ravin Kumar, Sarmad Hashmi, Shubham Agrawal, Zhitao Gong, Jane Fine, Tris Warkentin, Ale Jakse Hartman, Bin Ni, Kathy Korevec, Kelly Schaefer, Scott Huffman:
CodeGemma: Open Code Models Based on Gemma. CoRR abs/2406.11409 (2024) - 2023
- [c19]Lucio M. Dery, Paul Michel, Mikhail Khodak, Graham Neubig, Ameet Talwalkar:
AANG : Automating Auxiliary Learning. ICLR 2023 - [c18]Paul Michel, Mathieu Rita, Kory Wallace Mathewson, Olivier Tieleman, Angeliki Lazaridou:
Revisiting Populations in multi-agent Communication. ICLR 2023 - [c17]Valentin Taillandier, Dieuwke Hupkes, Benoît Sagot, Emmanuel Dupoux, Paul Michel:
Neural Agents Struggle to Take Turns in Bidirectional Emergent Communication. ICLR 2023 - [i20]Lucas Weber, Jaap Jumelet, Paul Michel, Elia Bruni, Dieuwke Hupkes:
Curriculum Learning with Adam: The Devil Is in the Wrong Details. CoRR abs/2308.12202 (2023) - 2022
- [c16]Lucio M. Dery, Paul Michel, Ameet Talwalkar, Graham Neubig:
Should We Be Pre-training? An Argument for End-task Aware Training as an Alternative. ICLR 2022 - [c15]Paul Michel, Tatsunori Hashimoto, Graham Neubig:
Distributionally Robust Models with Parametric Likelihood Ratios. ICLR 2022 - [c14]Mathieu Rita, Corentin Tallec, Paul Michel, Jean-Bastien Grill, Olivier Pietquin, Emmanuel Dupoux, Florian Strub:
Emergent Communication: Generalization and Overfitting in Lewis Games. NeurIPS 2022 - [i19]Paul Michel, Tatsunori Hashimoto, Graham Neubig:
Distributionally Robust Models with Parametric Likelihood Ratios. CoRR abs/2204.06340 (2022) - [i18]Lucio M. Dery, Paul Michel, Mikhail Khodak, Graham Neubig, Ameet Talwalkar:
AANG: Automating Auxiliary Learning. CoRR abs/2205.14082 (2022) - [i17]Mathieu Rita, Corentin Tallec, Paul Michel, Jean-Bastien Grill, Olivier Pietquin, Emmanuel Dupoux, Florian Strub:
Emergent Communication: Generalization and Overfitting in Lewis Games. CoRR abs/2209.15342 (2022) - 2021
- [c13]Paul Michel, Tatsunori Hashimoto, Graham Neubig:
Modeling the Second Player in Distributionally Robust Optimization. ICLR 2021 - [c12]Chunting Zhou, Xuezhe Ma
, Paul Michel, Graham Neubig:
Examining and Combating Spurious Features under Distribution Shift. ICML 2021: 12857-12867 - [i16]Paul Michel, Tatsunori Hashimoto, Graham Neubig:
Modeling the Second Player in Distributionally Robust Optimization. CoRR abs/2103.10282 (2021) - [i15]Chunting Zhou, Xuezhe Ma, Paul Michel, Graham Neubig:
Examining and Combating Spurious Features under Distribution Shift. CoRR abs/2106.07171 (2021) - [i14]Paul Michel:
Learning Neural Models for Natural Language Processing in the Face of Distributional Shift. CoRR abs/2109.01558 (2021) - [i13]Lucio M. Dery, Paul Michel, Ameet Talwalkar, Graham Neubig:
Should We Be Pre-training? An Argument for End-task Aware Training as an Alternative. CoRR abs/2109.07437 (2021) - [i12]Paul Michel, Sebastian Ruder, Dani Yogatama:
Balancing Average and Worst-case Accuracy in Multitask Learning. CoRR abs/2110.05838 (2021) - 2020
- [c11]Keita Kurita, Paul Michel, Graham Neubig:
Weight Poisoning Attacks on Pretrained Models. ACL 2020: 2793-2806 - [c10]Xinyi Wang, Hieu Pham, Paul Michel, Antonios Anastasopoulos, Jaime G. Carbonell, Graham Neubig:
Optimizing Data Usage via Differentiable Rewards. ICML 2020: 9983-9995 - [c9]Lucia Specia, Zhenhao Li, Juan Miguel Pino, Vishrav Chaudhary, Francisco Guzmán, Graham Neubig, Nadir Durrani, Yonatan Belinkov, Philipp Koehn, Hassan Sajjad, Paul Michel, Xian Li:
Findings of the WMT 2020 Shared Task on Machine Translation Robustness. WMT@EMNLP 2020: 76-91 - [i11]Keita Kurita, Paul Michel, Graham Neubig:
Weight Poisoning Attacks on Pre-trained Models. CoRR abs/2004.06660 (2020)
2010 – 2019
- 2019
- [c8]Graham Neubig, Zi-Yi Dou, Junjie Hu, Paul Michel, Danish Pruthi, Xinyi Wang:
compare-mt: A Tool for Holistic Comparison of Language Generation Systems. NAACL-HLT (Demonstrations) 2019: 35-41 - [c7]Paul Michel, Xian Li, Graham Neubig, Juan Miguel Pino:
On Evaluation of Adversarial Perturbations for Sequence-to-Sequence Models. NAACL-HLT (1) 2019: 3103-3114 - [c6]Paul Michel, Omer Levy, Graham Neubig:
Are Sixteen Heads Really Better than One? NeurIPS 2019: 14014-14024 - [c5]Xian Li, Paul Michel, Antonios Anastasopoulos, Yonatan Belinkov, Nadir Durrani, Orhan Firat, Philipp Koehn, Graham Neubig, Juan Miguel Pino, Hassan Sajjad:
Findings of the First Shared Task on Machine Translation Robustness. WMT (2) 2019: 91-102 - [i10]Paul Michel, Xian Li, Graham Neubig, Juan Miguel Pino:
