Across 17 public brain MRI datasets and eight frozen representations, the sequence is recognizable inside every dataset yet collapses on an unseen one, because each dataset encodes the sequence difference along different directions rather than because the features remember where a scan came from.
The work proposes Retain-aware Activation Steering (RASteer), a training-free method that first builds a retain subspace from the concepts to preserve, then uses Retain-Orthogonal Steering (ROS) to remove components aligned with this subspace from the erasure direction, and further introduces Overlap-Adaptive Calibration (OAC) to control, at each layer and denoising step, how much of each shared component is removed based on the overlap between the erasure direction and the retain subspace, thereby better balancing target erasure and concept preservation; experiments on unsafe-content, instance, and artistic-style erasure across multiple backbones and benchmarks show RASteer matches or outperforms the activation-steering and weight-editing baselines evaluated.
The work proposes FADE, a multi-concept unlearning framework for text-to-video diffusion transformers that first applies a joint closed-form key/value edit suppressing all target concepts, then trains per-concept frame-aware low-rank adapters gated by the frame index and denoising timestep to remove residual per-frame leakage, and combines adapters by a similarity-based soft router; erasing 16 concepts (objects, artistic styles, and nudity) from a single Wan2.1-T2V-1.3B backbone, FADE reduces residual object-benchmark accuracy to 4.9% against 15.5% for the strongest of eight baselines, keeps the VBench average within 0.9% of the unedited model, and the ranking holds under a VLM judge and a blinded human study.
You’re all caught up