News
Accepted papers
- NeurIPS 2026
Revisiting Diffusion Fine-Tuning for Unsupervised Domain Adaptation
SOLA: A Structured Operator Library for Attention in Pretrained Vision Transformers
- ECCV 2026
AracNet: Revealing Debiasing Signals across Layers with Shallow Monitors
- TMLR 2026
VT-DUDA: Visual Token Conditioning for Diffusion-guided Unsupervised Domain Adaptation
- MICCAI 2026
CDPM-Align: Multi-Scale Guidance-Aligned Diffusion Pretraining for Robust Few-Shot Anatomical Landmark Detection Accepted as Oral Presentation
- ICML 2026
Distribution Alignment for One-Shot Federated Learning via Optimal Transport
- ICPR 2026
CutClean: Neural Network Pruning for Privacy-Preserving Inference
- CVPR 2026
Bias In, Bias Out? Finding Unbiased Subnetworks in Vanilla Models
If you can describe it, they can see it: Cross-Modal Learning of Visual Concepts from Textual Descriptions Findings track
- WACV 2026
How I Met Your Bias: Investigating Bias Amplification in Diffusion Models
Lose Your Self (LoYS): An Adversarial Entropy-Based Unsupervised Approach for Model Debiasing
- TMLR 2025
Say My Name: A Model's Bias Discovery Framework
Read on arXiv - NeurIPS 2025
Diffusing DeBias: Synthetic Bias Amplification for Model Debiasing
Read on arXiv - WACV 2025
Self-Supervised Pre-Training with Diffusion Model for Few-Shot Landmark Detection in X-Ray Images
Looking at Model Debiasing through the Lens of Anomaly Detection
Workshops, tutorials and sessions
- ECCV 2026
Co-organising the 3rd FAILED workshop Fairness and ethics towards transparent AI: model debiasing. Malmö, Sweden.
Workshop website - ISBI 2026
Co-organised a special session on safety and reliability in medical imaging London, United Kingdom.
Session details - ICIAP 2025
Co-organised the tutorial “A journey through model debiasing”
Tutorial website - ICCV 2025
Co-organised the 2nd FAILED workshop Fairness and ethics towards transparent AI: model debiasing. Honolulu, Hawaii, USA.
Workshop website - ECCV 2024
Co-organised the 1st FAILED workshop Fairness and ethics towards transparent AI: model debiasing. Milan, Italy.
Workshop website
Editorial roles and recognition
- CVPR 2027 Area Chair
- NeurIPS 2026 Area Chair
- ICML 2026 Area Chair
- ICML 2025 Top Area Chair
- CVPR 2025 Outstanding Reviewer
- MICCAI 2024 Honorable mention, reviewing
Qualifications
- ASN National scientific qualification as Associate Professor, Informatics
- ASN National scientific qualification as Associate Professor, Computer Engineering
Open positions
I am looking for PhD students and postdocs to work on machine learning and computer vision, with applications in medical, biological and industrial settings.
Open calls are posted here as they become available.