Razvan Pascanu

248 papers A* 46A 2B 1Misc 3Journal 155Unranked 37
YearRankTypeTitle / Venue / Authors
2026 J jnl
A Survey on Over-smoothing and Over-squashing: Unified Propagation Perspectives on Graph Neural Networks and Transformers.
Trans. Mach. Learn. Res.
Alvaro Arroyo, Federico Barbero, Hugh Blayney, Michael M. Bronstein, Xiaowen Dong, Pietro Lio, Razvan Pascanu, Pierre Vandergheynst
2026 J jnl
Mining Generalizable Activation Functions.
CoRR
Alex Vitvitskyi, Michael Boratko, Matej Grcic, Razvan Pascanu, Deep Shah, Petar Velickovic
2026 J jnl
Perplexity Cannot Always Tell Right from Wrong.
CoRR
Petar Velickovic, Federico Barbero, Christos Perivolaropoulos, Simon Osindero, Razvan Pascanu
2026 J jnl
TRecViT: A Recurrent Video Transformer.
Trans. Mach. Learn. Res.
Viorica Patraucean, Xu Owen He, Joseph Heyward, Chuhan Zhang, Mehdi S. M. Sajjadi, George-Cristian Muraru, Artem Zholus, Mahdi Karami, Ross Goroshin, Yutian Chen, Simon Osindero, João Carreira, Razvan Pascanu
2025 A* conf
A Large Recurrent Action Model: xLSTM enables Fast Inference for Robotics Tasks.
ICML
Thomas Schmied, Thomas Adler, Vihang Prakash Patil, Maximilian Beck, Korbinian Pöppel, Johannes Brandstetter, Günter Klambauer, Razvan Pascanu, Sepp Hochreiter
2025 J jnl
Agency Is Frame-Dependent.
CoRR
David Abel, André Barreto, Michael Bowling, Will Dabney, Shi Dong, Steven Hansen, Anna Harutyunyan, Khimya Khetarpal, Clare Lyle, Razvan Pascanu, Georgios Piliouras, Doina Precup, Jonathan Richens, Mark Rowland, Tom Schaul, Satinder Singh
2025 A* conf
Attention as a Hypernetwork.
ICLR
Simon Schug, Seijin Kobayashi, Yassir Akram, João Sacramento, Razvan Pascanu
2025 J jnl
Filter Equivariant Functions: A symmetric account of length-general extrapolation on lists.
CoRR
Owen Lewis, Neil Ghani, Andrew Dudzik, Christos Perivolaropoulos, Razvan Pascanu, Petar Velickovic
2025 J jnl
Fine-Tuned In-Context Learners for Efficient Adaptation.
CoRR
Jörg Bornschein, Clare Lyle, Yazhe Li, Amal Rannen-Triki, Xu Owen He, Razvan Pascanu
2025 J jnl
From Markov to Laplace: How Mamba In-Context Learns Markov Chains.
CoRR
Marco Bondaschi, Nived Rajaraman, Xiuying Wei, Kannan Ramchandran, Razvan Pascanu, Caglar Gulcehre, Michael Gastpar, Ashok Vardhan Makkuva
2025 J jnl
Hadamard Product in Deep Learning: Introduction, Advances and Challenges.
IEEE Trans. Pattern Anal. Mach. Intell.
Grigorios G. Chrysos, Yongtao Wu, Razvan Pascanu, Philip H. S. Torr, Volkan Cevher
2025 J jnl
Hadamard product in deep learning: Introduction, Advances and Challenges.
CoRR
Grigorios G. Chrysos, Yongtao Wu, Razvan Pascanu, Philip Torr, Volkan Cevher
2025 J jnl
How Overconfidence in Initial Choices and Underconfidence Under Criticism Modulate Change of Mind in Large Language Models.
CoRR
Dharshan Kumaran, Stephen M. Fleming, Larisa Markeeva, Joe Heyward, Andrea Banino, Mrinal Mathur, Razvan Pascanu, Simon Osindero, Benedetto De Martino, Petar Velickovic, Viorica Patraucean
2025 J jnl
How do language models learn facts? Dynamics, curricula and hallucinations.
CoRR
Nicolas Zucchet, Jörg Bornschein, Stephanie C. Y. Chan, Andrew K. Lampinen, Razvan Pascanu, Soham De
2025 J jnl
LLMs are Greedy Agents: Effects of RL Fine-tuning on Decision-Making Abilities.
CoRR
Thomas Schmied, Jörg Bornschein, Jordi Grau-Moya, Markus Wulfmeier, Razvan Pascanu
2025 J jnl
MS-SSM: A Multi-Scale State Space Model for Efficient Sequence Modeling.
CoRR
Mahdi Karami, Ali Behrouz, Peilin Zhong, Razvan Pascanu, Vahab Mirrokni
2025 J jnl
Maxwell's Demon at Work: Efficient Pruning by Leveraging Saturation of Neurons.
Trans. Mach. Learn. Res.
Simon Dufort-Labbé, Pierluca D'Oro, Evgenii Nikishin, Irina Rish, Pierre-Luc Bacon, Razvan Pascanu, Aristide Baratin
2025 J jnl
MesaNet: Sequence Modeling by Locally Optimal Test-Time Training.
CoRR
Johannes von Oswald, Nino Scherrer, Seijin Kobayashi, Luca Versari, Songlin Yang, Maximilian Schlegel, Kaitlin Maile, Yanick Schimpf, Oliver Sieberling, Alexander Meulemans, Rif A. Saurous, Guillaume Lajoie, Charlotte Frenkel, Razvan Pascanu, Blaise Agüera y Arcas, João Sacramento
2025 J jnl
Meta-learning how to Share Credit among Macro-Actions.
CoRR
Ionel-Alexandru Hosu, Traian Rebedea, Razvan Pascanu
2025 J jnl
NoProp: Training Neural Networks without Back-propagation or Forward-propagation.
CoRR
Qinyu Li, Yee Whye Teh, Razvan Pascanu
2025 J jnl
On the generalization of language models from in-context learning and finetuning: a controlled study.
CoRR
Andrew K. Lampinen, Arslan Chaudhry, Stephanie C. Y. Chan, Cody Wild, Diane Wan, Alex Ku, Jörg Bornschein, Razvan Pascanu, Murray Shanahan, James L. McClelland
2025 J jnl
Optimizers Qualitatively Alter Solutions And We Should Leverage This.
CoRR
Razvan Pascanu, Clare Lyle, Ionut-Vlad Modoranu, Naima Elosegui Borras, Dan Alistarh, Petar Velickovic, Sarath Chandar, Soham De, James Martens
2025 J jnl
Plasticity as the Mirror of Empowerment.
CoRR
David Abel, Michael Bowling, André Barreto, Will Dabney, Shi Dong, Steven Hansen, Anna Harutyunyan, Khimya Khetarpal, Clare Lyle, Razvan Pascanu, Georgios Piliouras, Doina Precup, Jonathan Richens, Mark Rowland, Tom Schaul, Satinder Singh
2025 J jnl
RAT: Bridging RNN Efficiency and Attention Accuracy in Language Modeling.
CoRR
Xiuying Wei, Anunay Yadav, Razvan Pascanu, Caglar Gulcehre
2025 A* conf
Round and Round We Go! What makes Rotary Positional Encodings useful?
ICLR
Federico Barbero, Alex Vitvitskyi, Christos Perivolaropoulos, Razvan Pascanu, Petar Velickovic
2025 A* conf
Softmax is not Enough (for Sharp Size Generalisation).
ICML
Petar Velickovic, Christos Perivolaropoulos, Federico Barbero, Razvan Pascanu
2025 J jnl
Unpacking Softmax: How Temperature Drives Representation Collapse, Compression, and Generalization.
CoRR
Wojciech Masarczyk, Mateusz Ostaszewski, Tin Sum Cheng, Tomasz Trzcinski, Aurélien Lucchi, Razvan Pascanu
2025 J jnl
What Can Grokking Teach Us About Learning Under Nonstationarity?
CoRR
Clare Lyle, Ghada Sokar, Razvan Pascanu, András György
2025 J jnl
Why do LLMs attend to the first token?
CoRR
Federico Barbero, Alvaro Arroyo, Xiangming Gu, Christos Perivolaropoulos, Michael M. Bronstein, Petar Velickovic, Razvan Pascanu
2024 J jnl
A Large Recurrent Action Model: xLSTM enables Fast Inference for Robotics Tasks.
CoRR
Thomas Schmied, Thomas Adler, Vihang Patil, Maximilian Beck, Korbinian Pöppel, Johannes Brandstetter, Günter Klambauer, Razvan Pascanu, Sepp Hochreiter
2024 J jnl
Attention as a Hypernetwork.
