3 papers indexed here
We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.
Not the right person? Other researchers publish under this name.
TRUST (Targeted Robust Selective fine Tuning), a novel approach for dynamically estimating target concept neurons and unlearning them through selective finetuning, empowered by a Hessian based regularization, is proposed.
Eval-unlearn is an open-source Python library providing a unified, reproducible benchmarking framework for concept unlearning in T2I Diffusion models, integrating twelve published unlearning techniques spanning fine-tuning, closed-form model editing, and inference-time intervention.
This work introduces a novel certification framework for T2I concept unlearning that provides high-confidence guarantees with bounded error on residual concept leakage and establishes certification as a necessary complement for reliable auditing of concept unlearning in T2I diffusion models.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
