Publications | Apprentissage profond

Prépublications

• Hierarchical Planning with Latent World Models
  Wancong Zhang, Basile Terver, Artem Zholus, Soham Chitnis, Harsh Sutaria, Mido Assran, Randall Balestriero, Amir Bar, Adrien Bardes, Yann LeCun et Nicolas Ballas
  In ArXiv, 2026.
  #DL, #RL
  [arXiv], [website], [code]

• Probing the effectiveness of World Models for Spatial Reasoning through Test-time Scaling
  Saurav Jha, M. Jehanzeb Mirza, Wei Lin, Shiqi Yang et Sarath Chandar
  In ArXiv, 2025.
  #DL
  [arXiv]

• Neural Coherence: Find higher performance to out-of-distribution tasks from few samples
  Simon Guiroy, Mats Richter, Sarath Chandar et Christopher Pal
  In ArXiv, 2025.
  #DL
  [arXiv]

• Optimizers Qualitatively Alter Solutions And We Should Leverage This
  Razvan Pascanu, Clare Lyle, Ionut-Vlad Modoranu, Naima Elosegui Borras, Dan Alistarh, Petar Velickovic, Sarath Chandar, Soham De et James Martens
  In ArXiv, 2025.
  #DL
  [arXiv]

• V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planning
  Mido Assran*, Adrien Bardes*, David Fan*, Quentin Garrido*, Russell Howes*, Mojtaba Komeili*, Matthew Muckley*, Ammar Rizvi*, Claire Roberts*, Koustuv Sinha*, Artem Zholus*, Sergio Arnaud*, Abha Gejji*, Ada Martin*, Francois Robert Hogan*, Daniel Dugas*, Piotr Bojanowski, Vasil Khalidov, Patrick Labatut, Francisco Massa, Marc Szafraniec, Kapil Krishnakumar, Yong Li, Xiaodong Ma, Sarath Chandar, Franziska Meier*, Yann LeCun*, Michael Rabbat* et Nicolas Ballas*
  Technical Report, 2025.
  #DL
  [website], [arXiv], [code], [huggingface], [blogpost]

• Torque-Aware Momentum
  Pranshu Malviya, Gonçalo Mordido, Aristide Baratin, Reza Babanezhad Harikandeh, Gintare Karolina Dziugaite, Razvan Pascanu et Sarath Chandar
  In ArXiv, 2024.
  #DL
  [arXiv]

• Interpretability Needs a New Paradigm
  Andreas Madsen, Himabindu Lakkaraju, Siva Reddy et Sarath Chandar
  In ArXiv, 2024.
  #NLP, #DL
  [arXiv]

• Interpretability in Action: Exploratory Analysis of VPT, a Minecraft Agent
  Karolis Jucys, George Adamopoulos, Mehrab Hamidi, Stephanie Milani, Mohammad Reza Samsami, Artem Zholus, Sonia Joseph, Blake Richards, Irina Rish et Özgür Şimşek
  Workshop on Mechanistic Interpretability @ ICML, 2024.
  #DL
  [arXiv]

• Segmentation of Multiple Sclerosis Lesions across Hospitals: Learn Continually or Train from Scratch?
  Naga Karthik Enamundram, Anne Kerbrat, Pierre Labauge, Tobias Granberg, Jason Talbott, Daniel S. Reich, Massimo Filippi, Rohit Bakshi, Virginie Callot, Sarath Chandar et Julien Cohen-Adad
  In ArXiv, 2022.
  [Medical Imaging meets NeurIPS, 2022]
  #DL, #Other
  [arXiv], [code]

• Feature diversity in self-supervised learning
  Pranshu Malviya* et Arjun Vaithilingam Sudhakar*
  Conference on Lifelong Learning Agents (CoLLAs) Workshop Track, 2022.
  #DL
  [arXiv]

• An Introduction to Lifelong Supervised Learning
  Shagun Sodhani, Mojtaba Faramarzi, Sanket Vaibhav Mehta, Pranshu Malviya, Mohamed Abdelsalam, Janarthanan Rajendran et Sarath Chandar
  In ArXiv, 2022.
  #DL
  [arXiv]

Articles de conférence et de revue

2026

33. Squeezing More from the Stream: Learning Representation Online for Streaming Reinforcement Learning
    Nilaksh*, Antoine Clavaud*, Mathieu Reymond, François Rivest et Sarath Chandar
    International Conference on Machine Learning (ICML), 2026.
    #RL, #DL
    [arXiv], [code]

