EraseSAE: Surgical Concept Erasure in Text-to-Video Diffusion Models via Sparse Autoencoders

תקציר מקורי באנגליתarXiv:2609.03629v2 Announce Type: replace-cross Abstract: Recent advances in text-to-video (T2V) diffusion models have demonstrated remarkable generative capabilities, yet their reliance on loosely curated training data raises pressing safety and copyright concerns. Concept erasure offers a principled remedy by removing unwanted semantics from pretrained models while preserving remaining concepts. However, existing approaches typically operate at a coarse granularity misaligned with the fine-grained, distributed nature of concept representations, leading to incomplete removal or degraded generation quality. We argue that surgical erasure fundamentally requires intervention at the level of monosemantic features, where each unit encodes a single interpretable concept. To this end, we propose