Alignment, interpretability, red-teaming, bias and privacy: the research on what these systems do when they misbehave.
arXiv:2607. 21185v1 Announce Type: new Abstract: Neurosymbolic (NeSy) systems integrate neural networks with logical reasoning to achieve both generalization and interpretability, but recent work has shown they are susceptible to shortcut reasoning behaviors.
arXiv:2607. 20939v1 Announce Type: cross Abstract: Safe steerable catheter control is fundamentally a problem of interaction dynamics: the tip must follow a planned motion, remain compliant against moving tissue, reject friction and hysteresis, and respect a clinically meaningful never-exceed contact-force bound.
arXiv:2605. 27390v3 Announce Type: replace-cross Abstract: Speculative decoding accelerates Large Language Model inference through draft-then-verify generation, yet lightweight draft models face coupled efficiency and quality limitations: large-vocabulary output projection is costly, while limited draft capacity and static parameters reduce acceptance under specialized or shifting inputs.
arXiv:2512. 12086v2 Announce Type: replace Abstract: Data obfuscation is a promising technique for mitigating attribute inference attacks by semi-trusted parties with access to time-series data emitted by sensors.
arXiv:2607. 21496v1 Announce Type: cross Abstract: Cognitive impairment (CI) is a growing public health concern.
arXiv:2607. 20988v1 Announce Type: cross Abstract: Vision-Language-Action (VLA) models augmented with world modeling represent a promising paradigm for end-to-end autonomous driving.
arXiv:2607. 20558v1 Announce Type: cross Abstract: AI Assistants are increasingly deployed in high-stakes settings, such as healthcare or government services.
arXiv:2607. 20730v1 Announce Type: cross Abstract: Large language models increasingly use search tools to retrieve up-to-date information, introducing a new attack surface in which retrieved documents can be manipulated.
arXiv:2607. 21343v1 Announce Type: cross Abstract: Integrating heterogeneous biomedical data, including clinical metadata, histopathology images, and molecular profiles, is crucial for comprehensive disease understanding.
arXiv:2602. 13904v2 Announce Type: replace Abstract: Chain-of-thought (CoT) reasoning is fundamental to modern LLM architectures and represents a critical intervention point for AI safety.
arXiv:2607. 20742v1 Announce Type: new Abstract: Multimodal learning is a robust approach to improve predictive performance in applications such as medical prognosis.
arXiv:2607. 20674v1 Announce Type: new Abstract: We consider the problem of learning high-dimensional semi-global feedback controllers under hard safety constraints enforced by control barrier functions (CBFs).
arXiv:2505. 20955v5 Announce Type: replace-cross Abstract: Diffusion models have achieved tremendous success in image generation, but they also raise significant concerns regarding privacy and copyright issues.
arXiv:2607. 21558v1 Announce Type: new Abstract: Building socially calibrated large language models, which can learn from others without simply yielding to them, requires more than reducing sycophancy as a one-dimensional failure mode.
arXiv:2607. 20982v1 Announce Type: new Abstract: As large language model agents increasingly operate autonomously with access to tools and external environments, ensuring their safe and reliable behavior becomes critical.
arXiv:2607. 20436v1 Announce Type: cross Abstract: Safety evaluations often assume that behavior observed during testing reflects behavior in ordinary use, but fine-tuning can break this assumption.
arXiv:2607. 20705v1 Announce Type: cross Abstract: Interactive image segmentation is critical for efficient image annotation; however, existing methods often require many corrective clicks or rely on passive refinement schemes that converge slowly.
arXiv:2607. 21090v1 Announce Type: cross Abstract: We propose a Reinforcement Learning (RL) method to directly optimize the faithfulness of self-explanations - the extent to which a model's generated reasoning accurately reflects its internal decision-making process.
arXiv:2607. 21111v1 Announce Type: cross Abstract: Offline Reinforcement Learning (RL) agents are trained on fixed behavioral trajectories, which makes trajectory-level deletion important when selected data must be removed after training.
arXiv:2607. 21371v1 Announce Type: cross Abstract: Open-vocabulary semantic segmentation (OVSS) leverages textual semantics to segment objects beyond predefined categories.