Llama-2-7B on MUSE-News: target, retrained oracle and unlearned models (NPO, SimNPO, GradDiff, RMU; SAM, ILU, LAT defenses).
Varun Sampath Kumar PRO
Lordvarun23
AI & ML interests
Computer Vision
Recent Activity
updated a model 1 day ago
Lordvarun23/qwen2.5-vl-3b-mllmu-manu-v2-forget10 updated a collection 3 days ago
MLLMU-Bench Unlearning updated a collection 3 days ago
MLLMU-Bench UnlearningOrganizations
None yet