Mohammad Pezeshki

36 papers A* 7A 2Journal 24Unranked 3
YearRankTypeTitle / Venue / Authors
2026 J jnl
ReasonCACHE: Teaching LLMs To Reason Without Weight Updates.
CoRR
Sharut Gupta, Phillip Isola, Stefanie Jegelka, David Lopez-Paz, Kartik Ahuja, Mark Ibrahim, Mohammad Pezeshki
2025 J jnl
Beyond Multi-Token Prediction: Pretraining LLMs with Future Summaries.
CoRR
Divyat Mahajan, Sachin Goyal, Badr Youbi Idrissi, Mohammad Pezeshki, Ioannis Mitliagkas, David Lopez-Paz, Kartik Ahuja
2025 A* conf
Compositional Risk Minimization.
ICML
Divyat Mahajan, Mohammad Pezeshki, Charles Arnal, Ioannis Mitliagkas, Kartik Ahuja, Pascal Vincent
2025 A* conf
Improving the Scaling Laws of Synthetic Data with Deliberate Practice.
ICML
Reyhane Askari Hemmat, Mohammad Pezeshki, Elvis Dohmatob, Florian Bordes, Pietro Astolfi, Melissa Hall, Jakob Verbeek, Michal Drozdzal, Adriana Romero-Soriano
2025 J jnl
Improving the Scaling Laws of Synthetic Data with Deliberate Practice.
CoRR
Reyhane Askari Hemmat, Mohammad Pezeshki, Elvis Dohmatob, Florian Bordes, Pietro Astolfi, Melissa Hall, Jakob Verbeek, Michal Drozdzal, Adriana Romero-Soriano
2025 J jnl
Iterative Amortized Inference: Unifying In-Context Learning and Learned Optimizers.
CoRR
Sarthak Mittal, Divyat Mahajan, Guillaume Lajoie, Mohammad Pezeshki
2025 J jnl
Steering Large Language Model Activations in Sparse Spaces.
CoRR
Reza Bayat, Ali Rahimi-Kalahroudi, Mohammad Pezeshki, Sarath Chandar, Pascal Vincent
2025 A* conf
The Pitfalls of Memorization: When Memorization Hurts Generalization.
ICLR
Reza Bayat, Mohammad Pezeshki, Elvis Dohmatob, David Lopez-Paz, Pascal Vincent
2025 J jnl
Unveiling Simplicities of Attention: Adaptive Long-Context Head Identification.
CoRR
Konstantin Donhauser, Charles Arnal, Mohammad Pezeshki, Vivien Cabannes, David Lopez-Paz, Kartik Ahuja
2025 J jnl
Why Less is More (Sometimes): A Theory of Data Curation.
CoRR
Elvis Dohmatob, Mohammad Pezeshki, Reyhane Askari Hemmat
2024 J jnl
Compositional Risk Minimization.
CoRR
Divyat Mahajan, Mohammad Pezeshki, Ioannis Mitliagkas, Kartik Ahuja, Pascal Vincent
2024 A* conf
Discovering Environments with XRM.
ICML
Mohammad Pezeshki, Diane Bouchacourt, Mark Ibrahim, Nicolas Ballas, Pascal Vincent, David Lopez-Paz
2024 J jnl
Feedback-guided Data Synthesis for Imbalanced Classification.
Trans. Mach. Learn. Res.
Reyhane Askari Hemmat, Mohammad Pezeshki, Florian Bordes, Michal Drozdzal, Adriana Romero-Soriano
2024 J jnl
The Pitfalls of Memorization: When Memorization Hurts Generalization.
CoRR
Reza Bayat, Mohammad Pezeshki, Elvis Dohmatob, David Lopez-Paz, Pascal Vincent
2023 J jnl
Discovering environments with XRM.