CoRR
Simon Schug, Seijin Kobayashi, Yassir Akram, João Sacramento, Razvan Pascanu
2024 A* conf
Building on Efficient Foundations: Effective Training of LLMs with Structured Feedforward Layers.
NeurIPS
Xiuying Wei, Skander Moalla, Razvan Pascanu, Caglar Gulcehre
2024 J jnl
Building on Efficient Foundations: Effectively Training LLMs with Structured Feedforward Layers.
CoRR
Xiuying Wei, Skander Moalla, Razvan Pascanu, Caglar Gulcehre
2024 — ed.
Conference on Lifelong Learning Agents, 29-1 August 2024, University of Pisa, Pisa, Italy.
CoLLAs
Vincenzo Lomonaco, Stefano Melacci, Tinne Tuytelaars, Sarath Chandar, Razvan Pascanu
2024 J jnl
Continual Learning: Applications and the Road Forward.
Trans. Mach. Learn. Res.
Eli Verwimp, Rahaf Aljundi, Shai Ben-David, Matthias Bethge, Andrea Cossu, Alexander Gepperth, Tyler L. Hayes, Eyke Hüllermeier, Christopher Kanan, Dhireesha Kudithipudi, Christoph H. Lampert, Martin Mundt, Razvan Pascanu, Adrian Popescu, Andreas S. Tolias, Joost van de Weijer, Bing Liu, Vincenzo Lomonaco, Tinne Tuytelaars, Gido M. van de Ven
2024 J jnl
Deep Grokking: Would Deep Neural Networks Generalize Better?
CoRR
Simin Fan, Razvan Pascanu, Martin Jaggi
2024 A* conf
Discovering modular solutions that generalize compositionally.
ICLR
Simon Schug, Seijin Kobayashi, Yassir Akram, Maciej Wolczyk, Alexandra Maria Proca, Johannes von Oswald, Razvan Pascanu, João Sacramento, Angelika Steger
2024 — conf
Disentangling the Causes of Plasticity Loss in Neural Networks.
CoLLAs
Clare Lyle, Zeyu Zheng, Khimya Khetarpal, Hado van Hasselt, Razvan Pascanu, James Martens, Will Dabney
2024 J jnl
Disentangling the Causes of Plasticity Loss in Neural Networks.
CoRR
Clare Lyle, Zeyu Zheng, Khimya Khetarpal, Hado van Hasselt, Razvan Pascanu, James Martens, Will Dabney
2024 A* conf
Fine-tuning Reinforcement Learning Models is Secretly a Forgetting Mitigation Problem.
ICML
Maciej Wolczyk, Bartlomiej Cupial, Mateusz Ostaszewski, Michal Bortkiewicz, Michal Zajac, Razvan Pascanu, Lukasz Kucinski, Piotr Milos
2024 J jnl
Fine-tuning Reinforcement Learning Models is Secretly a Forgetting Mitigation Problem.
CoRR
Maciej Wolczyk, Bartlomiej Cupial, Mateusz Ostaszewski, Michal Bortkiewicz, Michal Zajac, Razvan Pascanu, Lukasz Kucinski, Piotr Milos
2024 J jnl
Griffin: Mixing Gated Linear Recurrences with Local Attention for Efficient Language Models.
CoRR
Soham De, Samuel L. Smith, Anushan Fernando, Aleksandar Botev, George-Cristian Muraru, Albert Gu, Ruba Haroun, Leonard Berrada, Yutian Chen, Srivatsan Srinivasan, Guillaume Desjardins, Arnaud Doucet, David Budden, Yee Whye Teh, Razvan Pascanu, Nando de Freitas, Caglar Gulcehre
2024 A* conf
Improving fine-grained understanding in image-text pre-training.
ICML
Ioana Bica, Anastasija Ilic, Matthias Bauer, Goker Erdogan, Matko Bosnjak, Christos Kaplanis, Alexey A. Gritsenko, Matthias Minderer, Charles Blundell, Razvan Pascanu, Jovana Mitrovic
2024 J jnl
Improving fine-grained understanding in image-text pre-training.
CoRR
Ioana Bica, Anastasija Ilic, Matthias Bauer, Goker Erdogan, Matko Bosnjak, Christos Kaplanis, Alexey A. Gritsenko, Matthias Minderer, Charles Blundell, Razvan Pascanu, Jovana Mitrovic
2024 J jnl
Investigating Low-Rank Training in Transformer Language Models: Efficiency and Scaling Analysis.
CoRR
Xiuying Wei, Skander Moalla, Razvan Pascanu, Caglar Gulcehre
2024 A* conf
Kalman Filter for Online Classification of Non-Stationary Data.
ICLR
Michalis K. Titsias, Alexandre Galashov, Amal Rannen-Triki, Razvan Pascanu, Yee Whye Teh, Jörg Bornschein
2024 J jnl
Maxwell's Demon at Work: Efficient Pruning by Leveraging Saturation of Neurons.
CoRR
Simon Dufort-Labbé, Pierluca D'Oro, Evgenii Nikishin, Razvan Pascanu, Pierre-Luc Bacon, Aristide Baratin
2024 A* conf
No Representation, No Trust: Connecting Representation, Collapse, and Trust Issues in PPO.
NeurIPS
Skander Moalla, Andrea Miele, Daniil Pyatko, Razvan Pascanu, Caglar Gulcehre
2024 J jnl
No Representation, No Trust: Connecting Representation, Collapse, and Trust Issues in PPO.
CoRR
Skander Moalla, Andrea Miele, Razvan Pascanu, Caglar Gulcehre
2024 A* conf
Non-Stationary Learning of Neural Networks with Automatic Soft Parameter Reset.
NeurIPS
Alexandre Galashov, Michalis K. Titsias, András György, Clare Lyle, Razvan Pascanu, Yee Whye Teh, Maneesh Sahani
2024 J jnl
Non-Stationary Learning of Neural Networks with Automatic Soft Parameter Reset.
CoRR
Alexandre Galashov, Michalis K. Titsias, András György, Clare Lyle, Razvan Pascanu, Yee Whye Teh, Maneesh Sahani
2024 A* conf
Normalization and effective learning rates in reinforcement learning.
NeurIPS
Clare Lyle, Zeyu Zheng, Khimya Khetarpal, James Martens, Hado Philip van Hasselt, Razvan Pascanu, Will Dabney
2024 J jnl
Normalization and effective learning rates in reinforcement learning.
CoRR
Clare Lyle, Zeyu Zheng, Khimya Khetarpal, James Martens, Hado van Hasselt, Razvan Pascanu, Will Dabney
2024 J jnl
Promoting Exploration in Memory-Augmented Adam using Critical Momenta.
Trans. Mach. Learn. Res.
Pranshu Malviya, Gonçalo Mordido, Aristide Baratin, Reza Babanezhad Harikandeh, Jerry Huang, Simon Lacoste-Julien, Razvan Pascanu, Sarath Chandar
2024 J jnl
RecurrentGemma: Moving Past Transformers for Efficient Open Language Models.
CoRR
Aleksandar Botev, Soham De, Samuel L. Smith, Anushan Fernando, George-Cristian Muraru, Ruba Haroun, Leonard Berrada, Razvan Pascanu, Pier Giuseppe Sessa, Robert Dadashi, Léonard Hussenot, Johan Ferret, Sertan Girgin, Olivier Bachem, Alek Andreev, Kathleen Kenealy, Thomas Mesnard, Cassidy Hardin, Surya Bhupatiraju, Shreya Pathak, Laurent Sifre, Morgane Rivière, Mihir Sanjay Kale, Juliette Love, Pouya Tafti, Armand Joulin, Noah Fiedel, Evan Senter, Yutian Chen, Srivatsan Srinivasan, Guillaume Desjardins, David Budden, Arnaud Doucet, Sharad Vikram, Adam Paszke, Trevor Gale, Sebastian Borgeaud, Charlie Chen, Andy Brock, Antonia Paterson, Jenny Brennan, Meg Risdal, Raj Gundluru, Nesh Devanathan, Paul Mooney, Nilay Chauhan, Phil Culliton, Luiz Gustavo Martins, Elisa Bandy, David Huntsperger, Glenn Cameron, Arthur Zucker, Tris Warkentin, Ludovic Peran, Minh Giang, Zoubin Ghahramani, Clément Farabet, Koray Kavukcuoglu, Demis Hassabis, Raia Hadsell, Yee Whye Teh, Nando de Frietas
2024 J jnl
Retrieval-Augmented Decision Transformer: External Memory for In-context RL.
CoRR
Thomas Schmied, Fabian Paischer, Vihang Patil, Markus Hofmarcher, Razvan Pascanu, Sepp Hochreiter
2024 J jnl
Revisiting Dynamic Evaluation: Online Adaptation for Large Language Models.
