arXiv AI
Jul 29
Real-Time Driver Safety Scoring Through Inverse Crash Probability Modeling
arXiv:2603. 14841v3 Announce Type: replace-cross Abstract: Road crashes remain a leading cause of preventable fatalities.
AI safety and alignment
Alignment, interpretability, red-teaming, bias and privacy: the research on what these systems do when they misbehave.
arXiv AI
Jul 29
Multi-Sensor Alignment for Weather Simulations
arXiv:2607. 25612v1 Announce Type: new Abstract: Perception tasks for autonomous vehicles need to work satisfactorily in adverse weather conditions.
Hugging Face Trending Papers
Jul 29
Zero-Fi: Zero-Shot Wi-Fi-Based Human Activity Recognition via Contrastive Signal-Language Alignment
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.
Hugging Face Trending Papers
Jul 29
Symphony of Bias: Exploring Gender Associations with Musical Instruments in Multimodal LLMs
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.
Hugging Face Trending Papers
Jul 28
Robostreet Flow: A Lightweight, Ultra-Low-Drag Electric Tractor and Four-Truck Hybrid Convoy Architecture for Minimum-Cost Point-to-Point Freight
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.
Hugging Face Trending Papers
Jul 28
Where Physics Meets Privacy: Federated PINNs for Privacy-Preserving Brain Tumor Biomechanical Modeling
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.
Hugging Face Trending Papers
Jul 28
Choosing Where and How to Moderate: End-to-End Trade-offs in Filter Placement and Response Rewriting
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.
Hugging Face Trending Papers
Jul 28
Shared SFT Lessons Across Alignment, Model Organisms, and Toy Models
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.
Hugging Face Trending Papers
Jul 28
VetClaw: An Edge-Cloud Multimodal Agentic System for Veterinary Disease Screening
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.
Hugging Face Trending Papers
Jul 28
Falling Behind Drives Unsafe Development in an Idealised AI Race Experiment
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.
Hugging Face Trending Papers
Jul 28
Rashomon Alignment
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.
Hugging Face Trending Papers
Jul 28
From Dyad to Triad: Eliciting XAI Requirements in Stroke Rehabilitation
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?
Hugging Face Trending Papers
Jul 28
Sense it with your eyes: Sensation Generation and Understanding for Advertisements
Sensory advertising evokes human senses through visual cues, enabling audiences to mentally simulate experiences and increasing persuasive impact. Despite the recent increase in using AI in generating and understanding creative and persuasive content, how advertisements visually evoke sensations remains largely unexplored.
arXiv AI
Jul 28
Keyword Matters: Unveiling the Energy Sensitivity of On-Device LLM Prompting
arXiv:2607. 22568v1 Announce Type: new Abstract: Large Language Models (LLMs) are increasingly deployed on mobile and embedded devices to improve privacy and reduce network latency.
arXiv AI
Jul 28
PANOPTICON: A PII-Based Assemblage of Naturalistic Output Tokens for Investigating Privacy Leakage Within LLM Context Window
arXiv:2607. 22695v1 Announce Type: new Abstract: Large Language Models (LLMs) are capable of generalizing human language for the completion of never-before-seen tasks, leading to widespread deployment.
arXiv AI
Jul 28
CallBench: A Benchmark for Dual-Goal Coordination in Phone Call Assistants
arXiv:2607. 22635v1 Announce Type: new Abstract: Target-oriented dialogue systems have demonstrated strong capabilities in completing user goals through interactive conversations.
arXiv Machine Learning
Jul 28
DynaCalKV: Key-Value Cache Compression via Head Grouping and Adaptive Rank Allocation
arXiv:2607. 24331v1 Announce Type: new Abstract: As the inference phase of Large Language Models (LLMs) requires handling long context windows, the Key-Value (KV) cache initially appears to address this challenge but eventually becomes a significant bottleneck as the context window continues to grow.
arXiv AI
Jul 28
ARdena: Scenario-driven control of real-time LLM agents
arXiv:2607. 22651v1 Announce Type: new Abstract: Large language models (LLMs) have enabled increasingly capable conversational agents, but reliably controlling their behavior in real-time interactive environments remains a significant challenge.
arXiv AI
Jul 28
Outcome-Fair Restless Multi-Armed Bandits for Stochastic Deadline Scheduling
arXiv:2607. 23772v1 Announce Type: cross Abstract: We study a restless multi-armed bandit (RMAB) problem for a stochastic deadline scheduling application.
arXiv Machine Learning
Jul 28
A Multi-stage Constrained Optimization Framework for Data-driven Problems
arXiv:2607. 23480v1 Announce Type: new Abstract: Variational autoencoders (VAEs) transform high-dimensional, often noisy data into a compact latent representation, making downstream optimization more tractable.