Activity

  • Principal Investigator: Jan 2020 - now

Preprints

Conference and Journal Papers

2025

  1. BindGPT: A Scalable Framework for 3D Molecular Design via Language Modeling and Reinforcement Learning
    , Maksim Kuznetsov, Roman Schutski, Rim Shayakhmetov, Daniil Polykovskiy, , and Alex Zhavoronkov
    AAAI Conference on Artificial Intelligence (AAAI), 2025.
    #DL, #RL
    [arXiv], [website]

2024

  1. Balancing Context Length and Mixing Times for Reinforcement Learning at Scale
    Matthew Riemer, Khimya Khetarpal, , and
    Conference on Neural Information Processing Systems (NeurIPS), 2024.
    #RL
    [openreview]

  2. Exploring Quantization for Efficient Pre-Training of Transformer Language Models
    , , , and
    Findings of the Association for Computational Linguistics (EMNLP), 2024.
    #NLP, #DL
    [acl], [arXiv]

  3. Context-Aware Assistant Selection for Improved Inference Acceleration with Large Language Models
    , Prasanna Parthasarathi, Mehdi Rezagholizadeh, and
    Conference on Empirical Methods in Natural Language Processing (EMNLP), 2024.
    #NLP
    [acl], [arXiv]

  4. Do Large Language Models Know How Much They Know?
    , , Prasanna Parthasarathi, Shagun Sodhani, and
    Conference on Empirical Methods in Natural Language Processing (EMNLP), 2024.
    #NLP
    [acl]

  5. Toward Debugging Deep Reinforcement Learning Programs with RLExplorer
    Rached Bouchoucha, Ahmed Haj Yahmed, , , Amin Nikanjam, , and Foutse Khomh
    International Conference on Software Maintenance and Evolution (ICSME), 2024.
    #RL
    [arXiv]

  6. Should We Attend More or Less? Modulating Attention for Fairness
    , , Samira Shabanian, and
    Conference on Language Modeling (COLM), 2024.
    #NLP
    [openreview], [arXiv]

  7. Are self-explanations from Large Language Models faithful?
    , , and Siva Reddy
    Findings of the Association for Computational Linguistics (ACL), 2024.
    #NLP
    [acl], [arXiv], [code], [YouTube]

  8. A deep-dive into the tradeoffs of preference alignment with PEFT
    , , Matthew Riemer, Pin-Yu Chen, Amal Zouaq, Payel Das, and
    Annual Meeting of the Association for Computational Linguistics (ACL), 2024.
    #NLP
    [acl], [arXiv]

  9. Why Don’t Prompt-Based Fairness Metrics Correlate?
    , , Ioana Baldini, and
    Annual Meeting of the Association for Computational Linguistics (ACL), 2024.
    #NLP
    [acl], [arXiv], [YouTube]

  10. Sub-goal Distillation: A Method to Improve Small Language Agents
    , Elias Stengel-Eskin, , and Marc-Alexandre Cote
    Conference on Lifelong Learning Agents (CoLLAs), 2024. [Oral presentation.]
    #RL, #NLP
    [arXiv]

  11. Lookbehind-SAM: k steps back, 1 step forward
    , , Aristide Baratin, and
    International Conference on Machine Learning (ICML), 2024.
    #DL
    [pmlr], [arXiv], [code], [YouTube]

  12. Faithfulness Measurable Masked Language Models
    , Siva Reddy, and
    International Conference on Machine Learning (ICML), 2024. [Spotlight award - top 3.5%]
    #NLP
    [pmlr], [arXiv], [code], [YouTube], [blogpost]

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

  14. Promoting Exploration in Memory-Augmented Adam using Critical Momenta
    , , Aristide Baratin, Reza Babanezhad Harikandeh, , Simon Lacoste-Julien, Razvan Pascanu, and
    Transactions on Machine Learning Research (TMLR), 2024.
    #DL
    [openreview], [arXiv]

  15. 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, , Pierre-Luc Déziel, Julie G Hussin, Samuel Kadoury, and Robert Avram
    Canadian Journal of Cardiology, 2024.
    #DL, #Other
    [paper]

  16. MVP: Minimal Viable Phrase for Long Text Understanding
    , Amal Zouaq, and
    Joint International Conference on Computational Linguistics, Language, Resources and Evaluation (LREC-COLING), 2024.
    #NLP
    [acl]

  17. Mastering Memory Tasks with World Models
    , , , and
    International Conference on Learning Representations (ICLR), 2024. [Oral presentation.]
    #RL, #DL
    [openreview], [arXiv]