CoRR
Amal Rannen-Triki, Jörg Bornschein, Razvan Pascanu, Marcus Hutter, András György, Alexandre Galashov, Yee Whye Teh, Michalis K. Titsias
2024 J jnl
Round and Round We Go! What makes Rotary Positional Encodings useful?
CoRR
Federico Barbero, Alex Vitvitskyi, Christos Perivolaropoulos, Razvan Pascanu, Petar Velickovic
2024 J jnl
State Soup: In-Context Skill Learning, Retrieval and Mixing.
CoRR
Maciej Pióro, Maciej Wolczyk, Razvan Pascanu, Johannes von Oswald, João Sacramento
2024 J jnl
TRecViT: A Recurrent Video Transformer.
CoRR
Viorica Patraucean, Xu Owen He, Joseph Heyward, Chuhan Zhang, Mehdi S. M. Sajjadi, George-Cristian Muraru, Artem Zholus, Mahdi Karami, Ross Goroshin, Yutian Chen, Simon Osindero, João Carreira, Razvan Pascanu
2024 J jnl
Torque-Aware Momentum.
CoRR
Pranshu Malviya, Gonçalo Mordido, Aristide Baratin, Reza Babanezhad Harikandeh, Gintare Karolina Dziugaite, Razvan Pascanu, Sarath Chandar
2024 J jnl
Transformers meet Neural Algorithmic Reasoners.
CoRR
Wilfried Bounsi, Borja Ibarz, Andrew Dudzik, Jessica B. Hamrick, Larisa Markeeva, Alex Vitvitskyi, Razvan Pascanu, Petar Velickovic
2024 A* conf
Transformers need glasses! Information over-squashing in language tasks.
NeurIPS
Federico Barbero, Andrea Banino, Steven Kapturowski, Dharshan Kumaran, João Guilherme Madeira Araújo, Oleksandr Vitvitskyi, Razvan Pascanu, Petar Velickovic
2024 J jnl
Transformers need glasses! Information over-squashing in language tasks.
CoRR
Federico Barbero, Andrea Banino, Steven Kapturowski, Dharshan Kumaran, João G. M. Araújo, Alex Vitvitskyi, Razvan Pascanu, Petar Velickovic
2024 A* conf
Universality of Linear Recurrences Followed by Non-linear Projections: Finite-Width Guarantees and Benefits of Complex Eigenvalues.
ICML
Antonio Orvieto, Soham De, Caglar Gulcehre, Razvan Pascanu, Samuel L. Smith
2024 J jnl
When can transformers compositionally generalize in-context?
CoRR
Seijin Kobayashi, Simon Schug, Yassir Akram, Florian Redhardt, Johannes von Oswald, Razvan Pascanu, Guillaume Lajoie, João Sacramento
2024 J jnl
softmax is not enough (for sharp out-of-distribution).
CoRR
Petar Velickovic, Christos Perivolaropoulos, Federico Barbero, Razvan Pascanu
2023 — conf
Asynchronous Algorithmic Alignment With Cocycles.
LoG
Andrew Joseph Dudzik, Tamara von Glehn, Razvan Pascanu, Petar Velickovic
2023 J jnl
Asynchronous Algorithmic Alignment with Cocycles.
CoRR
Andrew Dudzik, Tamara von Glehn, Razvan Pascanu, Petar Velickovic
2023 — ed.
Conference on Lifelong Learning Agents, 22-25 August 2023, McGill University, Montréal, Québec, Canada.
CoLLAs
Sarath Chandar, Razvan Pascanu, Hanie Sedghi, Doina Precup
2023 J jnl
Continual Learning: Applications and the Road Forward.
CoRR
Eli Verwimp, Rahaf Aljundi, Shai Ben-David, Matthias Bethge, Andrea Cossu, Alexander Gepperth, Tyler L. Hayes, Eyke Hüllermeier, Christopher Kanan, Dhireesha Kudithipudi, Christoph H. Lampert, Martin Mundt, Razvan Pascanu, Adrian Popescu, Andreas S. Tolias, Joost van de Weijer, Bing Liu, Vincenzo Lomonaco, Tinne Tuytelaars, Gido M. van de Ven
2023 — conf
Continually learning representations at scale.
CoLLAs
Alexandre Galashov, Jovana Mitrovic, Dhruva Tirumala, Yee Whye Teh, Timothy Nguyen, Arslan Chaudhry, Razvan Pascanu
2023 A* conf
Deep Reinforcement Learning with Plasticity Injection.
NeurIPS
Evgenii Nikishin, Junhyuk Oh, Georg Ostrovski, Clare Lyle, Razvan Pascanu, Will Dabney, André Barreto
2023 J jnl
Deep Reinforcement Learning with Plasticity Injection.
CoRR
Evgenii Nikishin, Junhyuk Oh, Georg Ostrovski, Clare Lyle, Razvan Pascanu, Will Dabney, André Barreto
2023 J jnl
Discovering modular solutions that generalize compositionally.
CoRR
Simon Schug, Seijin Kobayashi, Yassir Akram, Maciej Wolczyk, Alexandra Maria Proca, Johannes von Oswald, Razvan Pascanu, João Sacramento, Angelika Steger
2023 J jnl
Kalman Filter for Online Classification of Non-Stationary Data.
CoRR
Michalis K. Titsias, Alexandre Galashov, Amal Rannen-Triki, Razvan Pascanu, Yee Whye Teh, Jörg Bornschein
2023 — conf
Latent Space Representations of Neural Algorithmic Reasoners.
LoG
Vladimir V. Mirjanic, Razvan Pascanu, Petar Velickovic
2023 J jnl
Latent Space Representations of Neural Algorithmic Reasoners.
CoRR
Vladimir V. Mirjanic, Razvan Pascanu, Petar Velickovic
2023 A* conf
Learning to Modulate pre-trained Models in RL.
NeurIPS
Thomas Schmied, Markus Hofmarcher, Fabian Paischer, Razvan Pascanu, Sepp Hochreiter
2023 J jnl
Learning to Modulate pre-trained Models in RL.
CoRR
Thomas Schmied, Markus Hofmarcher, Fabian Paischer, Razvan Pascanu, Sepp Hochreiter
2023 J jnl
Nevis'22: A Stream of 100 Tasks Sampled from 30 Years of Computer Vision Research.
J. Mach. Learn. Res.
Jörg Bornschein, Alexandre Galashov, Ross Hemsley, Amal Rannen-Triki, Yutian Chen, Arslan Chaudhry, Xu Owen He, Arthur Douillard, Massimo Caccia, Qixuan Feng, Jiajun Shen, Sylvestre-Alvise Rebuffi, Kitty Stacpoole, Diego de Las Casas, Will Hawkins, Angeliki Lazaridou, Yee Whye Teh, Andrei A. Rusu, Razvan Pascanu, Marc'Aurelio Ranzato
2023 J jnl
On the Universality of Linear Recurrences Followed by Nonlinear Projections.
CoRR
Antonio Orvieto, Soham De, Çaglar Gülçehre, Razvan Pascanu, Samuel L. Smith
2023 A* conf
Pre-training via Denoising for Molecular Property Prediction.
ICLR
Sheheryar Zaidi, Michael Schaarschmidt, James Martens, Hyunjik Kim, Yee Whye Teh, Alvaro Sanchez-Gonzalez, Peter W. Battaglia, Razvan Pascanu, Jonathan Godwin
2023 J jnl
Promoting Exploration in Memory-Augmented Adam using Critical Momenta.
CoRR
Pranshu Malviya, Gonçalo Mordido, Aristide Baratin, Reza Babanezhad Harikandeh, Jerry Huang, Simon Lacoste-Julien, Razvan Pascanu, Sarath Chandar
2023 A* conf
Resurrecting Recurrent Neural Networks for Long Sequences.
ICML
Antonio Orvieto, Samuel L. Smith, Albert Gu, Anushan Fernando, Çaglar Gülçehre, Razvan Pascanu, Soham De
2023 J jnl
Resurrecting Recurrent Neural Networks for Long Sequences.
CoRR
Antonio Orvieto, Samuel L. Smith, Albert Gu, Anushan Fernando, Çaglar Gülçehre, Razvan Pascanu, Soham De
2023 A* conf
SemPPL: Predicting Pseudo-Labels for Better Contrastive Representations.
ICLR
Matko Bosnjak, Pierre Harvey Richemond, Nenad Tomasev, Florian Strub, Jacob C. Walker, Felix Hill, Lars Holger Buesing, Razvan Pascanu, Charles Blundell, Jovana Mitrovic
2023 J jnl
SemPPL: Predicting pseudo-labels for better contrastive representations.
CoRR
Matko Bosnjak, Pierre H. Richemond, Nenad Tomasev, Florian Strub, Jacob C. Walker, Felix Hill, Lars Holger Buesing, Razvan Pascanu, Charles Blundell, Jovana Mitrovic
2023 A* conf
The Tunnel Effect: Building Data Representations in Deep Neural Networks.
