arXiv:2601.04278v1 Announce Type: new Abstract: Although machine unlearning is essential for removing private, harmful, or copyrighted content from LLMs, current benchmarks often fail to faithfully represent the true “forgetting scope” learned by the model. We formalize two distinct unlearning granularities, domain-level and instance-level, and propose BiForget, an automated framework for synthesizing high-quality forget sets. Unlike prior work relying on external generators, BiForget exploits the target model per se to elicit data that matches its internal knowledge distribution through […]

Ver mais

You may come across a programming task where you want to implement the following pattern: try this and, if it doesn’t work out, try the other thing. In other words, you want a computation composed of two (or more) alternatives which should be tried one after the other until one of them produces a useful result. As an example, let’s build a function that takes a String as input and returns Just String if that input is either […]

Ver mais

arXiv:2601.00864v1 Announce Type: cross Abstract: Graphs are commonly used in machine learning to model relationships between instances. Consider the task of predicting the political preferences of users in a social network; to solve this task one should consider, both, the features of each individual user and the relationships between them. However, oftentimes one is not interested in the label of a single instance but rather in the distribution of labels over a set of instances; e.g., when predicting […]

Ver mais

EFF has, for many years, raised the alarm about the proliferation of stalkerware—commercially-available apps designed to be installed covertly on another person’s device and exfiltrate data from that device without their knowledge. In particular, we have urged the makers of anti-virus products for Android phones to improve their detection of stalkerware and call it out explicitly to users when it is found. In 2020  and 2021, AV Comparatives ran tests to see how well the most popular anti-virus […]

Ver mais

arXiv:2601.03362v1 Announce Type: new Abstract: Soft boundaries, like thin hairs, are commonly observed in natural and computer-generated imagery, but they remain challenging for 3D vision due to the ambiguous mixing of foreground and background cues. This paper introduces Guardians of the Hair (HairGuard), a framework designed to recover fine-grained soft boundary details in 3D vision tasks. Specifically, we first propose a novel data curation pipeline that leverages image matting datasets for training and design a depth fixer network […]

Ver mais

While most popular collaborative filtering methods use low-rank matrix factorization and parametric density assumptions, this article proposes an approach based on distribution-free concentration inequalities. Using agnostic hierarchical sampling assumptions, functions of observed ratings are provably close to their expectations over query ratings, on average. A joint probability distribution over queries of interest is estimated using maximum entropy regularization. The distribution resides in a convex hull of allowable candidate distributions which satisfy concentration inequalities that stem from the sampling […]

Ver mais

Supervised machine learning frameworks rely on extensive labeled datasets for robust performance on real-world tasks. However, there is a lack of large annotated datasets in audio and music domains, as annotating such recordings is resource-intensive, laborious, and often require expert domain knowledge. In this work, we explore the use of label propagation (LP), a graph-based semi-supervised learning technique, for automatically labeling the unlabeled set in an unsupervised manner. By constructing a similarity graph over audio embeddings, we propagate […]

Ver mais

I built Screen Vision, an open source website that guides you through any task by screen sharing with AI. Privacy Focused: Your screen data is never stored or used to train models. Local LLM Support: If you don’t trust cloud APIs, the app has a “Local Mode” that connects to local AI models running on your own machine. Your data never leaves your computer. Web-Native: No desktop app or extension required. Works directly on your browser. How it […]

Ver mais