News

Paper accepted at ICML 2026

- Distribution Alignment for One-Shot Federated Learning via Optimal Transport

paper accepted at ICPR 2026

- CutClean: Neural Network Pruning for Privacy-Preserving Inference

Two papers accepted at 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 (CVPR Findings)

Two papers accepted at 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

Paper accepted at TMLR

- Say My Name: a Model's Bias Discovery Framework

👉 Arxiv link

Paper accepted at NeurIPS 2025

- Diffusing DeBias: Synthetic Bias Amplification for Model Debiasing

👉 Arxiv link

Co-organizing Special Session at ISBI 2026

Safety and Reliability in Medical Imaging, London, United Kingdom

👉 Session Website

Co-organized Tutorial at ICIAP 2025

"A journey through Model Debiasing"

👉 Tutorial Website

Co-organizing the 2nd FAILED Workshop at ICCV 2025

Fairness and ethics towards transparent AI: model #Debiasing

Honolulu, Hawaii, USA

👉 Workshop Website

Co-organized the 1st FAILED Workshop at ECCV 2024

👉 Workshop Website