arXiv:2604.08573v1 Announce Type: new Abstract: Learning discriminative representations is a central goal of supervised deep learning. While cross-entropy (CE) remains the dominant objective for classification, it does not explicitly enforce desirable geometric properties in the embedding space, such as intra-class…
arXiv:2604.08574v1 Announce Type: new Abstract: Large Genomic Foundation Models have recently achieved remarkable results and in-vivo translation capabilities. However these models quickly grow to over a few Billion of parameters and are expensive to run when compute is limited. To…
arXiv:2604.08572v1 Announce Type: new Abstract: State-of-the-art post-hoc out-of-distribution detection methods rely on intermediate layer activation editing. However, they exhibit inconsistent performance across datasets and models. We show that this instability is driven by differences in the activation distributions, and identify…
arXiv:2604.08571v1 Announce Type: new Abstract: While Large Language Models (LLMs) achieve high performance on standard mathematical benchmarks, their underlying reasoning processes remain highly overfit to standard textual formatting. We propose a perturbation pipeline consisting of 14 techniques to evaluate robustness…
arXiv:2604.08570v1 Announce Type: new Abstract: Large Language Models (LLMs) are increasingly used for code generation, yet quantum code generation is still evaluated mostly within single frameworks, making it difficult to separate quantum reasoning from framework familiarity. We introduce QuanBench+, a…
arXiv:2510.21588v2 Announce Type: replace-cross Abstract: Biological and artificial learners are inherently exposed to a stream of data and experience throughout their lifetimes and must constantly adapt to, learn from, or selectively ignore the ongoing input. Recent findings reveal that, even…
arXiv:2604.08578v1 Announce Type: new Abstract: High-quality labeled data is critical for training reliable machine learning and deep learning models, yet manual annotation remains costly and error-prone. Programmatic labeling addresses this challenge by using label functions (LFs), i.e., heuristic rules that…
arXiv:2603.11178v3 Announce Type: replace-cross Abstract: Standard LLM distillation treats all training problems equally — wasting compute on problems the student has already mastered or cannot yet solve. We empirically show that this inefficiency has a precise gradient-level signature: the cross-problem…
arXiv:2604.08579v1 Announce Type: new Abstract: We study cross-modal alignment between independently pretrained vision (DINOv2) and language (all-MiniLM-L6-v2) encoders using the functional map framework from computational geometry, which represents correspondence between representation manifolds as a compact linear operator between graph Laplacian…
arXiv:2604.09069v1 Announce Type: cross Abstract: Court Judgment Prediction and Explanation (CJPE) aims to predict a judicial decision and provide a legally grounded explanation for a given case based on the facts, legal issues, arguments, cited statutes, and relevant precedents. For…
