Rathinaraja Jeyaraj Ph.D.

Look at everything as an infant does; absorbing everything, not judging anything, not labelling anyone!!!

I work at the intersection of machine learning, computer vision, multimodal learning, and healthcare, with a focus on biomedical and clinical AI. My research interests include large language models (LLMs), vision-language models (VLMs), foundation models, and trustworthy AI for clinical decision support.

My work focuses on building end-to-end AI pipelines, from data preparation and system design to model development, evaluation, deployment, and maintenance. I develop scalable deep learning and multimodal systems for whole-slide image preprocessing, multiple instance learning, classification, segmentation, survival prediction, and image-text modeling, and build Streamlit applications to support clinical and research use. A major part of my work involves improving data quality, model generalizability, and reliability for tumor diagnosis, subtyping, biomarker prediction, segmentation, and survival analysis. I also have experience with GPU infrastructure, large-scale datasets, and distributed computing.

My research philosophy is simple: build reliable data, develop generalizable models, and deliver interpretable, reproducible, and practically useful AI systems.

news

Oct 02, 2026	🎉 Our research work has been accepted at MICCAI 2026!
Apr 21, 2026	🎉 Two research works have been accepted at CVPR 2026!

selected publications

arXiv

MUFASA: An Information Utility-Aware Preprocessing Framework for Reliable Model Reasoning in Computational Pathology

Rathinaraja Jeyaraj, Barathi Subramanian, Songmi Noh, and 7 more authors

2026

Bib HTML PDF

@article{jeyaraj2026mufasa,
  title = {MUFASA: An Information Utility-Aware Preprocessing Framework for Reliable Model Reasoning in Computational Pathology},
  author = {Jeyaraj, Rathinaraja and Subramanian, Barathi and Noh, Songmi and Peterson, Mitchell N. and Guo, Terry and Fisher, George A. and Shah, Nigam H. and Langlotz, Curtis P. and Montine, Thomas J. and Shen, Jeanne},
  journal = {arXiv preprint arXiv:2609.00424},
  year = {2026},
  archiveprefix = {arXiv},
  type = {journal}
}

MICCAI

TRIAGE-MIL: Multi-Axis Instance Selection and Semantic Hypergraph Modeling for Survival Prediction from Whole-Slide Images

Barathi Subramanian, Rathinaraja Jeyaraj, Songmi Noh, and 2 more authors

2026

Top 9 percent DOI Bib HTML

Accepted as a top 9 percent paper at MICCAI 2026.

@inproceedings{subramanian2026triagemil,
  title = {TRIAGE-MIL: Multi-Axis Instance Selection and Semantic Hypergraph Modeling for Survival Prediction from Whole-Slide Images},
  author = {Subramanian, Barathi and Jeyaraj, Rathinaraja and Noh, Songmi and Fisher, George and Shen, Jeanne},
  booktitle = {Medical Image Computing and Computer Assisted Intervention (MICCAI)},
  year = {2026},
  publisher = {Springer},
  doi = {10.1007/978-3-032-38172-9_62},
  type = {conference}
}

CVPR

Gesture2Music: A Low-Latency Real-Time Framework for Continuous Gesture-Driven Music Generation

Rathinaraja Jeyaraj, Barathi Subramanian, Kapilya Gangadharan, and 1 more author

2026

Bib HTML

@inproceedings{jeyaraj2026gesture2music,
  title = {Gesture2Music: A Low-Latency Real-Time Framework for Continuous Gesture-Driven Music Generation},
  author = {Jeyaraj, Rathinaraja and Subramanian, Barathi and Gangadharan, Kapilya and Paul, Anand},
  booktitle = {First International Workshop on Interactive Physical AI (IPA), IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)},
  year = {2026},
  type = {conference}
}

CVPR

Contrast-Enhanced Gating in GRUs for Robust Low-Data Sequence Learning

Barathi Subramanian, Rathinaraja Jeyaraj, and Anand Paul

2026

Bib HTML

@inproceedings{subramanian2026contrast,
  title = {Contrast-Enhanced Gating in GRUs for Robust Low-Data Sequence Learning},
  author = {Subramanian, Barathi and Jeyaraj, Rathinaraja and Paul, Anand},
  booktitle = {Women in Computer Vision Workshop (WiCV), Proceedings Track, IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)},
  year = {2026},
  type = {conference}
}

EAAI

Defect Detection in Fused Deposition Modelling using Lightweight Convolutional Neural Networks

Basil Kuriachen^*, Rathinaraja Jeyaraj^*, Deepak Raphael, and 3 more authors

2025

Bib HTML

@article{kuriachen2025defect,
  title = {Defect Detection in Fused Deposition Modelling using Lightweight Convolutional Neural Networks},
  author = {Kuriachen, Basil and Jeyaraj, Rathinaraja and Raphael, Deepak and Ashok, P. and {Shanmuga Sundari}, P. and Paul, Anand},
  journal = {Engineering Applications of Artificial Intelligence},
  volume = {141},
  year = {2025},
  publisher = {Elsevier},
  type = {journal}
}

NeurIPS

STARC-9: A Large-scale Dataset for Multi-Class Tissue Classification for CRC Histopathology

Barathi Subramanian^*, Rathinaraja Jeyaraj^*, Mitchell Nevin Peterson, and 5 more authors

2025

Bib HTML

@inproceedings{subramanian2025starc9,
  title = {STARC-9: A Large-scale Dataset for Multi-Class Tissue Classification for CRC Histopathology},
  author = {Subramanian, Barathi and Jeyaraj, Rathinaraja and Peterson, Mitchell Nevin and Guo, Terry and Shah, Nigam and Langlotz, Curtis and Ng, Andrew Y. and Shen, Jeanne},
  booktitle = {The Thirty-ninth Annual Conference on Neural Information Processing Systems (NeurIPS), Datasets and Benchmarks Track},
  year = {2025},
  type = {conference}
}