CoRR
Mohammad Pezeshki, Diane Bouchacourt, Mark Ibrahim, Nicolas Ballas, Pascal Vincent, David Lopez-Paz
2023 J jnl
Feedback-guided Data Synthesis for Imbalanced Classification.
CoRR
Reyhane Askari Hemmat, Mohammad Pezeshki, Florian Bordes, Michal Drozdzal, Adriana Romero-Soriano
2023 J jnl
Predicting Grokking Long Before it Happens: A look into the loss landscape of models which grok.
CoRR
Pascal Tikeng Notsawo Jr., Hattie Zhou, Mohammad Pezeshki, Irina Rish, Guillaume Dumas
2022 A* conf
Multi-scale Feature Learning Dynamics: Insights for Double Descent.
ICML
Mohammad Pezeshki, Amartya Mitra, Yoshua Bengio, Guillaume Lajoie
2022 — conf
Simple data balancing achieves competitive worst-group-accuracy.
CLeaR
Badr Youbi Idrissi, Martín Arjovsky, Mohammad Pezeshki, David Lopez-Paz
2021 A* conf
Gradient Starvation: A Learning Proclivity in Neural Networks.
NeurIPS
Mohammad Pezeshki, Sékou-Oumar Kaba, Yoshua Bengio, Aaron C. Courville, Doina Precup, Guillaume Lajoie
2021 J jnl
Multi-scale Feature Learning Dynamics: Insights for Double Descent.
CoRR
Mohammad Pezeshki, Amartya Mitra, Yoshua Bengio, Guillaume Lajoie
2021 J jnl
Simple data balancing achieves competitive worst-group-accuracy.
CoRR
Badr Youbi Idrissi, Martín Arjovsky, Mohammad Pezeshki, David Lopez-Paz
2020 J jnl
Gradient Starvation: A Learning Proclivity in Neural Networks.
CoRR
Mohammad Pezeshki, Sékou-Oumar Kaba, Yoshua Bengio, Aaron C. Courville, Doina Precup, Guillaume Lajoie
2019 A conf
Negative Momentum for Improved Game Dynamics.
AISTATS
Gauthier Gidel, Reyhane Askari Hemmat, Mohammad Pezeshki, Rémi Le Priol, Gabriel Huang, Simon Lacoste-Julien, Ioannis Mitliagkas
2018 J jnl
Negative Momentum for Improved Game Dynamics.
CoRR
Gauthier Gidel, Reyhane Askari Hemmat, Mohammad Pezeshki, Gabriel Huang, Rémi Le Priol, Simon Lacoste-Julien, Ioannis Mitliagkas
2018 J jnl
On the Learning Dynamics of Deep Neural Networks.
CoRR
Remi Tachet des Combes, Mohammad Pezeshki, Samira Shabanian, Aaron C. Courville, Yoshua Bengio
2017 J jnl
Towards End-to-End Speech Recognition with Deep Convolutional Neural Networks.
CoRR
Ying Zhang, Mohammad Pezeshki, Philemon Brakel, Saizheng Zhang, César Laurent, Yoshua Bengio, Aaron C. Courville
2017 — conf
Zoneout: Regularizing RNNs by Randomly Preserving Hidden Activations.
ICLR (Poster)
David Krueger, Tegan Maharaj, János Kramár, Mohammad Pezeshki, Nicolas Ballas, Nan Rosemary Ke, Anirudh Goyal, Yoshua Bengio, Aaron C. Courville, Christopher J. Pal
2016 A* conf
Deconstructing the Ladder Network Architecture.
ICML
Mohammad Pezeshki, Linxi Fan, Philemon Brakel, Aaron C. Courville, Yoshua Bengio
2016 J jnl
Theano: A Python framework for fast computation of mathematical expressions.
