I'm an Applied Scientist II at Amazon Alexa AI in Turin, Italy, working on Large Language Models to make Alexa smarter for millions of users worldwide.
I'm also a PhD researcher in Artificial Intelligence at MICC, University of Florence, advised by Prof. Andrew D. Bagdanov and Prof. Marco Bertini. My research focuses on Multimodal Vision-Language Models (like CLIP) and their real-world applications.
My work has been published at NeurIPS 2026 (×2), CVPR 2026, ICLR 2026, ICLR 2025 and ECCV 2024.
Previously, I was an Applied Scientist Intern at Amazon (Rufus team, London), where I fine-tuned, evaluated and deployed Multimodal LLMs for Amazon Rufus.
🌐 Website: marcomistretta.github.io · 📄 CV (PDF) · 🎓 Google Scholar
-
WASP: Weakly Aligned Spatiotemporal Pairs for Fetal Brain MRI–Ultrasound Learning NeurIPS 2026 (main track) Authors: Correnti F., Magrini G., Mistretta M., Biondi N., Pala P., Ramalli A., Fiori S., Bagdanov A. D., Lenge M. Links: Project page · Code
-
GeoBiaset: A Counterfactual Benchmark for Demographic Bias in World-Level Geolocalization NeurIPS 2026 (Evaluations & Datasets track) Authors: Niccoli N., Dani S., Mistretta M., Bagdanov A. D., Bertini M., Seidenari L. Paper and dataset coming soon.
-
IsoCLIP: Decomposing CLIP Projectors for Efficient Intra-modal Alignment CVPR 2026 (main conference) Authors: Magistri S., Goswami D., Mistretta M., Twardowski B., van de Weijer J., Bagdanov A. D. Code: GitHub Repository
-
SpectralGCD: Spectral Concept Selection and Cross-modal Representation Learning for Generalized Category Discovery ICLR 2026 (main conference) Authors: Caselli L., Mistretta M., Magistri S., Bagdanov A. D. Code: GitHub Repository
-
Cross the Gap: Exposing the Intra-modal Misalignment in CLIP via Modality Inversion ICLR 2025 (main conference) Authors: Mistretta M.*, Baldrati A.*, Agnolucci L.*, Bertini M., Bagdanov A. D. Code: GitHub Repository
-
Improving Zero-shot Generalization of Learned Prompts via Unsupervised Knowledge Distillation ECCV 2024 (main conference) Authors: Mistretta M.*, Baldrati A.*, Bertini M., Bagdanov A. D. Code: GitHub Repository
-
RE-tune: Incremental Fine Tuning of Biomedical Vision-Language Models for Multi-label Chest X-ray Classification NeurIPS 2023, Medical Imaging meets NeurIPS Workshop Authors: Mistretta M., Bagdanov A. D.
* equal contribution
Applied Scientist II – Amazon Alexa AI (Turin, Italy) July 2026 – Present
- Working on cutting-edge Large Language Models to make Alexa smarter for millions of users worldwide.
Applied Scientist Intern – Amazon Rufus (London, UK) July 2025 – December 2025
- Worked on Generative AI and Multimodal Large Language Models (MLLMs) for Amazon Rufus.
- Fine-tuned, evaluated, and deployed multimodal models impacting millions of customers.
- 🧠 Multimodal Learning: Combining vision and language for richer model understanding.
- 💬 Prompt Learning: Optimizing prompts to effectively guide AI models.
- 🎯 Few-Shot Learning: Adapting AI to new tasks with limited examples.
- ♻️ Incremental Learning: Allowing models to keep learning without forgetting.
- 🖼️ Contrastive Self-Supervised Learning: Extracting insights from unlabeled data.
- Conferences: NeurIPS 2024, ICLR 2025, NeurIPS 2025, CVPR 2026
- Journals: IEEE Transactions on Multimedia, IEEE Transactions on Circuits and Systems for Video Technology
- Programming Languages: Python, Java, C++, MATLAB, R
- Frameworks & Tools: PyTorch, TensorFlow, NumPy, OpenCV, Git, Docker, Bash
