publications

2023

  1. ICML
    Reprogramming Pretrained Language Models for Antibody Sequence Infilling
    Igor Melnyk, Vijil Chenthamarakshan, Pin-Yu Chen, and 4 more authors
    In Proceedings of the International Conference on Machine Learning (ICML), 2023
    arXiv Code Poster
  2. NeurIPS W
    Risk Assessment and Statistical Significance in the Age of Foundation Models
    Apoorva Nitsure, Youssef Mroueh, Mattia Rigotti, and 6 more authors
    arXiv:2310.07132, 2023
    arXiv Poster
  3. ArXiv
    Auditing and Generating Synthetic Data with Controllable Trust Trade-offs
    Brian Belgodere, Pierre Dognin, Adam Ivankay, and 11 more authors
    arXiv:2304.10819, 2023
    arXiv
  4. NeurIPS W
    AlphaFold Distillation for Protein Design
    Igor Melnyk, Aurelie Lozano, Payel Das, and 1 more author
    arXiv:2210.03488, 2023
    arXiv Code Poster

2022

  1. JAIR
    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 (JAIR), 2022
    PDF Blog Code
  2. EMNLP
    Knowledge Graph Generation From Text
    Igor Melnyk, Pierre Dognin, and Payel Das
    In Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP), 2022
    arXiv Code Poster
  3. ECML PKDD
    Cloud-Based Real-Time Molecular Screening Platform with MolFormer
    Brian Belgodere, Vijil Chenthamarakshan, Payel Das, and 8 more authors
    In Proceedings of the European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML PKDD), 2022
    arXiv

2021

  1. AAAI
    Improved Mutual Information Estimation
    Youssef Mroueh, Igor Melnyk, Pierre Dognin, and 2 more authors
    In Proceedings of the International Conference on Artificial Intelligence (AAAI), 2021
    PDF
  2. ICASSP
    Tabular Transformers for Modeling Multivariate Time Series
    Inkit Padhi, Yair Schiff, Igor Melnyk, and 6 more authors
    In Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2021
    PDF Code
  3. EMNLP
    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 Conference on Empirical Methods in Natural Language Processing (EMNLP), 2021
    arXiv Blog Code
  4. NeurIPS W
    Grapher: Multi-Stage Knowledge Graph Construction using Pretrained Language Models
    Igor Melnyk, Pierre Dognin, and Payel Das
    In Workshop on Deep Generative Models and Downstream Applications at NeurIPS, 2021
    Website
  5. NeurIPS W
    Benchmarking Deep Generative Models for Diverse Antibody Sequence Design
    Igor Melnyk, Payel Das, Vijil Chenthamarakshan, and 1 more author
    In Workshop on Deep Generative Models and Downstream Applications at NeurIPS, 2021
    arXiv Poster

2020

  1. EMNLP
    DualTKB: A Dual Learning Bridge between Text and Knowledge Base
    Pierre Dognin, Igor Melnyk, Inkit Padhi, and 2 more authors
    In Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP), 2020
    arXiv Blog Code
  2. NeurIPS
    Optimizing Mode Connectivity via Neuron Alignment
    Norman Tatro, Pin-Yu Chen, Payel Das, and 3 more authors
    In Proceedings of the Conference on Advances in Neural Information Processing Systems (NeurIPS), 2020
    arXiv Code
  3. CVPR W
    Alleviating Noisy Data in Image Captioning with Cooperative Distillation
    Pierre L. Dognin, Igor Melnyk, Youssef Mroueh, and 4 more authors
    VizWiz Workshopn at CVPR, 2020
    arXiv
  4. Arxiv
    Image Captioning as an Assistive Technology: Lessons Learned from Vizwiz 2020 Challenge
    Pierre Dognin, Igor Melnyk, Youssef Mroueh, and 6 more authors
    arXiv:2012.11696, 2020
    arXiv

