Inference-Time Machine Unlearning via Gated Activation Redirection

Large Language Models memorize vast amounts of training data, raising concerns regarding privacy, copyright infringement, and safety. Machine unlearning seeks to remove the influence of a targeted forget set while preserving model performance, ideally approximating a model retrained from scratch without the forget set. Existing approaches aim to achieve this by updating model parameters via gradient-based methods. However, these updates are computationally expensive, lead to irreversible weight changes, and degrade when the model is quantized for deployment. A recent alternative to changing model weights is activation engineering, where activations are changed during inference to steer model behavior. Despite circumventing weight editing, naive activation steering introduces its own failure modes, as a single global steering vector applies the same intervention to every input, leading to unintended changes in model behavior. We introduce Inference-Time Unlearning via Gated Activation Redirection (GUARD-IT), a training- and gradient-free method that unlearns via input-dependent activation steering at inference time. The resulting intervention is applied as a norm-preserving rotation in the residual stream, leaving model weights untouched. Experiments on TOFU and MUSE show that GUARD-IT matches or exceeds 12 gradient-based baselines across three model scales, while being the only method to simultaneously preserve utility, suppress memorization, and avoid catastrophic collapse across all settings. GUARD-IT further supports continual unlearning without retraining, and remains effective under quantization, a scenario in which parameter-editing methods degrade.

Low-Rank Adapters Initialization via Gradient Surgery for Continual Learning

LoRA is widely adopted for continual fine-tuning of Large Language Models due to its parameter efficiency, modularity across tasks, and compatibility with replay strategies. However, LoRA-based continual learning remains vulnerable to catastrophic forgetting, whose severity depends on how successive task gradients interact: when consecutive task gradients conflict, standard adapter initializations channel updates into subspaces that overwrite previously learned directions. We propose SLICE, a gradient-surgery-based initialization for LoRA adapters in continual learning. SLICE accumulates gradients from both the current task and a replay buffer of prior tasks, reconciles them through a projection operator, and decomposes the result via truncated SVD to initialize the adapter weights. We evaluate SLICE on the TRACE benchmark and sequences of Super-NI tasks, including a set of adversarial Super-NI sequences that we construct by mining task pairs with maximally opposing gradients. Compared to vanilla LoRA, LoRA-GA, and LoRAM, SLICE consistently achieves a better stability-plasticity trade-off, improving Average Performance, Final Performance and Forgetting metrics while preserving General Performance and In Context Performance across both standard and adversarial continual learning sequences.

Zero-shot performance of the Segment Anything Model in 2D medical imaging: A comprehensive evaluation and practical guidelines

Segmentation in medical imaging is a critical component for the diagnosis, monitoring, and treatment of various diseases and medical conditions. Presently, the medical segmentation landscape is dominated by numerous specialized deep learning models, each fine-tuned for specific segmentation tasks and image modalities. The recently-introduced Segment Anything Model (SAM) employs the ViT neural architecture and harnesses a massive training dataset to segment nearly any object; however, its suitability to the medical domain has not yet been investigated. In this study, we explore the zero-shot performance of SAM in medical imaging by implementing eight distinct prompt strategies across six datasets from four imaging modalities, including X-ray, ultrasound, dermatoscopy, and colonoscopy. Our findings reveal that SAM's zero-shot performance is not only comparable to, but in certain cases, surpasses the current state-of-the-art. Based on these results, we propose practical guidelines that require minimal interaction while consistently yielding robust outcomes across all assessed contexts. The source code, along with a demonstration of the recommended guidelines, can be accessed at https://github.com/Malta-Lab/SAM-zero-shot-in-Medical-Imaging.