Publications

Preprints

• Emergent Natural Language with Communication Games for Improving Image Captioning Capabilities without Additional Data [arXiv]
  • By Parag Dutta and Ambedkar Dukkipati

Conference Papers

• One Encoder to Rule them All: Representation Learning for Model-free Visual Reinforcement Learning using Fourier Neural Operators

  • By Parag Dutta, Mohd. Ayyoob, Shalabh Bhatnagar and Ambedkar Dukkipati
  • In Proceedings of the 2025 IEEE/CVF International Conference on Computer Vision (ICCV)

• Active reinforcement learning strategies for offline policy improvement [ABS] [PDF]

  • By Ambedkar Dukkipati, Ranga Shaarad Ayyagari*, Bodhisattwa Dasgupta*, Parag Dutta* and Onteru Prabhas Reddy
  • In Proceedings of the Thirty-Ninth AAAI Conference on Artificial Intelligence 2025

• Causal Feature Alignment: Learning to Ignore Spurious Background Features [ABS] [PDF]

  • By Rahul Venkataraman, Parag Dutta, Vikram Melapudi and Ambedkar Dukkipati
  • In Proceedings of the 25^th IEEE/CVF Winter Conference on Computer Vision 2024

• Deep Representation Learning for Predicting Temporal Event Sets in the Continuous Time Domain [ABS] [PDF] [SUPP]

  • By Parag Dutta, Kawin Mayilvaghanan, Pratyaksha Sinha, and Ambedkar Dukkipati
  • In Proceedings of the 15^th Asian Conference on Machine Learning 2023

• CRUSH: Contextually Regularized and User Anchored Self-Supervised Hate Speech Detection [ABS] [PDF] [Video]

  • By Souvic Chakraborty*, Parag Dutta*, Sumegh Roychowdhury* and Animesh Mukherjee
  • In Findings of the Association for Computational Linguistics: NAACL 2022

• Active² Learning: Actively Reducing Redundancies in Active Learning Methods for Sequence Tagging and Machine Translation [ABS] [PDF] [Video]

  • By Rishi Hazra, Parag Dutta, Shubham Gupta, Md. Abdul Qaathir and Ambedkar Dukkipati
  • In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies