arxiv:2602.04521
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 model about 11 hours ago
pratinavsetharya/llama31-8b-hh-rlhf-aligned published a model about 12 hours ago
pratinavsetharya/llama31-8b-hh-rlhf-aligned submitted a paper about 16 hours ago
Forgetting That Sticks: Quantization-Permanent Unlearning via Circuit AttributionOrganizations
