Alignment, interpretability, red-teaming, bias and privacy: the research on what these systems do when they misbehave.
arXiv:2606. 27944v1 Announce Type: cross Abstract: Phone-use Agents can execute complex tasks end to end across real mobile applications.
arXiv:2601. 22993v4 Announce Type: replace Abstract: We introduce Canary, a risk-averse method designed to optimize Value-at-Risk (VaR) constrained reinforcement learning (RL) problems.
arXiv:2606. 28525v1 Announce Type: cross Abstract: Fine-tuning on harmless data can partially undo behaviors acquired earlier in training.
arXiv:2606. 29347v1 Announce Type: cross Abstract: Adaptive Financial Transformer (AFT) is proposed for stock return prediction under non-stationary financial markets.
arXiv:2606. 29601v1 Announce Type: cross Abstract: Current languages for specifying multiagent protocols either over-constrain protocol enactments or complicate capturing their meanings.
arXiv:2601. 03546v2 Announce Type: replace-cross Abstract: Large language models (LLMs) are increasingly used to simulate decision-making tasks involving personal data sharing, where privacy concerns and prosocial motivations can push choices in opposite directions.
arXiv:2604. 19971v2 Announce Type: replace-cross Abstract: Interactive spatial layouts empower users to synthesize information and organize findings for sensemaking.
arXiv:2604. 04385v5 Announce Type: replace-cross Abstract: We localize the policy routing mechanism in alignment-trained language models.
arXiv:2605. 10764v3 Announce Type: replace-cross Abstract: Recent studies show that gradient-based universal image jailbreaks on vision-language models (VLMs) exhibit little or no cross-model transferability, casting doubt on the feasibility of transferable multimodal jailbreaks.
arXiv:2606. 29925v1 Announce Type: new Abstract: As deep learning models are increasingly deployed in high-stakes applications, providing well-calibrated uncertainty estimates has become as critical as achieving high predictive accuracy.
arXiv:2606. 28354v1 Announce Type: cross Abstract: The classic paradigm of language identification in the limit models learning as a game between an adversary, who reveals strings from an unknown target language, and a learner tasked with identifying that language.
arXiv:2606. 28383v1 Announce Type: cross Abstract: Identifying complex and safety-critical driving scenarios in large unlabelled datasets is an important but expensive problem.
arXiv:2606. 30523v1 Announce Type: new Abstract: Covariance matrices serve as compact descriptors of feature distributions in many machine-learning pipelines, including domain adaptation and Gaussian embeddings.
arXiv:2510. 19465v2 Announce Type: replace-cross Abstract: Obtaining truly representative pore-scale images that match bulk formation properties remains a fundamental challenge in subsurface characterization, as natural spatial heterogeneity causes extracted sub-images to deviate significantly from core-measured values.
arXiv:2410. 05289v4 Announce Type: replace Abstract: Background: Neurosymbolic (NeSy) artificial intelligence describes the combination of logic or rule-based techniques with neural networks.
arXiv:2602. 12418v2 Announce Type: replace-cross Abstract: Jailbreak attacks remain a persistent threat to large language model safety.
arXiv:2606. 28556v1 Announce Type: new Abstract: Recent advances in large language models and vision-language models have enabled reasoning over multimodal data, offering opportunities for clinical applications such as decision support and triaging.
arXiv:2606. 30609v1 Announce Type: cross Abstract: Sparse Autoencoders (SAEs) are widely used to interpret large language models by decomposing activations into sparse, human-understandable features, but scaling to large dictionaries exposes fundamental challenges.
arXiv:2606. 30572v1 Announce Type: cross Abstract: Malware classification remains a challenging problem due to its inherent heterogeneity, the presence of packed binaries, and the diverse distribution of malware families.
arXiv:2606. 30156v1 Announce Type: cross Abstract: Wrist-worn photoplethysmography (PPG) enables continuous monitoring of cardiopulmonary physiology, but reliable heart rate (HR) and respiratory rate (RR) estimation in free-living conditions remains challenging due to non-stationary motion artifacts that spectrally overlap with physiological dynamics.