NeurIPS
Wojciech Masarczyk, Mateusz Ostaszewski, Ehsan Imani, Razvan Pascanu, Piotr Milos, Tomasz Trzcinski
2023 J jnl
The Tunnel Effect: Building Data Representations in Deep Neural Networks.
CoRR
Wojciech Masarczyk, Mateusz Ostaszewski, Ehsan Imani, Razvan Pascanu, Piotr Milos, Tomasz Trzcinski
2023 J jnl
Towards Compute-Optimal Transfer Learning.
CoRR
Massimo Caccia, Alexandre Galashov, Arthur Douillard, Amal Rannen-Triki, Dushyant Rao, Michela Paganini, Laurent Charlin, Marc'Aurelio Ranzato, Razvan Pascanu
2023 J jnl
Towards Robust and Efficient Continual Language Learning.
CoRR
Adam Fisch, Amal Rannen-Triki, Razvan Pascanu, Jörg Bornschein, Angeliki Lazaridou, Elena Gribovskaya, Marc'Aurelio Ranzato
2023 J jnl
Uncovering mesa-optimization algorithms in Transformers.
CoRR
Johannes von Oswald, Eyvind Niklasson, Maximilian Schlegel, Seijin Kobayashi, Nicolas Zucchet, Nino Scherrer, Nolan Miller, Mark Sandler, Blaise Agüera y Arcas, Max Vladymyrov, Razvan Pascanu, João Sacramento
2023 A* conf
Understanding Plasticity in Neural Networks.
ICML
Clare Lyle, Zeyu Zheng, Evgenii Nikishin, Bernardo Ávila Pires, Razvan Pascanu, Will Dabney
2023 J jnl
Understanding plasticity in neural networks.
CoRR
Clare Lyle, Zeyu Zheng, Evgenii Nikishin, Bernardo Ávila Pires, Razvan Pascanu, Will Dabney
2022 J jnl
An Empirical Study of Implicit Regularization in Deep Offline RL.
CoRR
Çaglar Gülçehre, Srivatsan Srinivasan, Jakub Sygnowski, Georg Ostrovski, Mehrdad Farajtabar, Matt Hoffman, Razvan Pascanu, Arnaud Doucet
2022 J jnl
An empirical study of implicit regularization in deep offline RL.
Trans. Mach. Learn. Res.
Çaglar Gülçehre, Srivatsan Srinivasan, Jakub Sygnowski, Georg Ostrovski, Mehrdad Farajtabar, Matthew Hoffman, Razvan Pascanu, Arnaud Doucet
2022 J jnl
Architecture Matters in Continual Learning.
CoRR
Seyed-Iman Mirzadeh, Arslan Chaudhry, Dong Yin, Timothy Nguyen, Razvan Pascanu, Dilan Görür, Mehrdad Farajtabar
2022 J jnl
Behavior Priors for Efficient Reinforcement Learning.
J. Mach. Learn. Res.
Dhruva Tirumala, Alexandre Galashov, Hyeonwoo Noh, Leonard Hasenclever, Razvan Pascanu, Jonathan Schwarz, Guillaume Desjardins, Wojciech Marian Czarnecki, Arun Ahuja, Yee Whye Teh, Nicolas Heess
2022 — ed.
Conference on Lifelong Learning Agents, CoLLAs 2022, 22-24 August 2022, McGill University, Montréal, Québec, Canada.
CoLLAs
Sarath Chandar, Razvan Pascanu, Doina Precup
2022 — conf
Correlation Based Semantic Transfer with Application to Domain Adaptation.
ICONIP (1)
Florina-Cristina Calnegru, John Shawe-Taylor, Iasonas Kokkinos, Razvan Pascanu
2022 A* conf
Disentangling Transfer in Continual Reinforcement Learning.
NeurIPS
Maciej Wolczyk, Michal Zajac, Razvan Pascanu, Lukasz Kucinski, Piotr Milos
2022 J jnl
Disentangling Transfer in Continual Reinforcement Learning.
CoRR
Maciej Wolczyk, Michal Zajac, Razvan Pascanu, Lukasz Kucinski, Piotr Milos
2022 — ed.
Learning on Graphs Conference, LoG 2022, 9-12 December 2022, Virtual Event.
LoG
Bastian Rieck, Razvan Pascanu
2022 J jnl
NEVIS'22: A Stream of 100 Tasks Sampled from 30 Years of Computer Vision Research.
CoRR
Jörg Bornschein, Alexandre Galashov, Ross Hemsley, Amal Rannen-Triki, Yutian Chen, Arslan Chaudhry, Xu Owen He, Arthur Douillard, Massimo Caccia, Qixuang Feng, Jiajun Shen, Sylvestre-Alvise Rebuffi, Kitty Stacpoole, Diego de Las Casas, Will Hawkins, Angeliki Lazaridou, Yee Whye Teh, Andrei A. Rusu, Razvan Pascanu, Marc'Aurelio Ranzato
2022 J jnl
Pre-training via Denoising for Molecular Property Prediction.
CoRR
Sheheryar Zaidi, Michael Schaarschmidt, James Martens, Hyunjik Kim, Yee Whye Teh, Alvaro Sanchez-Gonzalez, Peter W. Battaglia, Razvan Pascanu, Jonathan Godwin
2022 — conf
Probing Transfer in Deep Reinforcement Learning without Task Engineering.
CoLLAs
Andrei Alex Rusu, Sebastian Flennerhag, Dushyant Rao, Razvan Pascanu, Raia Hadsell
2022 J jnl
Probing Transfer in Deep Reinforcement Learning without Task Engineering.
CoRR
Andrei A. Rusu, Sebastian Flennerhag, Dushyant Rao, Razvan Pascanu, Raia Hadsell
2022 J jnl
Pushing the limits of self-supervised ResNets: Can we outperform supervised learning without labels on ImageNet?
CoRR
Nenad Tomasev, Ioana Bica, Brian McWilliams, Lars Buesing, Razvan Pascanu, Charles Blundell, Jovana Mitrovic
2022 — conf
Reasoning-Modulated Representations.
LoG
Petar Velickovic, Matko Bosnjak, Thomas Kipf, Alexander Lerchner, Raia Hadsell, Razvan Pascanu, Charles Blundell
2022 — conf
Test Sample Accuracy Scales with Training Sample Density in Neural Networks.
CoLLAs
Xu Ji, Razvan Pascanu, R. Devon Hjelm, Balaji Lakshminarayanan, Andrea Vedaldi
2022 A* conf
The CLRS Algorithmic Reasoning Benchmark.
ICML
Petar Velickovic, Adrià Puigdomènech Badia, David Budden, Razvan Pascanu, Andrea Banino, Misha Dashevskiy, Raia Hadsell, Charles Blundell
2022 J jnl
The CLRS Algorithmic Reasoning Benchmark.
CoRR
Petar Velickovic, Adrià Puigdomènech Badia, David Budden, Razvan Pascanu, Andrea Banino, Misha Dashevskiy, Raia Hadsell, Charles Blundell
2022 — conf
The First Learning on Graphs Conference: Preface.
LoG
Bastian Rieck, Razvan Pascanu, Yuanqi Du, Hannes Stärk, Derek Lim, Chaitanya K. Joshi, Andreea Deac, Iulia Duta, Joshua Robinson, Gabriele Corso, Leonardo Cotta, Yanqiao Zhu, Kexin Huang, Michelle M. Li, Sofia Bourhim, Ilia Igashov
2022 — conf
When Does Re-initialization Work?
ICBINB
Sheheryar Zaidi, Tudor Berariu, Hyunjik Kim, Jörg Bornschein, Claudia Clopath, Yee Whye Teh, Razvan Pascanu
2022 J jnl
When Does Re-initialization Work?
CoRR
Sheheryar Zaidi, Tudor Berariu, Hyunjik Kim, Jörg Bornschein, Claudia Clopath, Yee Whye Teh, Razvan Pascanu
2022 A* conf
Wide Neural Networks Forget Less Catastrophically.
ICML
Seyed-Iman Mirzadeh, Arslan Chaudhry, Dong Yin, Huiyi Hu, Razvan Pascanu, Dilan Görür, Mehrdad Farajtabar
2021 J jnl
A study on the plasticity of neural networks.
CoRR
Tudor Berariu, Wojciech Czarnecki, Soham De, Jörg Bornschein, Samuel L. Smith, Razvan Pascanu, Claudia Clopath
2021 A* conf
Continual World: A Robotic Benchmark For Continual Reinforcement Learning.
NeurIPS
Maciej Wolczyk, Michal Zajac, Razvan Pascanu, Lukasz Kucinski, Piotr Milos
2021 J jnl
Continual World: A Robotic Benchmark For Continual Reinforcement Learning.
