Alignment, interpretability, red-teaming, bias and privacy: the research on what these systems do when they misbehave.
arXiv:2607. 25117v1 Announce Type: cross Abstract: Deep learning models for ECG image classification may achieve high accuracy by exploiting non-physiological visual cues instead of ECG waveform morphology.
arXiv:2607. 24782v1 Announce Type: new Abstract: LLM behavior may be conditioned by human identity in several ways: they may be asked to adapt to users, role-play populations, or forecast how people would answer value-laden questions.
arXiv:2607. 25322v1 Announce Type: new Abstract: Multimodal drug discovery enables drug representation learning beyond chemical structure by incorporating cellular responses such as gene expression and cell morphology.
arXiv:2607. 24817v1 Announce Type: cross Abstract: Digital mental health interventions (DMHIs) offer scalable support, but ensuring they accurately detect users' intent during volatile situations can be challenging.
arXiv:2607. 18292v3 Announce Type: replace-cross Abstract: Bigger language models are less reliable.
arXiv:2607. 25912v1 Announce Type: cross Abstract: Vision-Language-Action (VLA) models have shown strong potential for general robot manipulation, but most existing models rely on 2D visual-language backbones and lack fine-grained 3D understanding of target objects, especially under occlusion, pose variation, scale changes, and precise spatial interaction.
arXiv:2607. 25612v1 Announce Type: new Abstract: Perception tasks for autonomous vehicles need to work satisfactorily in adverse weather conditions.
arXiv:2607. 26034v1 Announce Type: new Abstract: Technological races create tension between speed and safety: actors may gain by moving faster than competitors, even when risky development is harmful.
arXiv:2607. 25074v1 Announce Type: cross Abstract: Synthetic control (SC) matches a treated unit's pre-treatment trajectory to a weighted combination of donor units.
arXiv:2607. 25333v1 Announce Type: cross Abstract: Specula is a push-button agentic system that generates high-quality formal specifications for large, complex system code and uses the specifications for highly effective model checking and bug finding.
Wi-Fi-based human activity recognition has advanced substantially, but most existing methods assume a closed set of activities and require labeled Wi-Fi samples for every target class, limiting their ability to recognize unseen activities. We present Zero-Fi, a contrastive signal-language alignment framework for zero-shot Wi-Fi-based human activity recognition.
Large language models (LLMs) are increasingly embedded in everyday life and widely used for information seeking, raising concerns about their potential to perpetuate social biases and reinforce stereotypes. In this study, we investigate gender bias in LLMs through the lens of their associations with musical instruments.
Line-haul trucking costs are dominated by three comparably sized components: energy, driver labor, and equipment. Most efficiency technologies address only one component at a time.
Brain tumors such as glioma, meningioma, and pituitary adenoma alter the mechanical behavior of soft brain tissue, yet common diagnostic methods rely on static imaging that cannot capture tumor growth, tissue displacement, or changes in stiffness over time. Deep learning models for this task typically require pooling patient data at one site, which conflicts with privacy rules such as GDPR and HIPAA and limits generalization across institutions, a challenge that is pronounced in neuro oncology given patient diversity.
Content-moderation classifiers are usually evaluated in isolation, but deployment requires choosing where to intervene and what follows a flag. We evaluate these choices using two end-to-end customer-outcome metrics rather than component accuracy: Usefulness, the fraction of turns with a shown, non-harmful, relevant response, and Harmful Exposure, the fraction with a shown harmful response.
Alignment training, model organisms, and toy models are usually treated as separate research areas. But projects in all three frequently use supervised fine-tuning (SFT) to pursue the same underlying goals.
We present VetClaw, an edge-cloud multimodal agentic system for early veterinary disease screening. VetClaw uses a camera module as an edge sensing device and sends captured images, together with optional symptom descriptions, to a server-hosted vision-language model for zero-shot disease classification.
Technological races create tension between speed and safety: actors may gain by moving faster than competitors, even when risky development is harmful. This is prominent in debates about artificial intelligence (AI), where competitive pressure is often argued to incentivise riskier, less safety-conscious development.
We propose Rashomon Alignment (RA), a new measure to assess functional similarity between two models. Existing functional similarity measures are distributional, quantifying differences between outputs of models applied to real-world data.
Eliciting explainable AI (XAI) requirements from stroke survivors presents a methodological challenge with direct implications for the design of trustworthy brain-computer interfaces for rehabilitation. How can patients and caregivers articulate preferences about algorithmic transparency when they lack conceptual frameworks for explainability, and when standard elicitation approaches are structurally inadequate for users with acquired communication disorders?