Publications

2024

  1. Value Alignment from Unstructured Text
    Inkit Padhi, Karthikeyan Natesan Ramamurthy, Prasanna Sattigeri, and 3 more authors
    In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing: Industry Track, Nov 2024
  2. Programming Refusal with Conditional Activation Steering
    Bruce W. Lee, Inkit Padhi, Karthikeyan Natesan Ramamurthy, and 4 more authors
    Nov 2024
  3. When in Doubt, Cascade: Towards Building Efficient and Capable Guardrails
    Manish Nagireddy, Inkit Padhi, Soumya Ghosh, and 1 more author
    ArXiv, Nov 2024
  4. WikiContradict: A Benchmark for Evaluating LLMs on Real-World Knowledge Conflicts from Wikipedia
    Yufang Hou, Alessandra Pascale, Javier Carnerero-Cano, and 5 more authors
    Nov 2024
  5. Split, Unlearn, Merge: Leveraging Data Attributes for More Effective Unlearning in LLMs
    Swanand Ravindra Kadhe, Farhan Ahmed, Dennis Wei, and 2 more authors
    Nov 2024
  6. Contextual Moral Value Alignment Through Context-Based Aggregation
    Pierre Dognin, Jesus Rios, Ronny Luss, and 7 more authors
    Nov 2024
  7. Detectors for Safe and Reliable LLMs: Implementations, Uses, and Limitations
    Swapnaja Achintalwar, Adriana Alvarado Garcia, Ateret Anaby-Tavor, and 35 more authors
    Nov 2024
  8. Alignment Studio: Aligning Large Language Models to Particular Contextual Regulations
    Swapnaja Achintalwar, Ioana Baldini, Djallel Bouneffouf, and 16 more authors
    IEEE Internet Computing, Nov 2024
    DOI
  9. ComVas: Contextual Moral Values Alignment System
    Inkit Padhi, Pierre Dognin, Jesus Rios, and 8 more authors
    In Proceedings of the Thirty-Third International Joint Conference on Artificial Intelligence, IJCAI-24, Aug 2024
    Demo Track
    DOI
  10. Auditing and Generating Synthetic Data with Controllable Trust Trade-offs
    Brian Belgodere, Pierre Dognin, Adam Ivankay, and 11 more authors
    IEEE Journal on Emerging and Selected Topics in Circuits and Systems, Aug 2024
    DOI

2023

  1. The Impact of Positional Encoding on Length Generalization in Transformers
    Amirhossein Kazemnejad, Inkit Padhi, Karthikeyan Natesan Ramamurthy, and 2 more authors
    In Advances in Neural Information Processing Systems, Aug 2023
  2. Influence Based Approaches to Algorithmic Fairness: A Closer Look
    Soumya Ghosh, Prasanna Sattigeri, Inkit Padhi, and 2 more authors
    In XAI in Action: Past, Present, and Future Applications, Aug 2023
  3. Reprogramming Pretrained Language Models for Antibody Sequence Infilling
    Igor Melnyk, Vijil Chenthamarakshan, Pin-Yu Chen, and 4 more authors
    In Proceedings of the 40th International Conference on Machine Learning, 23–29 jul 2023
    PDF
  4. The incentive gap in data work in the era of large models
    Katy Ilonka Gero, Payel Das, Pierre Dognin, and 3 more authors
    Nature Machine Intelligence, Jun 2023
    DOI
  5. Accelerating material design with the generative toolkit for scientific discovery
    Matteo Manica, Jannis Born, Joris Cadow, and 21 more authors
    npj Computational Materials, May 2023
    DOI
  6. Explainable Cross-Topic Stance Detection for Search Results
    Tim Draws, Karthikeyan Natesan Ramamurthy, Ioana Baldini, and 4 more authors
    In Proceedings of the 2023 Conference on Human Information Interaction and Retrieval, Austin, TX, USA, May 2023
    DOI
  7. Cloud-Based Real-Time Molecular Screening Platform with MolFormer
    Brian Belgodere, Vijil Chenthamarakshan, Payel Das, and 9 more authors
    May 2023
    DOI