2019

  1. CompPhys
    Deep Learning Algorithm for Data-driven Simulation of Noisy Dynamical System
    Kyongmin Yeo, and Igor Melnyk
    Journal of Computational Physics, 2019
    arXiv
  2. ICLR W
    Improved Adversarial Image Captioning
    Pierre Dognin, Igor Melnyk, Youssef Mroueh, and 2 more authors
    In Workshop on Deep Generative Models for Highly Structured Data at ICLR, 2019
    PDF
  3. ICML
    Estimating Information Flow in Deep Neural Networks
    Ziv Goldfeld, Ewout Van Den Berg, Kristjan Greenewald, and 4 more authors
    In Proceedings of the International Conference on Machine Learning (ICML), 2019
    arXiv Blog
  4. ICLR
    Wasserstein Barycenter Model Ensembling
    Pierre Dognin, Igor Melnyk, Youssef Mroueh, and 3 more authors
    In Proceedings of the International Conference on Learning Representations (ICLR), 2019
    arXiv Code Poster
  5. CVPR
    Adversarial Semantic Alignment for Improved Image Captions
    Pierre Dognin, Igor Melnyk, Youssef Mroueh, and 2 more authors
    In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2019
    arXiv

2018

  1. ICDM
    DE-RNN: Forecasting the Probability Density Function of Nonlinear Time Series
    Kyongmin Yeo, Igor Melnyk, Nam Nguyen, and 1 more author
    In Proceedings of the IEEE International Conference on Data Mining (ICDM), 2018
    PDF
  2. ACL
    Fighting Offensive Language on Social Media with Unsupervised Text Style Transfer
    Cicero Santos, Igor Melnyk, and Inkit Padhi
    In Proceedings of the Association for Computational Linguistics (ACL), 2018
    arXiv Blog

2017

  1. Arxiv
    R2N2: Residual Recurrent Neural Networks for Multivariate Time Series Forecasting
    Hardik Goel, Igor Melnyk, and Arindam Banerjee
    arXiv:1709.03159, 2017
    arXiv
  2. JMLR
    A Spectral Algorithm for Inference in Hidden Semi-Markov Models
    Igor Melnyk, and Arindam Banerjee
    The Journal of Machine Learning Research (JMLR), 2017
    PDF
  3. ICML W
    SenGen: Sentence Generating Neural Variational Topic Model
    Ramesh Nallapati, Igor Melnyk, Abhishek Kumar, and 1 more author
    Workshop on Generating Natural Language at ICML, 2017
    arXiv
  4. NeurIPS W
    Improved Neural Text Attribute Transfer with Non-Parallel Data
    Igor Melnyk, Cicero Nogueira dos Santos, Kahini Wadhawan, and 2 more authors
    Workshop on Learning Disentangled Representations: from Perception to Control at NeurIPS, 2017
    arXiv Poster

2016

  1. JAIS
    Vector Autoregressive Model-Based Anomaly Detection in Aviation Systems
    Igor Melnyk, Bryan Matthews, Hamed Valizadegan, and 2 more authors
    Journal of Aerospace Information Systems (JAIS), 2016
    PDF
  2. ICML
    Estimating Structured Vector Autoregressive Models
    Igor Melnyk, and Arindam Banerjee
    In Proceedings of the International Conference on Machine Learning (ICML), 2016
    PDF Slides
  3. KDD
    Semi-Markov Switching Vector Autoregressive Model-based Anomaly Detection in Aviation Systems
    Igor Melnyk, Arindam Banerjee, Bryan Matthews, and 1 more author
    In Proceedings of the International Conference on Knowledge Discovery and Data Mining (KDD), 2016
    PDF Slides

2015

  1. AISTATS
    A Spectral Algorithm for Inference in Hidden semi-Markov Models
    Igor Melnyk, and Arindam Banerjee
    In Proceedings of the International Conference on Artificial Intelligence and Statistics (AISTATS), 2015
    PDF

2013

  1. ICDM
    Detection of Precursors to Aviation Safety Incidents Due to Human Factors
    Igor Melnyk, Pranjul Yadav, Michael Steinbach, and 3 more authors
    In Proceedings of the IEEE International Conference on Data Mining Workshops (ICDM), 2013
    PDF

2012

  1. ICRA
    Cooperative Vision-Aided Inertial Navigation Using Overlapping Views
    Igor Melnyk, Joel Hesch, and Stergios Roumeliotis
    In Proceedings of the IEEE International Conference on Robotics and Automation (ICRA), 2012
    PDF