CoRR
Rami Al-Rfou, Guillaume Alain, Amjad Almahairi, Christof Angermüller, Dzmitry Bahdanau, Nicolas Ballas, Frédéric Bastien, Justin Bayer, Anatoly Belikov, Alexander Belopolsky, Yoshua Bengio, Arnaud Bergeron, James Bergstra, Valentin Bisson, Josh Bleecher Snyder, Nicolas Bouchard, Nicolas Boulanger-Lewandowski, Xavier Bouthillier, Alexandre de Brébisson, Olivier Breuleux, Pierre Luc Carrier, Kyunghyun Cho, Jan Chorowski, Paul F. Christiano, Tim Cooijmans, Marc-Alexandre Côté, Myriam Côté, Aaron C. Courville, Yann N. Dauphin, Olivier Delalleau, Julien Demouth, Guillaume Desjardins, Sander Dieleman, Laurent Dinh, Melanie Ducoffe, Vincent Dumoulin, Samira Ebrahimi Kahou, Dumitru Erhan, Ziye Fan, Orhan Firat, Mathieu Germain, Xavier Glorot, Ian J. Goodfellow, Matthew Graham, Çaglar Gülçehre, Philippe Hamel, Iban Harlouchet, Jean-Philippe Heng, Balázs Hidasi, Sina Honari, Arjun Jain, Sébastien Jean, Kai Jia, Mikhail Korobov, Vivek Kulkarni, Alex Lamb, Pascal Lamblin, Eric Larsen, César Laurent, Sean Lee, Simon Lefrançois, Simon Lemieux, Nicholas Léonard, Zhouhan Lin, Jesse A. Livezey, Cory Lorenz, Jeremiah Lowin, Qianli Ma, Pierre-Antoine Manzagol, Olivier Mastropietro, Robert McGibbon, Roland Memisevic, Bart van Merriënboer, Vincent Michalski, Mehdi Mirza, Alberto Orlandi, Christopher Joseph Pal, Razvan Pascanu, Mohammad Pezeshki, Colin Raffel, Daniel Renshaw, Matthew Rocklin, Adriana Romero, Markus Roth, Peter Sadowski, John Salvatier, François Savard, Jan Schlüter, John Schulman, Gabriel Schwartz, Iulian Vlad Serban, Dmitriy Serdyuk, Samira Shabanian, Étienne Simon, Sigurd Spieckermann, S. Ramana Subramanyam, Jakub Sygnowski, Jérémie Tanguay, Gijs van Tulder, Joseph P. Turian, Sebastian Urban, Pascal Vincent, Francesco Visin, Harm de Vries, David Warde-Farley, Dustin J. Webb, Matthew Willson, Kelvin Xu, Lijun Xue, Li Yao, Saizheng Zhang, Ying Zhang
2016 A conf
Towards End-to-End Speech Recognition with Deep Convolutional Neural Networks.
INTERSPEECH
Ying Zhang, Mohammad Pezeshki, Philémon Brakel, Saizheng Zhang, César Laurent, Yoshua Bengio, Aaron C. Courville
2016 J jnl
Zoneout: Regularizing RNNs by Randomly Preserving Hidden Activations.
CoRR
David Krueger, Tegan Maharaj, János Kramár, Mohammad Pezeshki, Nicolas Ballas, Nan Rosemary Ke, Anirudh Goyal, Yoshua Bengio, Hugo Larochelle, Aaron C. Courville, Chris Pal
2015 J jnl
Deconstructing the Ladder Network Architecture.
CoRR
Mohammad Pezeshki, Linxi Fan, Philemon Brakel, Aaron C. Courville, Yoshua Bengio
2015 J jnl
Sequence Modeling using Gated Recurrent Neural Networks.
CoRR
Mohammad Pezeshki
2014 — conf
Deep Belief Networks for Image Denoising.
ICLR (Workshop Poster)
Mohammad Ali Keyvanrad, Mohammad Pezeshki, Mohammad Ali Homayounpour
2013 J jnl
Distinction between features extracted using deep belief networks.
CoRR
Mohammad Pezeshki, Sajjad Gholami, Ahmad Nickabadi