Alignment, interpretability, red-teaming, bias and privacy: the research on what these systems do when they misbehave.
arXiv:2607. 22985v1 Announce Type: cross Abstract: Conformalized selection has been widely applied to select high-quality candidates from large datasets with rigorous uncertainty quantification, such as reliable labeling, drug discovery, and the alignment of large language models.
arXiv:2607. 22702v1 Announce Type: cross Abstract: Text-motion representation learning has advanced rapidly, with growing interest in multi person interactions for animation, AR/VR, and embodied AI.
arXiv:2607. 22868v1 Announce Type: new Abstract: Runtime guardrails act before irreversible tool calls, but their guarantees depend on what policy state is representable, what a judge observes, and whether intervention changes future behavior.
arXiv:2607. 24556v1 Announce Type: cross Abstract: Split learning enables collaborative model training by partitioning neural networks across clients and servers.
arXiv:2607. 24391v1 Announce Type: cross Abstract: AI systems already govern.
arXiv:2601. 18350v5 Announce Type: replace-cross Abstract: Large language models fine-tuned via a two-stage pipeline (domain adaptation followed by instruction alignment) can exhibit non-trivial interference after adapter merging, including the re-emergence of explicit reasoning traces under strict decoding.
arXiv:2607. 23388v1 Announce Type: cross Abstract: As constrained learning becomes increasingly common, models are trained under explicit feasibility requirements to enforce fairness, safety, robustness, regulariza- tion, and physics or logic constraints.
arXiv:2607. 24392v1 Announce Type: cross Abstract: Jailbreak defenses are essential for protecting large language models (LLMs), but they can also introduce secondary costs that weaken model utility.
arXiv:2606. 24941v2 Announce Type: replace-cross Abstract: Reviewing recorded interviews for affective cues such as composure and agitation is slow and subjective, and cloud services that could automate the task require sensitive audio to leave the device.
arXiv:2607. 23055v1 Announce Type: new Abstract: Chain-of-thought (CoT) prompting can fail severely on constraint-dense logical reasoning tasks, where unverified errors accumulate silently across steps.
arXiv:2607. 24586v1 Announce Type: cross Abstract: Large Language Models can produce fluent text that is false, unsupported by the available evidence, or inconsistent with information that appears to be internally represented by the model.
arXiv:2607. 23408v1 Announce Type: new Abstract: Expensive black-box optimization is ubiquitous in science and engineering, where function evaluations are costly and the evaluation budget is limited.
arXiv:2607. 24275v1 Announce Type: cross Abstract: Ethical governance of AI-driven systems is often expressed through high-level principles and static documentation, creating a gap between regulatory requirements and system-level verification.
arXiv:2512. 24625v3 Announce Type: replace-cross Abstract: Accurate traffic prediction is essential for Intelligent Transportation Systems, including ride-hailing, urban road planning, and vehicle fleet management.
arXiv:2607. 24077v1 Announce Type: cross Abstract: Optical Character Recognition (OCR) is a key component in the digitization of historical archives.
arXiv:2603. 20248v2 Announce Type: replace-cross Abstract: AI systems are increasingly entrenched in public governance, yet scholarship lacks formal tools to determine when deviations of public trust in algorithmic institutions dissipate and when they grow into collapse.
arXiv:2604. 06550v3 Announce Type: replace-cross Abstract: Agent skills combine natural-language instructions with executable code while inheriting an agent's filesystem, credential, and network access.
arXiv:2607. 23364v1 Announce Type: new Abstract: Group Relative Policy Optimization (GRPO) is the dominant reinforcement learning algorithm for training reasoning capabilities in large language models, notably adopted by DeepSeek-R1.
arXiv:2607. 23617v1 Announce Type: new Abstract: Designing effective reward functions for model-free reinforcement learning under non-holonomic constraints remains a persistent challenge, often resulting in severe local minima such as policy paralysis or over-conservative hazard avoidance.
arXiv:2607. 23753v1 Announce Type: new Abstract: Partial differential equation (PDE) discovery aims to identify from data the governing law of a physical system.