Forgetting That Sticks: Quantization-Permanent Unlearning via Circuit Attribution
Paper • 2605.15138 • Published • 6
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 2 hours ago
Lexsi/audit-recover-apply_safe_lora-qwen3-4b-code updated a model about 2 hours ago
Lexsi/audit-recover-apply_safe_lora-qwen3-4b-gsm8k updated a model about 3 hours ago
Lexsi/audit-recover-apply_safe_lora-gemma3-4b-dollyOrganizations