2022

  1. Fair Infinitesimal Jackknife: Mitigating the Influence of Biased Training Data Points Without Refitting
    Prasanna Sattigeri, Soumya Ghosh, Inkit Padhi, and 2 more authors
    In Advances in Neural Information Processing Systems, May 2022
  2. Large-scale chemical language representations capture molecular structure and properties
    Jerret Ross, Brian Belgodere, Vijil Chenthamarakshan, and 3 more authors
    Nature Machine Intelligence, Dec 2022
    DOI
  3. Image Captioning as an Assistive Technology: Lessons Learned from VizWiz 2020 Challenge
    Pierre Dognin, Igor Melnyk, Youssef Mroueh, and 6 more authors
    Journal of Artificial Intelligence Research, Jan 2022
    DOI

2021

  1. ReGen: Reinforcement Learning for Text and Knowledge Base Generation using Pretrained Language Models
    Pierre Dognin, Inkit Padhi, Igor Melnyk, and 1 more author
    In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, Nov 2021
    DOI
  2. Tabular Transformers for Modeling Multivariate Time Series
    Inkit Padhi, Yair Schiff, Igor Melnyk, and 6 more authors
    In ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Jun 2021
    DOI
  3. Accelerated antimicrobial discovery via deep generative models and molecular dynamics simulations
    Payel Das, Tom Sercu, Kahini Wadhawan, and 12 more authors
    Nature Biomedical Engineering, Mar 2021
    DOI
  4. Generate Your Counterfactuals: Towards Controlled Counterfactual Generation for Text
    Nishtha Madaan, Inkit Padhi, Naveen Panwar, and 1 more author
    Proceedings of the AAAI Conference on Artificial Intelligence, May 2021
    DOI

2020

  1. Alleviating Noisy Data in Image Captioning with Cooperative Distillation
    Pierre Dognin, Igor Melnyk, Youssef Mroueh, and 4 more authors
    May 2020
  2. DualTKB: A Dual Learning Bridge between Text and Knowledge Base
    Pierre Dognin, Igor Melnyk, Inkit Padhi, and 2 more authors
    In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), Nov 2020
    DOI
  3. Learning Implicit Text Generation via Feature Matching
    Inkit Padhi, Pierre Dognin, Ke Bai, and 4 more authors
    In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, Jul 2020
    DOI
  4. CogMol: Target-Specific and Selective Drug Design for COVID-19 Using Deep Generative Models
    Vijil Chenthamarakshan, Payel Das, Samuel Hoffman, and 8 more authors
    In Advances in Neural Information Processing Systems, Jul 2020

2019

  1. Interactive Visual Exploration of Latent Space (IVELS) for peptide auto-encoder model selection
    Tom Sercu, Sebastian Gehrmann, Hendrik Strobelt, and 5 more authors
    Jul 2019
  2. Learning Implicit Generative Models by Matching Perceptual Features
    Cicero Nogueira dos Santos, Youssef Mroueh, Inkit Padhi, and 1 more author
    In Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), Oct 2019
  3. Sobolev Independence Criterion
    Youssef Mroueh, Tom Sercu, Mattia Rigotti, and 2 more authors
    In Advances in Neural Information Processing Systems, Oct 2019
  4. Generative Feature Matching Networks
    Cicero Nogueira Santos, Inkit Padhi, Pierre Dognin, and 1 more author
    Oct 2019

2018

  1. Data Driven Techniques for Organizing Scientific Articles Relevant to Biomimicry
    Yuanshuo Zhao, Ioana Baldini, Prasanna Sattigeri, and 3 more authors
    In Proceedings of the 2018 AAAI/ACM Conference on AI, Ethics, and Society, New Orleans, LA, USA, Oct 2018
    DOI
  2. PepCVAE: Semi-Supervised Targeted Design of Antimicrobial Peptide Sequences
    Payel Das, Kahini Wadhawan, Oscar Chang, and 6 more authors
    Oct 2018
  3. Fighting Offensive Language on Social Media with Unsupervised Text Style Transfer
    Cicero Santos, Igor Melnyk, and Inkit Padhi
    In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), Jul 2018
    DOI

2017

  1. Improved Neural Text Attribute Transfer with Non-parallel Data
    Igor Melnyk, Cicero Nogueira Santos, Kahini Wadhawan, and 2 more authors
    Jul 2017

2016

  1. Does String-Based Neural MT Learn Source Syntax?
    Xing Shi, Inkit Padhi, and Kevin Knight
    In Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing, Nov 2016
    DOI