34. Position: Modular Memory is the Key to Continual Learning Agents
    Vaggelis Dorovatas, Malte Schwerin, Andrew D. Bagdanov, Lucas Caccia, Antonio Carta, Laurent Charlin, Barbara Hammer, Tyler L. Hayes, Timm Hess, Christopher Kanan, Dhireesha Kudithipudi, Xialei Liu, Vincenzo Lomonaco, Jorge Mendez-Mendez, Darshan Patil, Ameya Prabhu, Elisa Ricci, Tinne Tuytelaars, Gido M van de Ven, Liyuan Wang, Joost van de Weijer, Jonghyun Choi, Martin Mundt et Rahaf Aljundi
    International Conference on Machine Learning (ICML), 2026.
    #DL
    [arXiv]

35. TAPNext++: What's Next for Tracking Any Point (TAP)?
    Sebastian Jung*, Artem Zholus*, Martin Sundermeyer, Carl Doersch, Ross Goroshin, David Joseph Tan, Sarath Chandar, Rudolph Triebel et Federico Tombari
    Findings of the IEEE CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2026.
    #DL
    [arXiv], [website], [code]

36. The Expressive Limits of Diagonal SSMs for State-Tracking
    Mehran Shakerinava, Behnoush Khavari, Siamak Ravanbakhsh et Sarath Chandar
    International Conference on Learning Representations (ICLR), 2026.
    #DL
    [openreview], [arXiv]

37. Investigating the Multilingual Calibration Effects of Language Model Instruction-Tuning
    Jerry Huang, Peng Lu, Qiuhao Zeng, Yusuke Iwasawa, Yutaka Matsuo, Sarath Chandar, Edison Marrese-Taylor et Irene Li
    Conference of the European Chapter of the Association for Computational Linguistics (EACL), 2026.
    #NLP, #DL
    [arXiv], [code]

38. Monitoring morphometric drift in lifelong learning segmentation of the spinal cord
    Enamundram Naga Karthik, Sandrine Bédard, Jan Valošek, Christoph S. Aigner, Elise Bannier, Josef Bednařík, Virginie Callot, Anna Combes, Armin Curt, Gergely David, Falk Eippert, Lynn Farner, Michael G Fehlings, Patrick Freund, Tobias Granberg, Cristina Granziera, RHSCIR Network Imaging Group, Ulrike Horn, Tomáš Horák, Suzanne Humphreys, Markus Hupp, Anne Kerbrat, Nawal Kinany, Shannon Kolind, Petr Kudlička, Anna Lebret, Lisa Eunyoung Lee, Caterina Mainero, Allan R. Martin, Megan McGrath, Govind Nair, Kristin P. O'Grady, Jiwon Oh, Russell Ouellette, Nikolai Pfender, Dario Pfyffer, Pierre-François Pradat, Alexandre Prat, Emanuele Pravatà, Daniel S. Reich, Ilaria Ricchi, Naama Rotem-Kohavi, Simon Schading-Sassenhausen, Maryam Seif, Andrew Smith, Seth A Smith, Grace Sweeney, Roger Tam, Anthony Traboulsee, Constantina Andrada Treaba, Charidimos Tsagkas, Zachary Vavasour, Dimitri Van De Ville, Kenneth Arnold Weber II, Sarath Chandar et Julien Cohen-Adad
    Imaging Neuroscience, 2026.
    #DL, #Other
    [mit], [arXiv]

2025

27. TRecViT: A Recurrent Video Transformer
    Viorica Pătrăucean, 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 et Razvan Pascanu
    Transactions on Machine Learning Research (TMLR), 2025.
    #DL
    [openreview], [arXiv], [code]

28. TAPNext: Tracking Any Point (TAP) as Next Token Prediction
    Artem Zholus, Carl Doersch, Yi Yang, Skanda Koppula, Viorica Pătrăucean, Xu Owen He, Ignacio Rocco, Mehdi S. M. Sajjadi, Sarath Chandar et Ross Goroshin
    International Conference on Computer Vision (ICCV), 2025.
    #DL, #Other
    [website], [arXiv], [code], [huggingface], [YouTube]

29. Steering Large Language Model Activations in Sparse Spaces
    Reza Bayat*, Ali Rahimi-Kalahroudi*, Mohammad Pezeshki, Sarath Chandar et Pascal Vincent
    Conference on Language Modeling (COLM), 2025.
    #NLP, #DL
    [openreview], [arXiv]