  18. Intelligent Switching for Reset-Free RL
    , , Glen Berseth, and
    International Conference on Learning Representations (ICLR), 2024.
    #RL
    [openreview], [arXiv]

  19. 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, , , and Bram Adams
    International Conference on Software Engineering (ICSE) - Software Engineering in Practice Track, 2024. [ICSE24 SEIP Distinguished Paper Award.]
    #DL
    [arXiv]

  20. Fairness-Aware Structured Pruning in Transformers
    , , Samira Shabanian, Ioana Baldini, and
    AAAI Conference on Artificial Intelligence (AAAI), 2024.
    #NLP
    [aaai], [arXiv], [YouTube]

  21. Learning Conditional Policies for Crystal Design Using Offline Reinforcement Learning
    , Santiago Miret, , Mariano Phielipp, , and
    Digital Discovery Journal, 2024.
    #RL
    [paper]

2023

  1. Self-Influence Guided Data Reweighting for Language Model Pre-training
    , Tolga Bolukbasi, Sriram Ganapathy, Shikhar Vashishth, , and Partha Talukdar
    Conference on Empirical Methods in Natural Language Processing (EMNLP), 2023.
    #NLP
    [acl], [openreview], [arXiv]

  2. EpiK-Eval: Evaluation for Language Models as Epistemic Models
    , , Prasanna Parthasarathi, Shagun Sodhani, and
    Conference on Empirical Methods in Natural Language Processing (EMNLP), 2023.
    #NLP
    [acl], [openreview], [arXiv], [code]

  3. Measuring the Knowledge Acquisition-Utilization Gap in Pretrained Language Models
    Amirhossein Kazemnejad, Mehdi Rezagholizadeh, Prasanna Parthasarathi, and
    Findings of the Association for Computational Linguistics (EMNLP), 2023.
    #NLP
    [acl], [openreview], [arXiv]

  4. Replay Buffer with Local Forgetting for Adapting to Local Environment Changes in Deep Model-Based Reinforcement Learning
    , , Ida Momennejad, Harm van Seijen, and
    Conference on Lifelong Learning Agents (CoLLAs), 2023.
    [Deep Reinforcement Learning Workshop, NeurIPS, 2022]
    #RL
    [pmlr], [arXiv]

  5. Towards Few-shot Coordination: Revisiting Ad-hoc Teamplay Challenge In the Game of Hanabi
    , , , Miao Liu, and
    Conference on Lifelong Learning Agents (CoLLAs), 2023.
    #RL
    [pmlr], [arXiv]

  6. Dealing With Non-stationarity in Decentralized Cooperative Multi-Agent Deep Reinforcement Learning via Multi-Timescale Learning
    , , Amit Sinha, Mohammad Amini, , Aditya Mahajan, and
    Conference on Lifelong Learning Agents (CoLLAs), 2023.
    #RL
    [pmlr], [arXiv]

  7. Conditionally Optimistic Exploration for Cooperative Deep Multi-Agent Reinforcement Learning
    , Yangchen Pan, Chenjun Xiao, , and
    Conference on Uncertainty in Artificial Intelligence (UAI), 2023.
    #RL
    [pmlr], [arXiv]

  8. An Empirical Investigation of the Role of Pre-training in Lifelong Learning
    Sanket Vaibhav Mehta, , , and Emma Strubell
    Journal of Machine Learning Research, 2023.
    #DL
    [jmlr], [arXiv]

  9. Deep Learning on a Healthy Data Diet: Finding Important Examples for Fairness
    , Prasanna Parthasarathi, , Hamid Palangi, Samira Shabanian, and
    AAAI Conference on Artificial Intelligence (AAAI), 2023.
    #NLP
    [aaai], [arXiv], [YouTube]

2022

  1. Detecting Languages Unintelligible to Multilingual Models through Local Structure Probes
    , Prasanna Parthasarathi, Amal Zouaq, and
    Findings of the Association for Computational Linguistics (EMNLP), 2022.
    #NLP
    [acl]

  2. Local Structure Matters Most in Most Languages
    , Prasanna Parthasarathi, Amal Zouaq, and
    Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the International Joint Conference on Natural Language Processing (AACL-IJCNLP), 2022.
    #NLP
    [acl]

  3. TAG: Task-based Accumulated Gradients for Lifelong Learning
    , Balaraman Ravindran, and
    Conference on Lifelong Learning Agents (CoLLAs), 2022.
    [Workshop on Theory and Foundation of Continual Learning, ICML, 2021]
    #DL
    [pmlr], [arXiv], [code]

