Alignment, interpretability, red-teaming, bias and privacy: the research on what these systems do when they misbehave.
arXiv:2610.14152v1 Announce Type: cross Abstract: Gate coefficients describe how a fusion layer weights intermediate features, but they do not necessarily reflect the magnitude of branch contribution...
arXiv:2610.14015v1 Announce Type: cross Abstract: Learning-to-rank (LTR) models can align rankings with undesignated signals when those signals appear as features or leak into training labels. We com...
arXiv:2610.14360v1 Announce Type: new Abstract: Large language model (LLM) alignment often assumes that the user interacting with a model is also the primary beneficiary of its behavior. Yet in many...
arXiv:2610.14507v1 Announce Type: new Abstract: Generative modeling offers a promising solution to the scarcity of labeled clinical electroencephalography (EEG) data under strict privacy constraints....
arXiv:2610.15429v1 Announce Type: cross Abstract: How do we tell a world model what information to preserve? We study this question through the lens of spectral representation learning. We introduce...
arXiv:2610.17544v1 Announce Type: cross Abstract: Thought templates, skill libraries, agent memories and caches turn many reasoning steps into one. We call this reasoning contraction. A contracted me...
arXiv:2610.19996v1 Announce Type: new Abstract: Large language models often produce fluent but factually incorrect output. Gray-box detectors identify such hallucinations from the token-probability s...
The paper introduces an exhaustive dataset of univariate canonical skeletons for neural symbolic regression, generated deterministically via a constrained context-free grammar. These skeletons serve as generic structural representations that eliminate redundant expressions and provide uniform operator distribution, thereby avoiding simplicity bias. The authors also present a sampling strategy for clean numerical data and benchmark 150 SR problems across three tiers, demonstrating challenges for current state‑of‑the‑art methods.
arXiv:2610.14988v1 Announce Type: cross Abstract: The average-reward setting for reinforcement learning is challenging because its Bellman operator is known to contract in span only when the underlyi...
arXiv:2610.15029v1 Announce Type: cross Abstract: Automated disease classification from patient-reported symptoms requires balancing the speed of lightweight discriminative models against the context...
arXiv:2609.20827v2 Announce Type: replace Abstract: Effective discharge education is personalized: a clinician adapts the discharge plan to each patient's literacy, recall, and personality. Before la...
arXiv:2610.17424v1 Announce Type: cross Abstract: Respecting a-priori known symmetries of underlying data is a key principle in designing efficient neural architectures. Convolutional neural networks...
arXiv:2610.15514v1 Announce Type: cross Abstract: Structured pruning reduces the inference cost of large language models (LLMs) by permanently removing neurons and weight rows, yielding dense, hardwa...
arXiv:2610.15555v1 Announce Type: cross Abstract: Training-free story visualization without reference images must preserve recurring entities across frames while scaling to long narratives. Existing...
arXiv:2610.19050v1 Announce Type: cross Abstract: Dense cardiac dynamics are essential for assessing cardiac function, yet in practice clinicians often observe only extremely sparse measurements. How...
arXiv:2610.17523v1 Announce Type: cross Abstract: With recent developments in Artificial Intelligence (AI), the adoption of distributed learning paradigms such as Federated Learning (FL) has emerged....
arXiv:2610.17541v1 Announce Type: cross Abstract: Safety verification of a Markov decision process (MDP) asks whether the probabilities of reaching several failure states jointly lie in a convex safe...
arXiv:2610.20461v1 Announce Type: new Abstract: Character Error Rate (CER), the standard metric for OCR and vision-language models (VLMs), charges a typo as much as a wrong name. We introduce semCER,...
arXiv:2610.15207v1 Announce Type: cross Abstract: Large Language Models (LLMs) have been shown to be computationally expensive and vulnerable to jailbreak attacks, in which adversarial prompts bypass...
arXiv:2610.16942v1 Announce Type: cross Abstract: Large audio-language models (LALMs) are fast becoming a general interface to sound, yet how far their broad pretraining carries into specialized doma...