30. Manifold Metric: A Loss Landscape Approach for Predicting Model Performance
    Pranshu Malviya, Jerry Huang, Ariside Baratin, Quentin Fournier et Sarath Chandar
    Conference on Lifelong Learning Agents (CoLLAs), 2025.
    #DL
    [arXiv]

31. Revisiting Replay and Gradient Alignment for Continual Pre-Training of Large Language Models
    Istabrak Abbes, Gopeshh Subbaraj, Matthew Riemer, Nizar Islah, Tsuguchika Tabaru, Hiroaki Kingetsu, Sarath Chandar et Irina Rish
    Conference on Lifelong Learning Agents (CoLLAs), 2025.
    #NLP, #DL
    [arXiv], [code]

32. Compression via Pre-trained Transformers: A Study on Byte-Level Multimodal Data
    David Heurtel-Depeiges, Anian Ruoss, Joel Veness et Tim Genewein
    International Conference on Machine Learning (ICML), 2025.
    #DL
    [pmlr], [openreview], [arXiv]

33. BindGPT: A Scalable Framework for 3D Molecular Design via Language Modeling and Reinforcement Learning
    Artem Zholus, Maksim Kuznetsov, Roman Schutski, Rim Shayakhmetov, Daniil Polykovskiy, Sarath Chandar et Alex Zhavoronkov
    AAAI Conference on Artificial Intelligence (AAAI), 2025. [Best poster award]
    #DL, #RL
    [website], [arXiv], [code], [YouTube]

2024

20. Exploring Quantization for Efficient Pre-Training of Transformer Language Models
    Kamran Chitsaz, Quentin Fournier, Gonçalo Mordido et Sarath Chandar
    Findings of the Association for Computational Linguistics (EMNLP), 2024.
    #NLP, #DL
    [acl], [arXiv]

21. Sharpness-Aware Minimization Scaled by Outlier Normalization for Robust DNNs on In-Memory Computing Accelerators
    Sébastien Henwood, Gonçalo Mordido, Yvon Savaria, Sarath Chandar et François Leduc-Primeau
    Asilomar Conference on Signals, Systems, and Computers, 2024.
    [Conference on Lifelong Learning Agents (CoLLAs) Workshop Track, 2022]
    [Edge Intelligence Workshop (EIW), 2022]
    #DL
    [paper], [arXiv]

22. Lookbehind-SAM: k steps back, 1 step forward
    Gonçalo Mordido, Pranshu Malviya, Aristide Baratin et Sarath Chandar
    International Conference on Machine Learning (ICML), 2024.
    #DL
    [pmlr], [arXiv], [code], [YouTube]

23. Contrast-agnostic Spinal Cord Segmentation: A Comparative Study of ConvNets and Vision Transformers
    Naga Karthik Enamundram, Sandrine Bedard, Jan Valosek, Sarath Chandar et Julien Cohen-Adad
    Medical Imaging with Deep Learning (MIDL), 2024.
    #DL, #Other
    [openreview]

24. Promoting Exploration in Memory-Augmented Adam using Critical Momenta
    Pranshu Malviya, Gonçalo Mordido, Aristide Baratin, Reza Babanezhad Harikandeh, Jerry Huang, Simon Lacoste-Julien, Razvan Pascanu et Sarath Chandar
    Transactions on Machine Learning Research (TMLR), 2024.
    #DL
    [openreview], [arXiv]

25. A Responsible Framework for Applying Artificial Intelligence on Medical Images and Signals at the Point-of-care: the PACS-AI Platform
    Pascal Theriault-Lauzier, Denis Cobin, Olivier Tastet, Elodie Labrecque Langlais, Bahareh Taji, Guson Kang, Aun-Yeong Chong, Derek So, An Tang, Judy Wawira Gichoya, Sarath Chandar, Pierre-Luc Déziel, Julie G Hussin, Samuel Kadoury et Robert Avram
    Canadian Journal of Cardiology, 2024.
    #DL, #Other
    [paper]

26. Mastering Memory Tasks with World Models
    Mohammad Reza Samsami*, Artem Zholus*, Janarthanan Rajendran et Sarath Chandar
    International Conference on Learning Representations (ICLR), 2024. [Oral presentation.]
    #RL, #DL
    [openreview], [arXiv], [code]

