Alignment, interpretability, red-teaming, bias and privacy: the research on what these systems do when they misbehave.
arXiv:2602. 01051v5 Announce Type: replace Abstract: Repertoire-level analysis of T cell receptors offers a biologically grounded signal for disease detection and immune monitoring, yet practical deployment is impeded by label sparsity, cohort heterogeneity, and the computational burden of adapting large encoders to new tasks.
arXiv:2607. 19356v1 Announce Type: new Abstract: Tool-using LLM agents increasingly execute high-impact actions, making runtime safety monitoring essential.
arXiv:2607. 19824v1 Announce Type: new Abstract: LLM preference alignment aims to optimize models toward human preferences across diverse user instructions.
arXiv:2607. 19956v1 Announce Type: cross Abstract: Knowledge distillation (KD) is a standard approach for compressing sequence-to-sequence models, but its per-sample effects are rarely examined.
arXiv:2607. 19361v1 Announce Type: cross Abstract: Most safety guardrails for large language models (LLMs) evaluate each prompt-response pair in isolation, which misses failures that arise only over a dialogue as benign turns compose into harm.
arXiv:2607. 19942v1 Announce Type: cross Abstract: This work introduces G-MAD, an open-source framework that uses Arma3 to generate synchronized multi-view RGB-T data for aerial object detection.
arXiv:2607. 19433v1 Announce Type: new Abstract: The transition from stateless generative models in artificial intelligence to stateful, autonomous agents represents an architectural evolution that, while providing the capabilities of long-term planning and the automation of enterprise workflows, also represents the introduction of a new form of security threat, the Chronos Vulnerability.
arXiv:2605. 30116v2 Announce Type: replace-cross Abstract: Distribution Matching Distillation (DMD) is a widely used paradigm for accelerating inference in few-step video diffusion models.
arXiv:2503. 22223v2 Announce Type: replace Abstract: The semi-airborne transient electromagnetic method (SATEM) is capable of conducting rapid surveys over large-scale and hard-to-reach areas.
arXiv:2607. 20379v1 Announce Type: new Abstract: Natural-language autoencoders score explanations of hidden activations by reconstruction: an explanation is deemed faithful if the activation can be regenerated from it.
arXiv:2602. 17071v3 Announce Type: replace-cross Abstract: Graph neural networks frequently encounter significant performance degradation when confronted with structural noise or non-homophilous topologies.
arXiv:2607. 20141v1 Announce Type: cross Abstract: The rapid growth of chiplet-based artificial intelligence systems-on-chip (SoCs) has exposed a fundamental gap in semiconductor test methodology.
arXiv:2607. 19366v1 Announce Type: new Abstract: Safety as Polytope (SaP) learns linear half-space constraints in LLM hidden space but requires per-category tuning of the constraint count K.
arXiv:2607. 20216v1 Announce Type: cross Abstract: Malware analysis demands rapid interpretation of complex detonation reports spanning filesystem, network, and process behaviours.
arXiv:2607. 19902v1 Announce Type: new Abstract: Most existing nonlinear adaptive filtering algorithms only account for output noise, neglecting the fact that input noise is also prevalent in practice.
arXiv:2607. 19375v1 Announce Type: cross Abstract: Language models perform economically valuable work, yet they are not currently assessed for how well they perform every economically valuable task.
arXiv:2602. 18047v4 Announce Type: replace-cross Abstract: City-scale person re-identification across distributed cameras must handle severe appearance changes from viewpoint, occlusion, and domain shift while complying with data protection rules that prevent sharing raw imagery.
arXiv:2607. 19794v1 Announce Type: cross Abstract: Production LLM-based financial sentiment analysis faces a structural cost trap: most queries are trivially classifiable, yet expensive cloud reasoners process them all, and the bill scales linearly with user count.
arXiv:2607. 20345v1 Announce Type: cross Abstract: Closing the gap between benchmark performance and reliable real-world operation remains a central challenge for Vision-Language-Action (VLA) humanoid robots, which must handle execution errors, distribution shifts, and environmental variability.
arXiv:2607. 20277v1 Announce Type: new Abstract: Machine learning models achieve high predictive accuracy in regression tasks, but their deployment in safety-critical and regulated domains requires interpretability.