4 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.
Machine unlearning in large language models aims to remove unwanted knowledge while preserving the model's remaining capabilities. Although existing methods use retention objectives or restrict where edits occur, achieving the desired forgetting level can still leave collateral changes that impair non-target behavior....
This work proposes GRACE, a structured concept erasure framework designed to enable localized and selective intervention, and introduces a semantically weighted sensitive subspace estimation to precisely lock intervention directions, and employs lightweight subspace-constrained adapters to prevent global semantic distu...
Dynamic Semantic Steering (DSS) is proposed, a training-free, inference-time defense framework for robust and controllable concept erasure under prompt-level adversarial settings and achieves strong and consistent suppression across diverse concept categories and adversarial prompts.
Gaussian Core LoRA, a distribution-aware low-rank adaptation framework that enables prototype-adaptive erasure with a single lightweight adapter, and shows robustness to adversarial prompts, scalability to multi-identity and multi-style erasure, and compatibility with SDXL and FLUX.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