  4. Improving Meta-Learning Generalization with Activation-Based Early-Stopping
    , Christopher Pal, , and
    Conference on Lifelong Learning Agents (CoLLAs), 2022.
    #DL
    [pmlr], [arXiv], [code], [YouTube]

  5. Combining Reinforcement Learning and Constraint Programming for Sequence-Generation Tasks with Hard Constraints
    , , and Gilles Pesant
    International Conference on Principles and Practice of Constraint Programming (CP), 2022.
    #RL
    [paper]

  6. Towards Evaluating Adaptivity of Model-Based Reinforcement Learning Methods
    , , , Ida Momennejad, , and Harm van Seijen
    International Conference on Machine Learning (ICML), 2022.
    #RL
    [pmlr], [arXiv], [code]

  7. Post-hoc Interpretability for Neural NLP: A Survey
    , Siva Reddy, and
    ACM Computing Surveys, 2022.
    #NLP
    [acm], [arXiv]

  8. Local Structure Matters Most: Perturbation Study in NLU
    , Prasanna Parthasarathi, Amal Zouaq, and
    Findings of the Association for Computational Linguistics (ACL), 2022.
    #NLP
    [acl], [arXiv]

  9. Memory Augmented Optimizers for Deep Learning
    , Prasanna Parthasarathi, Mido Assran, and
    International Conference on Learning Representations (ICLR), 2022.
    #DL
    [openreview], [arXiv], [code]

  10. PatchUp: A Feature-Space Block-Level Regularization Technique for Convolutional Neural Networks
    , Mohammad Amini, , Vikas Verma, and
    AAAI Conference on Artificial Intelligence (AAAI), 2022.
    #DL
    [aaai], [arXiv], [code]

2021

  1. A Survey of Data Augmentation Approaches for NLP
    Steven Y. Feng, Varun Gangal, Jason Wei, , Soroush Vosoughi, Teruko Mitamura, and Eduard Hovy
    Findings of the Association for Computational Linguistics (ACL-IJCNLP), 2021.
    #NLP
    [acl], [arXiv]

  2. MLMLM: Link Prediction with Mean Likelihood Masked Language Model
    , Philippe Trempe, Amal Zouaq, and
    Findings of the Association for Computational Linguistics (ACL-IJCNLP), 2021.
    #NLP
    [acl], [arXiv]

  3. Continuous Coordination As a Realistic Scenario for Lifelong Learning
    , , Aaron Courville, and
    International Conference on Machine Learning (ICML), 2021.
    #RL
    [pmlr], [arXiv], [code]

  4. A Brief Study on the Effects of Training Generative Dialogue Models with a Semantic loss
    Prasanna Parthasarathi, , Joelle Pineau, and
    Proceedings of the 22nd Annual SIGdial Meeting on Discourse and Dialogue, 2021.
    #NLP
    [acl]

  5. Do Encoder Representations of Generative Dialogue Models Encode Sufficient Information about the Task ?
    Prasanna Parthasarathi, , and Joelle Pineau
    Proceedings of the 22nd Annual SIGdial Meeting on Discourse and Dialogue, 2021.
    #NLP
    [acl]

  6. IIRC: Incremental Implicitly-Refined Classification
    , , Shagun Sodhani, and
    IEEE CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2021.
    #DL
    [paper], [arXiv], [code], [website], [PyPI], [docs]

  7. Towered Actor Critic for Handling Multiple Action Types in Reinforcement Learning For Drug Discovery
    Sai Krishna Gottipati, Yashaswi Pathak, Boris Sattarov, Sahir, Rohan Nuttall, Mohammad Amini, Matthew E. Taylor, and
    AAAI Conference on Artificial Intelligence (AAAI), 2021.
    #RL
    [aaai]

2020

  1. The LoCA Regret: A Consistent Metric to Evaluate Model-Based Behavior in Reinforcement Learning
    Harm van Seijen, , , and
    Conference on Neural Information Processing Systems (NeurIPS), 2020.
    #RL
    [neurips], [arXiv], [code]

  2. Learning To Navigate The Synthetically Accessible Chemical Space Using Reinforcement Learning
    Sai Krishna Gottipati*, Boris Sattarov*, Sufeng Niu, Yashaswi Pathak, Haoran Wei, Shengchao Liu, Karam MJ Thomas, Simon Blackburn, Connor W Coley, Jian Tang, , and Yoshua Bengio
    International Conference on Machine Learning (ICML), 2020.
    #RL
    [pmlr], [arXiv]