Linear Probe Recovery
No mentions found
This entity hasn't been tracked yet, or Iris is still building its knowledge base.
Related Articles from SNS
Can Vision Models Truly Forget? Mirage: Representation-Level Certification of Visual Unlearning
arXiv:2605.20282v2 Announce Type: replace Abstract: Machine unlearning in Vertical Federated Learning (VFL) has attracted growing interest, yet existing methods certify forgetting solely using output-level metrics. We challenge these claims by introducing Mirage, a representation-level auditing framework comprising four complementary diagnostics: Linear Probe Recovery (LPR), Centered Kernel Alignment (CKA), Feature Separability Scoring, and Layer-Wise Recovery Analysis. Through experiments...
Catastrophic Forgetting as Accessibility Collapse: A Three-Level Framework for Knowledge Persistence in Continual Learning
arXiv:2606.06032v1 Announce Type: new Abstract: Catastrophic forgetting is commonly interpreted as the irreversible erasure of previously acquired knowledge during sequential learning. In this work, we investigate an alternative perspective: that forgetting may arise not from complete destruction of task representations but from a loss of accessibility to preserved information. We introduce a three-level framework separating knowledge storage, representation, and accessibility, and evaluate...
Now You (Still) See Me: Detecting Evasive Steganographic Payloads in LLMs
arXiv:2606.09411v1 Announce Type: new Abstract: Large language models can be fine-tuned to encode prompt-borne secrets into fluent, seemingly benign outputs. This creates a steganographic exfiltration risk that is difficult to detect with output-level steganalysis.
SIRT7 regulates dosage compensation and safeguards the female X chromosome
Abstract Sirtuins are deacetylases implicated in stress responses and longevity in mammals1,2. Although their differential impact on disease for the two sexes has been noted3,4,5,6,7, the underlying reasons are unclear. Here, using Sirt7 as a model in mice, we examine the mechanisms leading to sex differences and find that Sirt7−/− female mice have decreased fitness throughout their lifespan.
A prognostic human brain network for diffuse midline glioma
Abstract Diffuse midline gliomas (DMGs) are near-universally lethal tumours of the childhood central nervous system1,2. In animal models, DMGs form brain-wide integrated networks through neuron-to-glioma synapses3,4,5,6 and glioma-to-glioma gap junctional coupling3. This extensive connectivity robustly promotes the growth and invasion of DMG3,4,5,6,7,8,9 and other glial malignancies10,11,12 through paracrine mechanisms and direct neuron-to-glioma synapses.