arXiv:2509.20230v3 Announce Type: replace Abstract: Current LLM unlearning methods face a critical security vulnerability that undermines their fundamental purpose: while they appear to successfully remove sensitive or harmful knowledge, this “forgotten” information remains precariously recoverable through relearning attacks. We identify…
arXiv:2509.25238v1 Announce Type: new Abstract: Tool-augmented language agents frequently fail in real-world deployment due to tool malfunctions–timeouts, API exceptions, or inconsistent outputs–triggering cascading reasoning errors and task abandonment. Existing agent training pipelines optimize only for success trajectories, failing to expose…
arXiv:2507.03828v2 Announce Type: replace-cross Abstract: Large language models (LLMs) achieve strong performance across many domains but are difficult to deploy in resource-constrained settings due to their size. Low-rank weight matrix compression is a popular strategy for reducing model size, typically…
arXiv:2507.09828v3 Announce Type: replace Abstract: Bayesian optimization is a powerful tool for optimizing an expensive-to-evaluate black-box function. In particular, the effectiveness of expected improvement (EI) has been demonstrated in a wide range of applications. However, theoretical analyses of EI are…
arXiv:2405.04811v2 Announce Type: replace-cross Abstract: Randomized algorithms have proven to perform well on a large class of numerical linear algebra problems. Their theoretical analysis is critical to provide guarantees on their behaviour, and in this sense, the stochastic analysis of…
arXiv:2408.10502v2 Announce Type: replace Abstract: Despite the widespread occurrence of classification problems and the increasing collection of point process data across many disciplines, study of error probability for point process classification only emerged very recently. Here, we consider classification of…
arXiv:2509.25783v1 Announce Type: new Abstract: Understanding the geometry of the loss landscape near a minimum is key to explaining the implicit bias of gradient-based methods in non-convex optimization problems such as deep neural network training and deep matrix factorization. A…
arXiv:2509.25481v1 Announce Type: new Abstract: We develop new classifiers under group fairness in the attribute-aware setting for binary classification with multiple group fairness constraints (e.g., demographic parity (DP), equalized odds (EO), and predictive parity (PP)). We propose a novel approach,…
arXiv:2509.25630v1 Announce Type: new Abstract: Efficient sampling from complex and high dimensional target distributions turns out to be a fundamental task in diverse disciplines such as scientific computing, statistics and machine learning. In this paper, we revisit the randomized Langevin…
arXiv:2509.25741v1 Announce Type: new Abstract: Test-time training (TTT) enhances model performance by explicitly updating designated parameters prior to each prediction to adapt to the test data. While TTT has demonstrated considerable empirical success, its theoretical underpinnings remain limited, particularly for…