CoRR
Maciej Wolczyk, Michal Zajac, Razvan Pascanu, Lukasz Kucinski, Piotr Milos
2021 J jnl
Drawing Multiple Augmentation Samples Per Image During Training Efficiently Decreases Test Error.
CoRR
Stanislav Fort, Andrew Brock, Razvan Pascanu, Soham De, Samuel L. Smith
2021 — conf
LiRo: Benchmark and leaderboard for Romanian language tasks.
NeurIPS Datasets and Benchmarks
Stefan Daniel Dumitrescu, Petru Rebeja, Beáta Lorincz, Mihaela Gaman, Andrei-Marius Avram, Mihai Ilie, Andrei Pruteanu, Adriana Stan, Lorena Rosia, Cristina Iacobescu, Luciana Morogan, George Dima, Gabriel Marchidan, Traian Rebedea, Madalina Chitez, Dani Yogatama, Sebastian Ruder, Radu Tudor Ionescu, Razvan Pascanu, Viorica Patraucean
2021 A* conf
Linear Mode Connectivity in Multitask and Continual Learning.
ICLR
Seyed-Iman Mirzadeh, Mehrdad Farajtabar, Dilan Görür, Razvan Pascanu, Hassan Ghasemzadeh
2021 A* conf
On the Role of Optimization in Double Descent: A Least Squares Study.
NeurIPS
Ilja Kuzborskij, Csaba Szepesvári, Omar Rivasplata, Amal Rannen-Triki, Razvan Pascanu
2021 J jnl
On the Role of Optimization in Double Descent: A Least Squares Study.
CoRR
Ilja Kuzborskij, Csaba Szepesvári, Omar Rivasplata, Amal Rannen-Triki, Razvan Pascanu
2021 A* conf
Powerpropagation: A sparsity inducing weight reparameterisation.
NeurIPS
Jonathan Schwarz, Siddhant M. Jayakumar, Razvan Pascanu, Peter E. Latham, Yee Whye Teh
2021 J jnl
Powerpropagation: A sparsity inducing weight reparameterisation.
CoRR
Jonathan Schwarz, Siddhant M. Jayakumar, Razvan Pascanu, Peter E. Latham, Yee Whye Teh
2021 J jnl
Predicting Unreliable Predictions by Shattering a Neural Network.
CoRR
Xu Ji, Razvan Pascanu, R. Devon Hjelm, Andrea Vedaldi, Balaji Lakshminarayanan, Yoshua Bengio
2021 J jnl
Reasoning-Modulated Representations.
CoRR
Petar Velickovic, Matko Bosnjak, Thomas Kipf, Alexander Lerchner, Raia Hadsell, Razvan Pascanu, Charles Blundell
2021 J jnl
Regularized Behavior Value Estimation.
CoRR
Çaglar Gülçehre, Sergio Gómez Colmenarejo, Ziyu Wang, Jakub Sygnowski, Thomas Paine, Konrad Zolna, Yutian Chen, Matthew W. Hoffman, Razvan Pascanu, Nando de Freitas
2021 A* conf
Spectral Normalisation for Deep Reinforcement Learning: An Optimisation Perspective.
ICML
Florin Gogianu, Tudor Berariu, Mihaela Rosca, Claudia Clopath, Lucian Busoniu, Razvan Pascanu
2021 J jnl
Spectral Normalisation for Deep Reinforcement Learning: an Optimisation Perspective.
CoRR
Florin Gogianu, Tudor Berariu, Mihaela Rosca, Claudia Clopath, Lucian Busoniu, Razvan Pascanu
2021 J jnl
Task-agnostic Continual Learning with Hybrid Probabilistic Models.
CoRR
Polina Kirichenko, Mehrdad Farajtabar, Dushyant Rao, Balaji Lakshminarayanan, Nir Levine, Ang Li, Huiyi Hu, Andrew Gordon Wilson, Razvan Pascanu
2021 J jnl
Top-KAST: Top-K Always Sparse Training.
CoRR
Siddhant M. Jayakumar, Razvan Pascanu, Jack W. Rae, Simon Osindero, Erich Elsen
2021 J jnl
Wide Neural Networks Forget Less Catastrophically.
CoRR
Seyed-Iman Mirzadeh, Arslan Chaudhry, Huiyi Hu, Razvan Pascanu, Dilan Görür, Mehrdad Farajtabar
2020 J jnl
BYOL works even without batch statistics.
CoRR
Pierre H. Richemond, Jean-Bastien Grill, Florent Altché, Corentin Tallec, Florian Strub, Andrew Brock, Samuel L. Smith, Soham De, Razvan Pascanu, Bilal Piot, Michal Valko
2020 J jnl
Behavior Priors for Efficient Reinforcement Learning.
CoRR
Dhruva Tirumala, Alexandre Galashov, Hyeonwoo Noh, Leonard Hasenclever, Razvan Pascanu, Jonathan Schwarz, Guillaume Desjardins, Wojciech Marian Czarnecki, Arun Ahuja, Yee Whye Teh, Nicolas Heess
2020 A* conf
Functional Regularisation for Continual Learning with Gaussian Processes.
ICLR
Michalis K. Titsias, Jonathan Schwarz, Alexander G. de G. Matthews, Razvan Pascanu, Yee Whye Teh
2020 A* conf
Improving the Gating Mechanism of Recurrent Neural Networks.
ICML
Albert Gu, Çaglar Gülçehre, Thomas Paine, Matt Hoffman, Razvan Pascanu
2020 J jnl
Linear Mode Connectivity in Multitask and Continual Learning.
CoRR
Seyed-Iman Mirzadeh, Mehrdad Farajtabar, Dilan Görür, Razvan Pascanu, Hassan Ghasemzadeh
2020 A* conf
Meta-Learning with Warped Gradient Descent.
ICLR
Sebastian Flennerhag, Andrei A. Rusu, Razvan Pascanu, Francesco Visin, Hujun Yin, Raia Hadsell
2020 A* conf
Multiplicative Interactions and Where to Find Them.
ICLR
Siddhant M. Jayakumar, Wojciech M. Czarnecki, Jacob Menick, Jonathan Schwarz, Jack W. Rae, Simon Osindero, Yee Whye Teh, Tim Harley, Razvan Pascanu
2020 A* conf
Pointer Graph Networks.
NeurIPS
Petar Velickovic, Lars Buesing, Matthew C. Overlan, Razvan Pascanu, Oriol Vinyals, Charles Blundell
2020 J jnl
Pointer Graph Networks.
CoRR
Petar Velickovic, Lars Buesing, Matthew C. Overlan, Razvan Pascanu, Oriol Vinyals, Charles Blundell
2020 A* conf
Stabilizing Transformers for Reinforcement Learning.
ICML
Emilio Parisotto, H. Francis Song, Jack W. Rae, Razvan Pascanu, Çaglar Gülçehre, Siddhant M. Jayakumar, Max Jaderberg, Raphaël Lopez Kaufman, Aidan Clark, Seb Noury, Matthew M. Botvinick, Nicolas Heess, Raia Hadsell
2020 J jnl
Temporal Difference Uncertainties as a Signal for Exploration.
CoRR
Sebastian Flennerhag, Jane X. Wang, Pablo Sprechmann, Francesco Visin, Alexandre Galashov, Steven Kapturowski, Diana L. Borsa, Nicolas Heess, André Barreto, Razvan Pascanu
2020 A* conf
Top-KAST: Top-K Always Sparse Training.
NeurIPS
Siddhant M. Jayakumar, Razvan Pascanu, Jack W. Rae, Simon Osindero, Erich Elsen
2020 A* conf
Understanding the Role of Training Regimes in Continual Learning.
NeurIPS
Seyed-Iman Mirzadeh, Mehrdad Farajtabar, Razvan Pascanu, Hassan Ghasemzadeh
2020 J jnl
Understanding the Role of Training Regimes in Continual Learning.
CoRR
Seyed-Iman Mirzadeh, Mehrdad Farajtabar, Razvan Pascanu, Hassan Ghasemzadeh
2019 J jnl
A Deep Neural Network's Loss Surface Contains Every Low-dimensional Pattern.
CoRR
Wojciech Marian Czarnecki, Simon Osindero, Razvan Pascanu, Max Jaderberg
2019 — conf
A RAD approach to deep mixture models.
DGS@ICLR
Laurent Dinh, Jascha Sohl-Dickstein, Razvan Pascanu, Hugo Larochelle
2019 J jnl
A RAD approach to deep mixture models.
CoRR
Laurent Dinh, Jascha Sohl-Dickstein, Razvan Pascanu, Hugo Larochelle
2019 A* conf
Continual Unsupervised Representation Learning.
