Vinay Gogineni
Associate Professor. University of Southern Denmark.
Mærsk 2,
Campusvej 55
Odense, Denmark
I am an Associate Professor at the Applied Artificial Intelligence and Data Science Unit, The Mærsk Mc-Kinney Møller Institute, University of Southern Denmark, where I lead the SDU Responsible and Safe AI Lab. I conduct research in Artificial Intelligence (AI), focusing on three core pillars including foundational AI, responsible AI, and quantum AI, with applications in healthcare, the industrial internet of things, life sciences, and optics.
Within Foundational AI, I make efforts to advance Deep Learning and its subfields, including Graph-based and Generative models, with a focus on improving model efficiency, generalization, and handling multimodalities.
In Responsible AI, I develop privacy-preserving and trustworthy AI systems using Federated Learning to ensure data confidentiality while addressing challenges such as heterogeneity, communication efficiency, personalization, privacy and security. I also develop Machine Unlearning methods that help AI comply with GDPR and the AI Act, while promoting fairness, transparency, and unbiased decision-making.
In Quantum AI, I co-design AI architectures to align with quantum requirements, enabling efficient implementation of classical AI models in the quantum domain.
In addition to fundamental research, my research in Applied AI has led to the development of a personalized cervical cancer screening recommender system to mitigate under- and over-treatment, and continues with AI-based early detection systems for colorectal cancer, cardio calcification, and dementia.
I am an IEEE Senior Member, Affiliated member of Pioneer Center for AI, Denmark, Member of IEEE Sensors Editorial board, recipient of the HC Ørsted Research Talent Award, 2024, Denmark, Best Poster Award from HAMLETS Conference/Workshop, 2025 in Copenhagen, Denmark, and Best Paper Award from APSIPA ASC, 2021 in Tokyo, Japan.
Collaboration Opportunities
I am open to collaborations with both academia and industry. If you are interested in partnering on research projects or innovative AI applications, please feel free to reach out to me.
For postdoc candidates with a background in AI or Large-Scale Optimization, I encourage you to review our recent work. If it aligns with your interests and you wish to join our team, please send me your CV. While fully funded positions may not always be available, I (our unit) will support your fellowship applications to Danish and European funding agencies.
Interested Ph.D. students are also welcome to enquire about applying for funding. Master and Bachelor students are welcome to inquire about opportunities with me. We welcome and support international students visiting via the DDSA Visiting Grant.
News
| Sep 08, 2026 | Delivered a talk titled “Responsible AI in Clinical and Public Health: Trust, Fairness, and Privacy,” at National Institute of Public Health, Copenhagen. |
|---|---|
| Aug 08, 2026 | The Metric, Not the Model: Anatomy Confounds Attention Faithfulness in Coronary Calcium, has been accepted to MI4MedFM at MICCAI 2026. Congratulations Congratulations Jyothi 👏. |
| Aug 04, 2026 | Our bachelors’ students thesis work “Synthetic Data Augmentation via Stable Diffusion for Polyp Characterisation in Colon Capsule Endoscopy” has been accepted to SASHIMI@MICCAI 2026. Congratulations Florentin Mustafa and Mohamed Wali-Wali 👏. |
| Jun 15, 2026 | Delivered a plenary talk titled “Responsible AI and Mathematical Foundations of Machine Unlearning,” at Scandinavian Conference on AI (SCAI), 2026, Odense. |
| Apr 01, 2026 | Carlsberg Foundation granted 80000 DKK to support Scandinavian Conference on AI (SCAI), 2026! I sincerely thank the Carlsberg Foundation for their generous support. |
Selected Publications
- Responsible AIControlling Path Dependence in Gradient Ascent Unlearning through Forget-Set OrderingIn Forty-Second Annual Conference on Uncertainty in Artificial Intelligence (UAI), 2026
- Responsible AIFINU: Fisher-Informed Noise Injection for Efficient Zero-Shot UnlearningIn 2026 International Joint Conference on Neural Networks (IJCNN), 2026
- Responsible AIRKLU: Redistributive KL Distillation for Efficient Retain-Free Machine UnlearningIn European Symposium on Artificial Neural Networks (ESANN), 2026
- Responsible AIOn the Path Dependence of Gradient Ascent-Based UnlearningIn ICLR Third Workshop on Test-Time Updates (Main Track), 2026
- Responsible AIThe Metric, Not the Model: Anatomy Confounds Attention Faithfulness in Coronary CalciumIn 1st MICCAI Workshop on Mechanistic Interpretability for Medical Foundational Models, 2026
- Applied AISynthetic Data Augmentation via Stable Diffusion for Polyp Characterisation in Colon Capsule EndoscopyIn MICCAI 2026 Workshop on Simulation and Synthesis in Medical Imaging (SASHIMI), 2026
- Responsible AIEfficient Knowledge Deletion from Trained Models Through Layer-wise Partial Machine UnlearningJournal of Machine Learning Research, 2025