27. On the Costs and Benefits of Adopting Lifelong Learning for Software Analytics - Empirical Study on Brown Build and Risk Prediction
    Doriane Olewicki, Sarra Habchi, Mathieu Nayrolles, Mojtaba Faramarzi, Sarath Chandar et Bram Adams
    International Conference on Software Engineering (ICSE) - Software Engineering in Practice Track, 2024. [ICSE24 SEIP Distinguished Paper Award]
    #DL
    [arXiv]

28. Fast and Accurate Output Error Estimation for Memristor-Based Deep Neural Networks
    Jonathan Kern, Sébastien Henwood, Gonçalo Mordido, Elsa Dupraz, Abdeldjalil Aïssa-El-Bey, Yvon Savaria et François Leduc-Primeau
    IEEE Transactions on Signal Processing, 2024.
    #DL
    [paper]

2023

11. Training DNNs Resilient to Adversarial and Random Bit-Flips by Learning Quantization Ranges
    Kamran Chitsaz, Gonçalo Mordido, Jean Pierre David et François Leduc-Primeau
    Transactions on Machine Learning Research (TMLR), 2023.
    #DL
    [openreview], [code]

12. An Empirical Investigation of the Role of Pre-training in Lifelong Learning
    Sanket Vaibhav Mehta, Darshan Patil, Sarath Chandar et Emma Strubell
    Journal of Machine Learning Research, 2023.
    #DL
    [jmlr], [arXiv]

13. DEUP: Direct Epistemic Uncertainty Prediction
    Moksh Jain, Salem Lahlou, Hadi Nekoei, Victor Butoi, Paul Bertin, Jarrid Rector-Brooks, Maksym Korablyov et Yoshua Bengio
    Transactions on Machine Learning Research (TMLR), 2023.
    #DL
    [openreview], [arXiv], [code]

14. Label fusion and training methods for reliable representation of inter-rater uncertainty
    Andreanne Lemay, Charley Gros, Naga Karthik Enamundram et Julien Cohen-Adad
    The Journal of Machine Learning for Biomedical Imaging (MELBA), 2023.
    #DL, #Other
    [paper]

2022

7. TAG: Task-based Accumulated Gradients for Lifelong Learning
   Pranshu Malviya, Balaraman Ravindran et Sarath Chandar
   Conference on Lifelong Learning Agents (CoLLAs), 2022.
   [Theory and Foundation of Continual Learning @ ICML, 2021]
   #DL
   [pmlr], [arXiv], [code]

8. Improving Meta-Learning Generalization with Activation-Based Early-Stopping
   Simon Guiroy, Christopher Pal, Gonçalo Mordido et Sarath Chandar
   Conference on Lifelong Learning Agents (CoLLAs), 2022.
   #DL
   [pmlr], [arXiv], [code], [YouTube]

9. Biological Sequence Design with GFlowNets
   Moksh Jain, Emmanuel Bengio, Alex-Hernandez Garcia, Jarrid Rector-Brooks, Bonaventure F. P. Dossou, Chanakya Ekbote, Jie Fu, Tianyu Zhang, Micheal Kilgour, Dinghuai Zhang, Lena Simine, Payel Das et Yoshua Bengio
   International Conference on Machine Learning (ICML), 2022.
   #DL
   [pmlr], [arXiv], [code]

10. Memory Augmented Optimizers for Deep Learning
    Paul-Aymeric McRae, Prasanna Parthasarathi, Mido Assran et Sarath Chandar
    International Conference on Learning Representations (ICLR), 2022.
    #DL
    [openreview], [arXiv], [code]

11. PatchUp: A Feature-Space Block-Level Regularization Technique for Convolutional Neural Networks
    Mojtaba Faramarzi, Mohammad Amini, Akilesh Badrinaaraayanan, Vikas Verma et Sarath Chandar
    AAAI Conference on Artificial Intelligence (AAAI), 2022.
    #DL
    [aaai], [arXiv], [code]

2021

2. IIRC: Incremental Implicitly-Refined Classification
   Mohamed Abdelsalam, Mojtaba Faramarzi, Shagun Sodhani et Sarath Chandar
   IEEE CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2021.
   #DL
   [website], [paper], [arXiv], [code], [PyPI], [docs]

2020

1. Fully Quantized Transformer for Machine Translation
   Gabriele Prato, Ella Charlaix et Mehdi Rezagholizadeh
   Findings of the Association for Computational Linguistics (EMNLP), 2020.
   #NLP, #DL
   [acl], [arXiv]