NeurIPS
Dushyant Rao, Francesco Visin, Andrei A. Rusu, Razvan Pascanu, Yee Whye Teh, Raia Hadsell
2019 J jnl
Continual Unsupervised Representation Learning.
CoRR
Dushyant Rao, Francesco Visin, Andrei A. Rusu, Yee Whye Teh, Razvan Pascanu, Raia Hadsell
2019 — conf
Deep reinforcement learning with relational inductive biases.
ICLR (Poster)
Vinícius Flores Zambaldi, David Raposo, Adam Santoro, Victor Bapst, Yujia Li, Igor Babuschkin, Karl Tuyls, David P. Reichert, Timothy P. Lillicrap, Edward Lockhart, Murray Shanahan, Victoria Langston, Razvan Pascanu, Matthew M. Botvinick, Oriol Vinyals, Peter W. Battaglia
2019 A conf
Distilling Policy Distillation.
AISTATS
Wojciech M. Czarnecki, Razvan Pascanu, Simon Osindero, Siddhant M. Jayakumar, Grzegorz Swirszcz, Max Jaderberg
2019 J jnl
Distilling Policy Distillation.
CoRR
Wojciech Marian Czarnecki, Razvan Pascanu, Simon Osindero, Siddhant M. Jayakumar, Grzegorz Swirszcz, Max Jaderberg
2019 J jnl
Exploiting Hierarchy for Learning and Transfer in KL-regularized RL.
CoRR
Dhruva Tirumala, Hyeonwoo Noh, Alexandre Galashov, Leonard Hasenclever, Arun Ahuja, Greg Wayne, Razvan Pascanu, Yee Whye Teh, Nicolas Heess
2019 J jnl
Functional Regularisation for Continual Learning using Gaussian Processes.
CoRR
Michalis K. Titsias, Jonathan Schwarz, Alexander G. de G. Matthews, Razvan Pascanu, Yee Whye Teh
2019 — conf
Hyperbolic Attention Networks.
ICLR (Poster)
Çaglar Gülçehre, Misha Denil, Mateusz Malinowski, Ali Razavi, Razvan Pascanu, Karl Moritz Hermann, Peter W. Battaglia, Victor Bapst, David Raposo, Adam Santoro, Nando de Freitas
2019 J jnl
Improving the Gating Mechanism of Recurrent Neural Networks.
CoRR
Albert Gu, Çaglar Gülçehre, Tom Le Paine, Matthew W. Hoffman, Razvan Pascanu
2019 — conf
Information asymmetry in KL-regularized RL.
ICLR (Poster)
Alexandre Galashov, Siddhant M. Jayakumar, Leonard Hasenclever, Dhruva Tirumala, Jonathan Schwarz, Guillaume Desjardins, Wojciech M. Czarnecki, Yee Whye Teh, Razvan Pascanu, Nicolas Heess
2019 J jnl
Information asymmetry in KL-regularized RL.
CoRR
Alexandre Galashov, Siddhant M. Jayakumar, Leonard Hasenclever, Dhruva Tirumala, Jonathan Schwarz, Guillaume Desjardins, Wojciech M. Czarnecki, Yee Whye Teh, Razvan Pascanu, Nicolas Heess
2019 — conf
Meta-Learning with Latent Embedding Optimization.
ICLR (Poster)
Andrei A. Rusu, Dushyant Rao, Jakub Sygnowski, Oriol Vinyals, Razvan Pascanu, Simon Osindero, Raia Hadsell
2019 J jnl
Meta-Learning with Warped Gradient Descent.
CoRR
Sebastian Flennerhag, Andrei A. Rusu, Razvan Pascanu, Hujun Yin, Raia Hadsell
2019 J jnl
Meta-learning of Sequential Strategies.
CoRR
Pedro A. Ortega, Jane X. Wang, Mark Rowland, Tim Genewein, Zeb Kurth-Nelson, Razvan Pascanu, Nicolas Heess, Joel Veness, Alexander Pritzel, Pablo Sprechmann, Siddhant M. Jayakumar, Tom McGrath, Kevin J. Miller, Mohammad Gheshlaghi Azar, Ian Osband, Neil C. Rabinowitz, András György, Silvia Chiappa, Simon Osindero, Yee Whye Teh, Hado van Hasselt, Nando de Freitas, Matthew M. Botvinick, Shane Legg
2019 J jnl
Ray Interference: a Source of Plateaus in Deep Reinforcement Learning.
CoRR
Tom Schaul, Diana Borsa, Joseph Modayil, Razvan Pascanu
2019 J jnl
Stabilizing Transformers for Reinforcement Learning.
CoRR
Emilio Parisotto, H. Francis Song, Jack W. Rae, Razvan Pascanu, Çaglar Gülçehre, Siddhant M. Jayakumar, Max Jaderberg, Raphael Lopez Kaufman, Aidan Clark, Seb Noury, Matthew M. Botvinick, Nicolas Heess, Raia Hadsell
2019 J jnl
Task Agnostic Continual Learning via Meta Learning.
CoRR
Xu He, Jakub Sygnowski, Alexandre Galashov, Andrei A. Rusu, Yee Whye Teh, Razvan Pascanu
2018 J jnl
Adapting Auxiliary Losses Using Gradient Similarity.
CoRR
Yunshu Du, Wojciech M. Czarnecki, Siddhant M. Jayakumar, Razvan Pascanu, Balaji Lakshminarayanan
2018 A* conf
Been There, Done That: Meta-Learning with Episodic Recall.
ICML
Samuel Ritter, Jane X. Wang, Zeb Kurth-Nelson, Siddhant M. Jayakumar, Charles Blundell, Razvan Pascanu, Matthew M. Botvinick
2018 J jnl
Been There, Done That: Meta-Learning with Episodic Recall.
CoRR
Samuel Ritter, Jane X. Wang, Zeb Kurth-Nelson, Siddhant M. Jayakumar, Charles Blundell, Razvan Pascanu, Matthew M. Botvinick
2018 J jnl
Block Mean Approximation for Efficient Second Order Optimization.
CoRR
Yao Lu, Mehrtash Harandi, Richard I. Hartley, Razvan Pascanu
2018 J jnl
Hyperbolic Attention Networks.
CoRR
Çaglar Gülçehre, Misha Denil, Mateusz Malinowski, Ali Razavi, Razvan Pascanu, Karl Moritz Hermann, Peter W. Battaglia, Victor Bapst, David Raposo, Adam Santoro, Nando de Freitas
2018 J jnl
Learning Deep Generative Models of Graphs.
CoRR
Yujia Li, Oriol Vinyals, Chris Dyer, Razvan Pascanu, Peter W. Battaglia
2018 J jnl
Low-pass Recurrent Neural Networks - A memory architecture for longer-term correlation discovery.
CoRR
Thomas S. Stepleton, Razvan Pascanu, Will Dabney, Siddhant M. Jayakumar, Hubert Soyer, Rémi Munos
2018 — conf
Memory-based Parameter Adaptation.
ICLR (Poster)
Pablo Sprechmann, Siddhant M. Jayakumar, Jack W. Rae, Alexander Pritzel, Adrià Puigdomènech Badia, Benigno Uria, Oriol Vinyals, Demis Hassabis, Razvan Pascanu, Charles Blundell
2018 J jnl
Memory-based Parameter Adaptation.
CoRR
Pablo Sprechmann, Siddhant M. Jayakumar, Jack W. Rae, Alexander Pritzel, Adrià Puigdomènech Badia, Benigno Uria, Oriol Vinyals, Demis Hassabis, Razvan Pascanu, Charles Blundell
2018 J jnl
Meta-Learning with Latent Embedding Optimization.
CoRR
Andrei A. Rusu, Dushyant Rao, Jakub Sygnowski, Oriol Vinyals, Razvan Pascanu, Simon Osindero, Raia Hadsell
2018 A* conf
Mix & Match Agent Curricula for Reinforcement Learning.
ICML
Wojciech Marian Czarnecki, Siddhant M. Jayakumar, Max Jaderberg, Leonard Hasenclever, Yee Whye Teh, Nicolas Heess, Simon Osindero, Razvan Pascanu
2018 J jnl
Mix&Match - Agent Curricula for Reinforcement Learning.
CoRR
Wojciech Marian Czarnecki, Siddhant M. Jayakumar, Max Jaderberg, Leonard Hasenclever, Yee Whye Teh, Simon Osindero, Nicolas Heess, Razvan Pascanu
2018 — conf
Model compression via distillation and quantization.
ICLR (Poster)
Antonio Polino, Razvan Pascanu, Dan Alistarh
2018 J jnl
Model compression via distillation and quantization.
CoRR
Antonio Polino, Razvan Pascanu, Dan Alistarh
2018 A* conf
Progress & Compress: A scalable framework for continual learning.