On Evaluation of Adversarial Perturbations for Sequence-to-Sequence Models. CoRR abs/1903.06620 (2019) - [i9]Graham Neubig, Zi-Yi Dou, Junjie Hu, Paul Michel, Danish Pruthi, Xinyi Wang:
compare-mt: A Tool for Holistic Comparison of Language Generation Systems. CoRR abs/1903.07926 (2019) - [i8]Paul Michel, Omer Levy, Graham Neubig:
Are Sixteen Heads Really Better than One? CoRR abs/1905.10650 (2019) - [i7]Xian Li, Paul Michel, Antonios Anastasopoulos, Yonatan Belinkov, Nadir Durrani, Orhan Firat, Philipp Koehn, Graham Neubig, Juan Miguel Pino, Hassan Sajjad:
Findings of the First Shared Task on Machine Translation Robustness. CoRR abs/1906.11943 (2019) - [i6]Xinyi Wang, Hieu Pham, Paul Michel, Antonios Anastasopoulos, Graham Neubig, Jaime G. Carbonell:
Optimizing Data Usage via Differentiable Rewards. CoRR abs/1911.10088 (2019) - 2018
- [c4]Paul Michel, Graham Neubig:
Extreme Adaptation for Personalized Neural Machine Translation. ACL (2) 2018: 312-318 - [c3]Paul Michel, Graham Neubig:
MTNT: A Testbed for Machine Translation of Noisy Text. EMNLP 2018: 543-553 - [i5]Paul Michel, Graham Neubig:
Extreme Adaptation for Personalized Neural Machine Translation. CoRR abs/1805.01817 (2018) - [i4]Paul Michel, Graham Neubig:
MTNT: A Testbed for Machine Translation of Noisy Text. CoRR abs/1809.00388 (2018) - 2017
- [c2]Paul Michel, Okko Räsänen
Blind Phoneme Segmentation With Temporal Prediction Errors. ACL (Student Research Workshop) 2017: 62-68 - [c1]Paul Michel, Abhilasha Ravichander, Shruti Rijhwani:
Does the Geometry of Word Embeddings Help Document Classification? A Case Study on Persistent Homology-Based Representations. Rep4NLP@ACL 2017: 235-240 - [i3]Graham Neubig, Chris Dyer, Yoav Goldberg, Austin Matthews, Waleed Ammar, Antonios Anastasopoulos, Miguel Ballesteros, David Chiang, Daniel Clothiaux, Trevor Cohn, Kevin Duh, Manaal Faruqui, Cynthia Gan, Dan Garrette, Yangfeng Ji, Lingpeng Kong, Adhiguna Kuncoro, Gaurav Kumar, Chaitanya Malaviya, Paul Michel, Yusuke Oda, Matthew Richardson, Naomi Saphra, Swabha Swayamdipta, Pengcheng Yin:
DyNet: The Dynamic Neural Network Toolkit. CoRR abs/1701.03980 (2017) - [i2]Paul Michel, Abhilasha Ravichander, Shruti Rijhwani:
Does the Geometry of Word Embeddings Help Document Classification? A Case Study on Persistent Homology Based Representations. CoRR abs/1705.10900 (2017) - 2016
- [i1]Paul Michel, Okko Räsänen, Roland Thiollière, Emmanuel Dupoux
Improving Phoneme segmentation with Recurrent Neural Networks. CoRR abs/1608.00508 (2016)
Coauthor Index
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.
Unpaywalled article links
Add open access links from to the list of external document links (if available).
Privacy notice: By enabling the option above, your browser will contact the API of unpaywall.org to load hyperlinks to open access articles. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the Unpaywall privacy policy.
Archived links via Wayback Machine
For web page which are no longer available, try to retrieve content from the of the Internet Archive (if available).
Privacy notice: By enabling the option above, your browser will contact the API of archive.org to check for archived content of web pages that are no longer available. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the Internet Archive privacy policy.
Reference lists
Add a list of references from ,
, and
to record detail pages.
load references from crossref.org and opencitations.net
Privacy notice: By enabling the option above, your browser will contact the APIs of crossref.org, opencitations.net, and semanticscholar.org to load article reference information. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the Crossref privacy policy and the OpenCitations privacy policy, as well as the AI2 Privacy Policy covering Semantic Scholar.
Citation data
Add a list of citing articles from and
to record detail pages.
load citations from opencitations.net
Privacy notice: By enabling the option above, your browser will contact the API of opencitations.net and semanticscholar.org to load citation information. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the OpenCitations privacy policy as well as the AI2 Privacy Policy covering Semantic Scholar.
OpenAlex data
Load additional information about publications from .
Privacy notice: By enabling the option above, your browser will contact the API of openalex.org to load additional information. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the information given by OpenAlex.
last updated on 2024-09-26 00:58 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: