Publications

2026

1. Coming Soon

   

   CroissantMiner: Automated Extraction and Validation of Croissant Metadata for ML Datasets

   Berke Arda, Mubashara Akhtar, Ahmetcan Yavuz, Paul Gerry, Sebastian Lobentanzer, Nobin Sarwar, Joan Giner-Miguelez, and 3 more authors

   Coming soon

   Bib Code

   @article{arda2026croissantminer,
     title = {CroissantMiner: Automated Extraction and Validation of Croissant Metadata for ML Datasets},
     author = {Arda, Berke and Akhtar, Mubashara and Yavuz, Ahmetcan and Gerry, Paul and Lobentanzer, Sebastian and Sarwar, Nobin and Giner-Miguelez, Joan and Chen, Kongtao and Zhang, Luyao and Sachan, Mrinmaya},
     year = {2026},
     note = {Coming soon},
     dimensions = {true},
     demo = {https://huggingface.co/spaces/bearda/croissantminer},
     dataset = {https://huggingface.co/datasets/croissantminer/croissantminer}
   }

2. Preprint’26

   

   Croissant Baker: Metadata Generation for Discoverable, Governable, and Reusable ML Datasets

   Rafi Al Attrach, Rajna Fani, Sebastian Lobentanzer, Joan Giner-Miguelez, Debanshu Das, Varuni H. K., Nobin Sarwar, and 13 more authors

   arXiv preprint arXiv:2605.15079

   arXiv Bib PDF Code

   @article{attrach2026croissantbaker,
     title = {Croissant Baker: Metadata Generation for Discoverable, Governable, and Reusable ML Datasets},
     author = {Al Attrach, Rafi and Fani, Rajna and Lobentanzer, Sebastian and Giner-Miguelez, Joan and Das, Debanshu and H. K., Varuni and Sarwar, Nobin and Ghosh, Rajat and Archit, Anwai and Motghare, Surbhi and Parry, Christina Conrad and Oala, Luis and Grosso, Lara and Vanschoren, Joaquin and Vogler, Steffen and Goswami, Sujata and Rosenthal, Eric S. and Ghassemi, Marzyeh and McDermott, Matthew and Pollard, Tom},
     journal = {arXiv preprint arXiv:2605.15079},
     year = {2026},
     dimensions = {true},
   }

3. ACL’26

   

   Multimodal Unlearning Across Vision, Language, Video, and Audio: Survey of Methods, Datasets, and Benchmarks

   Nobin Sarwar, Shubhashis Roy Dipta, Zheyuan Liu, and Vaidehi Patil

   In Findings of ACL

   TechRxiv Bib Code Website

   @inproceedings{sarwar2026mm-unlearning-survey,
     title = {{Multimodal Unlearning Across Vision, Language, Video, and Audio: Survey of Methods, Datasets, and Benchmarks}},
     author = {Sarwar, Nobin and {Roy Dipta}, Shubhashis and Liu, Zheyuan and Patil, Vaidehi},
     booktitle = {Findings of ACL},
     year = {2026},
     address = {San Diego, California, USA},
     month = jul,
     publisher = {Association for Computational Linguistics},
     techrxiv = {http://dx.doi.org/10.36227/techrxiv.176945748.88280394/v1},
     dimensions = {true},
   }

2025

1. NeurIPS-W’25

   

   FedMentor: Domain-Aware Differential Privacy for Heterogeneous Federated LLMs in Mental Health

   Nobin Sarwar and Shubhashis Roy Dipta

   In GenAI4Health Workshop, NeurIPS

   arXiv Bib PDF Code Poster

   @inproceedings{sarwar2025fedmentor,
     title = {FedMentor: Domain-Aware Differential Privacy for Heterogeneous Federated LLMs in Mental Health},
     author = {Sarwar, Nobin and {Roy Dipta}, Shubhashis},
     booktitle = {GenAI4Health Workshop, NeurIPS},
     year = {2025},
     url = {https://genai4health.github.io/},
     dimensions = {true}
   }

2. ICCV-W’25

   

   FilterRAG: Zero-Shot Informed Retrieval-Augmented Generation to Mitigate Hallucinations in VQA

   Nobin Sarwar

   In T2FM Workshop, ICCV

   arXiv Bib PDF Poster Slides

   @inproceedings{sarwar2025filterrag,
     title = {FilterRAG: Zero-Shot Informed Retrieval-Augmented Generation to Mitigate Hallucinations in VQA},
     author = {Sarwar, Nobin},
     booktitle = {T2FM Workshop, ICCV},
     year = {2025},
     url = {https://t2fm-ws.github.io/T2FM-ICCV25/},
     dimensions = {true}
   }