ICML
Jonathan Schwarz, Wojciech Czarnecki, Jelena Luketina, Agnieszka Grabska-Barwinska, Yee Whye Teh, Razvan Pascanu, Raia Hadsell
2018 J jnl
Progress & Compress: A scalable framework for continual learning.
CoRR
Jonathan Schwarz, Jelena Luketina, Wojciech M. Czarnecki, Agnieszka Grabska-Barwinska, Yee Whye Teh, Razvan Pascanu, Raia Hadsell
2018 J jnl
Relational Deep Reinforcement Learning.
CoRR
Vinícius Flores Zambaldi, David Raposo, Adam Santoro, Victor Bapst, Yujia Li, Igor Babuschkin, Karl Tuyls, David P. Reichert, Timothy P. Lillicrap, Edward Lockhart, Murray Shanahan, Victoria Langston, Razvan Pascanu, Matthew M. Botvinick, Oriol Vinyals, Peter W. Battaglia
2018 J jnl
Relational inductive biases, deep learning, and graph networks.
CoRR
Peter W. Battaglia, Jessica B. Hamrick, Victor Bapst, Alvaro Sanchez-Gonzalez, Vinícius Flores Zambaldi, Mateusz Malinowski, Andrea Tacchetti, David Raposo, Adam Santoro, Ryan Faulkner, Çaglar Gülçehre, H. Francis Song, Andrew J. Ballard, Justin Gilmer, George E. Dahl, Ashish Vaswani, Kelsey R. Allen, Charles Nash, Victoria Langston, Chris Dyer, Nicolas Heess, Daan Wierstra, Pushmeet Kohli, Matthew M. Botvinick, Oriol Vinyals, Yujia Li, Razvan Pascanu
2018 A* conf
Relational recurrent neural networks.
NeurIPS
Adam Santoro, Ryan Faulkner, David Raposo, Jack W. Rae, Mike Chrzanowski, Theophane Weber, Daan Wierstra, Oriol Vinyals, Razvan Pascanu, Timothy P. Lillicrap
2018 J jnl
Relational recurrent neural networks.
CoRR
Adam Santoro, Ryan Faulkner, David Raposo, Jack W. Rae, Mike Chrzanowski, Theophane Weber, Daan Wierstra, Oriol Vinyals, Razvan Pascanu, Timothy P. Lillicrap
2018 J jnl
Vector-based navigation using grid-like representations in artificial agents.
Nat.
Andrea Banino, Caswell Barry, Benigno Uria, Charles Blundell, Timothy P. Lillicrap, Piotr Mirowski, Alexander Pritzel, Martin J. Chadwick, Thomas Degris, Joseph Modayil, Greg Wayne, Hubert Soyer, Fabio Viola, Brian Zhang, Ross Goroshin, Neil C. Rabinowitz, Razvan Pascanu, Charlie Beattie, Stig Petersen, Amir Sadik, Stephen Gaffney, Helen King, Koray Kavukcuoglu, Demis Hassabis, Raia Hadsell, Dharshan Kumaran
2017 — conf
A simple neural network module for relational reasoning.
NIPS
Adam Santoro, David Raposo, David G. T. Barrett, Mateusz Malinowski, Razvan Pascanu, Peter W. Battaglia, Tim Lillicrap
2017 J jnl
A simple neural network module for relational reasoning.
CoRR
Adam Santoro, David Raposo, David G. T. Barrett, Mateusz Malinowski, Razvan Pascanu, Peter W. Battaglia, Timothy P. Lillicrap
2017 — conf
Discovering objects and their relations from entangled scene representations.
ICLR (Workshop)
David Raposo, Adam Santoro, David G. T. Barrett, Razvan Pascanu, Tim Lillicrap, Peter W. Battaglia
2017 J jnl
Discovering objects and their relations from entangled scene representations.
CoRR
David Raposo, Adam Santoro, David G. T. Barrett, Razvan Pascanu, Timothy P. Lillicrap, Peter W. Battaglia
2017 J jnl
Distral: Robust Multitask Reinforcement Learning.
CoRR
Yee Whye Teh, Victor Bapst, Wojciech Marian Czarnecki, John Quan, James Kirkpatrick, Raia Hadsell, Nicolas Heess, Razvan Pascanu
2017 — conf
Distral: Robust multitask reinforcement learning.
NIPS
Yee Whye Teh, Victor Bapst, Wojciech M. Czarnecki, John Quan, James Kirkpatrick, Raia Hadsell, Nicolas Heess, Razvan Pascanu
2017 — conf
Imagination-Augmented Agents for Deep Reinforcement Learning.
NIPS
Sébastien Racanière, Theophane Weber, David P. Reichert, Lars Buesing, Arthur Guez, Danilo Jimenez Rezende, Adrià Puigdomènech Badia, Oriol Vinyals, Nicolas Heess, Yujia Li, Razvan Pascanu, Peter W. Battaglia, Demis Hassabis, David Silver, Daan Wierstra
2017 J jnl
Imagination-Augmented Agents for Deep Reinforcement Learning.
CoRR
Theophane Weber, Sébastien Racanière, David P. Reichert, Lars Buesing, Arthur Guez, Danilo Jimenez Rezende, Adrià Puigdomènech Badia, Oriol Vinyals, Nicolas Heess, Yujia Li, Razvan Pascanu, Peter W. Battaglia, David Silver, Daan Wierstra
2017 J jnl
Learning model-based planning from scratch.
CoRR
Razvan Pascanu, Yujia Li, Oriol Vinyals, Nicolas Heess, Lars Buesing, Sébastien Racanière, David P. Reichert, Theophane Weber, Daan Wierstra, Peter W. Battaglia
2017 — conf
Learning to Navigate in Complex Environments.
ICLR (Poster)
Piotr Mirowski, Razvan Pascanu, Fabio Viola, Hubert Soyer, Andy Ballard, Andrea Banino, Misha Denil, Ross Goroshin, Laurent Sifre, Koray Kavukcuoglu, Dharshan Kumaran, Raia Hadsell
2017 — conf
Metacontrol for Adaptive Imagination-Based Optimization.
ICLR (Poster)
Jessica B. Hamrick, Andrew J. Ballard, Razvan Pascanu, Oriol Vinyals, Nicolas Heess, Peter W. Battaglia
2017 J jnl
Metacontrol for Adaptive Imagination-Based Optimization.
CoRR
Jessica B. Hamrick, Andrew J. Ballard, Razvan Pascanu, Oriol Vinyals, Nicolas Heess, Peter W. Battaglia
2017 A* conf
Sharp Minima Can Generalize For Deep Nets.
ICML
Laurent Dinh, Razvan Pascanu, Samy Bengio, Yoshua Bengio
2017 J jnl
Sharp Minima Can Generalize For Deep Nets.
CoRR
Laurent Dinh, Razvan Pascanu, Samy Bengio, Yoshua Bengio
2017 Misc conf
Sim-to-Real Robot Learning from Pixels with Progressive Nets.
CoRL
Andrei A. Rusu, Matej Vecerík, Thomas Rothörl, Nicolas Heess, Razvan Pascanu, Raia Hadsell
2017 — conf
Sobolev Training for Neural Networks.
NIPS
Wojciech M. Czarnecki, Simon Osindero, Max Jaderberg, Grzegorz Swirszcz, Razvan Pascanu
2017 J jnl
Sobolev Training for Neural Networks.
CoRR
Wojciech Marian Czarnecki, Simon Osindero, Max Jaderberg, Grzegorz Swirszcz, Razvan Pascanu
2017 J jnl
Visual Interaction Networks.
CoRR
Nicholas Watters, Andrea Tacchetti, Theophane Weber, Razvan Pascanu, Peter W. Battaglia, Daniel Zoran
2017 — conf
Visual Interaction Networks: Learning a Physics Simulator from Video.
NIPS
Nicholas Watters, Daniel Zoran, Theophane Weber, Peter W. Battaglia, Razvan Pascanu, Andrea Tacchetti
2016 — conf
Interaction Networks for Learning about Objects, Relations and Physics.
NIPS
Peter W. Battaglia, Razvan Pascanu, Matthew Lai, Danilo Jimenez Rezende, Koray Kavukcuoglu
2016 J jnl
Interaction Networks for Learning about Objects, Relations and Physics.
CoRR
Peter W. Battaglia, Razvan Pascanu, Matthew Lai, Danilo Jimenez Rezende, Koray Kavukcuoglu
2016 J jnl
Learning to Navigate in Complex Environments.
CoRR
Piotr Mirowski, Razvan Pascanu, Fabio Viola, Hubert Soyer, Andrew J. Ballard, Andrea Banino, Misha Denil, Ross Goroshin, Laurent Sifre, Koray Kavukcuoglu, Dharshan Kumaran, Raia Hadsell
2016 J jnl
Local minima in training of deep networks.
