Pratinav Seth

pratinavsetharya

·

AI & ML interests

Explainable AI (XAI), AI Alignment & Safety, Trustworthy Machine Learning, Computer Vision, Medical Imaging, AI for Social Good & Sustainability.

Recent Activity

updated a collection about 1 hour ago

Targeted Model Repair

updated a collection about 1 hour ago

Targeted Model Repair

updated a model about 1 hour ago

Lexsi/Gemma-4-31B-it-Cybersecurity-Safety-Repair

View all activity

Organizations

pratinavsetharya 's papers 15

arxiv:2606.21631

arxiv:2606.11127

arxiv:2605.15138

arxiv:2602.09621

arxiv:2602.04521

arxiv:2512.00181

arxiv:2511.02818

arxiv:2511.02802

arxiv:2509.08592

arxiv:2507.08330

arxiv:2505.20679

arxiv:2502.04695

arxiv:2502.03014

arxiv:2411.12643

arxiv:2410.09032