CoRR
Grzegorz Swirszcz, Wojciech Marian Czarnecki, Razvan Pascanu
2016 J jnl
Overcoming catastrophic forgetting in neural networks.
CoRR
James Kirkpatrick, Razvan Pascanu, Neil C. Rabinowitz, Joel Veness, Guillaume Desjardins, Andrei A. Rusu, Kieran Milan, John Quan, Tiago Ramalho, Agnieszka Grabska-Barwinska, Demis Hassabis, Claudia Clopath, Dharshan Kumaran, Raia Hadsell
2016 A* conf
Policy Distillation.
ICLR (Poster)
Andrei A. Rusu, Sergio Gomez Colmenarejo, Çaglar Gülçehre, Guillaume Desjardins, James Kirkpatrick, Razvan Pascanu, Volodymyr Mnih, Koray Kavukcuoglu, Raia Hadsell
2016 J jnl
Progressive Neural Networks.
CoRR
Andrei A. Rusu, Neil C. Rabinowitz, Guillaume Desjardins, Hubert Soyer, James Kirkpatrick, Koray Kavukcuoglu, Razvan Pascanu, Raia Hadsell
2016 J jnl
Sim-to-Real Robot Learning from Pixels with Progressive Nets.
CoRR
Andrei A. Rusu, Matej Vecerík, Thomas Rothörl, Nicolas Heess, Razvan Pascanu, Raia Hadsell
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
2015 Misc conf
Malware classification with recurrent networks.
ICASSP
Razvan Pascanu, Jack W. Stokes, Hermineh Sanossian, Mady Marinescu, Anil Thomas
2015 — conf
Natural Neural Networks.
NIPS
Guillaume Desjardins, Karen Simonyan, Razvan Pascanu, Koray Kavukcuoglu
2015 J jnl
Natural Neural Networks.
CoRR
Guillaume Desjardins, Karen Simonyan, Razvan Pascanu, Koray Kavukcuoglu
2014 — conf
How to Construct Deep Recurrent Neural Networks.
ICLR (Poster)
Razvan Pascanu, Çaglar Gülçehre, Kyunghyun Cho, Yoshua Bengio
2014 — conf
Identifying and attacking the saddle point problem in high-dimensional non-convex optimization.
NIPS
Yann N. Dauphin, Razvan Pascanu, Çaglar Gülçehre, Kyunghyun Cho, Surya Ganguli, Yoshua Bengio
2014 J jnl
Identifying and attacking the saddle point problem in high-dimensional non-convex optimization.
CoRR
Yann N. Dauphin, Razvan Pascanu, Çaglar Gülçehre, Kyunghyun Cho, Surya Ganguli, Yoshua Bengio
2014 — conf
Learned-Norm Pooling for Deep Feedforward and Recurrent Neural Networks.
ECML/PKDD (1)
Çaglar Gülçehre, Kyunghyun Cho, Razvan Pascanu, Yoshua Bengio
2014 — conf
On the Number of Linear Regions of Deep Neural Networks.
NIPS
Guido Montúfar, Razvan Pascanu, Kyunghyun Cho, Yoshua Bengio
2014 J jnl
On the Number of Linear Regions of Deep Neural Networks.
CoRR
Guido Montúfar, Razvan Pascanu, Kyunghyun Cho, Yoshua Bengio
2014 — conf
On the number of inference regions of deep feed forward networks with piece-wise linear activations.
ICLR (Poster)
Razvan Pascanu, Guido Montúfar, Yoshua Bengio
2014 J jnl
On the saddle point problem for non-convex optimization.
CoRR
Razvan Pascanu, Yann N. Dauphin, Surya Ganguli, Yoshua Bengio
2014 — conf
Revisiting Natural Gradient for Deep Networks
ICLR
Razvan Pascanu, Yoshua Bengio
2013 Misc conf
Advances in optimizing recurrent networks.
ICASSP
Yoshua Bengio, Nicolas Boulanger-Lewandowski, Razvan Pascanu
2013 B conf
Combining modality specific deep neural networks for emotion recognition in video.
ICMI
Samira Ebrahimi Kahou, Christopher J. Pal, Xavier Bouthillier, Pierre Froumenty, Çaglar Gülçehre, Roland Memisevic, Pascal Vincent, Aaron C. Courville, Yoshua Bengio, Raul Chandias Ferrari, Mehdi Mirza, Sébastien Jean, Pierre Luc Carrier, Yann N. Dauphin, Nicolas Boulanger-Lewandowski, Abhishek Aggarwal, Jeremie Zumer, Pascal Lamblin, Jean-Philippe Raymond, Guillaume Desjardins, Razvan Pascanu, David Warde-Farley, Atousa Torabi, Arjun Sharma, Emmanuel Bengio, Kishore Reddy Konda, Zhenzhou Wu
2013 J jnl
Learned-norm pooling for deep neural networks.
CoRR
Çaglar Gülçehre, Kyunghyun Cho, Razvan Pascanu, Yoshua Bengio
2013 A* conf
Metric-Free Natural Gradient for Joint-Training of Boltzmann Machines
ICLR (Poster)
Guillaume Desjardins, Razvan Pascanu, Aaron C. Courville, Yoshua Bengio
2013 — conf
Natural Gradient Revisited
ICLR (Workshop Poster)
Razvan Pascanu, Yoshua Bengio
2013 — conf
On the difficulty of training recurrent neural networks.
ICML (3)
Razvan Pascanu, Tomás Mikolov, Yoshua Bengio
2013 J jnl
Pylearn2: a machine learning research library.
CoRR
Ian J. Goodfellow, David Warde-Farley, Pascal Lamblin, Vincent Dumoulin, Mehdi Mirza, Razvan Pascanu, James Bergstra, Frédéric Bastien, Yoshua Bengio
2012 J jnl
Advances in Optimizing Recurrent Networks
CoRR
Yoshua Bengio, Nicolas Boulanger-Lewandowski, Razvan Pascanu
2012 J jnl
Learning Algorithms for the Classification Restricted Boltzmann Machine.
J. Mach. Learn. Res.
Hugo Larochelle, Michael I. Mandel, Razvan Pascanu, Yoshua Bengio
2012 J jnl
Theano: new features and speed improvements
CoRR
Frédéric Bastien, Pascal Lamblin, Razvan Pascanu, James Bergstra, Ian J. Goodfellow, Arnaud Bergeron, Nicolas Bouchard, David Warde-Farley, Yoshua Bengio
2012 J jnl
Understanding the exploding gradient problem
CoRR
Razvan Pascanu, Tomás Mikolov, Yoshua Bengio
2011 J jnl
A neurodynamical model for working memory.
Neural Networks
Razvan Pascanu, Herbert Jaeger
2011 J jnl
Autotagging music with conditional restricted Boltzmann machines
CoRR
Michael I. Mandel, Razvan Pascanu, Hugo Larochelle, Yoshua Bengio
2011 J jnl
Contextual tag inference.
ACM Trans. Multim. Comput. Commun. Appl.
Michael I. Mandel, Razvan Pascanu, Douglas Eck, Yoshua Bengio, Luca Maria Aiello, Rossano Schifanella, Filippo Menczer
2011 A conf
Deep Learners Benefit More from Out-of-Distribution Examples.
AISTATS
Yoshua Bengio, Frédéric Bastien, Arnaud Bergeron, Nicolas Boulanger-Lewandowski, Thomas M. Breuel, Youssouf Chherawala, Moustapha Cissé, Myriam Côté, Dumitru Erhan, Jeremy Eustache, Xavier Glorot, Xavier Muller, Sylvain Pannetier Lebeuf, Razvan Pascanu, Salah Rifai, François Savard, Guillaume Sicard
2010 J jnl
Deep Self-Taught Learning for Handwritten Character Recognition
CoRR
Frédéric Bastien, Yoshua Bengio, Arnaud Bergeron, Nicolas Boulanger-Lewandowski, Thomas M. Breuel, Youssouf Chherawala, Moustapha Cissé, Myriam Côté, Dumitru Erhan, Jeremy Eustache, Xavier Glorot, Xavier Muller, Sylvain Pannetier Lebeuf, Razvan Pascanu, Salah Rifai, François Savard, Guillaume Sicard
2010 A* conf
Extraction of quadrics from noisy point-clouds using a sensor noise model.
ICRA
Narunas Vaskevicius, Kaustubh Pathak, Razvan Pascanu, Andreas Birk
2010 — conf
Theano: A CPU and GPU Math Compiler in Python.
SciPy
James Bergstra, Olivier Breuleux, Frédéric Bastien, Pascal Lamblin, Razvan Pascanu, Guillaume Desjardins, Joseph P. Turian, David Warde-Farley, Yoshua Bengio