arXiv:2604.09602v1 Announce Type: new Abstract: Leyva-V’azquez and Smarandache (2025) demonstrated that neutrosophic T/I/F evaluation, where Truth, Indeterminacy, and Falsity are independent dimensions not constrained to sum to 1.0, which reveals “hyper-truth”‘ (T+I+F > 1.0) in 35% of complex epistemic cases evaluated by LLMs. We extend their work in two directions. First, we replicate and extend […]
ACCIDENT: A Benchmark Dataset for Vehicle Accident Detection from Traffic Surveillance Videos
arXiv:2604.09819v1 Announce Type: cross Abstract: We introduce ACCIDENT, a benchmark dataset for traffic accident detection in CCTV footage, designed to evaluate models in supervised (IID and OOD) and zero-shot settings, reflecting both data-rich and data-scarce scenarios. The benchmark consists of a curated set of 2,027 real and 2,211 synthetic clips annotated with the accident time, […]
A mathematical theory of evolution for self-designing AIs
arXiv:2604.05142v2 Announce Type: replace Abstract: As artificial intelligence systems (AIs) become increasingly produced by recursive self-improvement, a form of evolution may emerge, with the traits of AI systems shaped by the success of earlier AIs in designing and propagating their descendants. There is a rich mathematical theory modeling how behavioral traits are shaped by biological […]
Efficient Personalization of Generative User Interfaces
arXiv:2604.09876v1 Announce Type: cross Abstract: Generative user interfaces (UIs) create new opportunities to adapt interfaces to individual users on demand, but personalization remains difficult because desirable UI properties are subjective, hard to articulate, and costly to infer from sparse feedback. We study this problem through a new dataset in which 20 trained designers each provide […]
LLMs for Text-Based Exploration and Navigation Under Partial Observability
arXiv:2604.09604v1 Announce Type: new Abstract: Exploration and goal-directed navigation in unknown layouts are central to inspection, logistics, and search-and-rescue. We ask whether large language models (LLMs) can function as emphtext-only controllers under partial observability — without code execution, tools, or program synthesis. We introduce a reproducible benchmark with oracle localisation in fixed ASCII gridworlds: each […]
Cross-Cultural Value Awareness in Large Vision-Language Models
arXiv:2604.09945v1 Announce Type: cross Abstract: The rapid adoption of large vision-language models (LVLMs) in recent years has been accompanied by growing fairness concerns due to their propensity to reinforce harmful societal stereotypes. While significant attention has been paid to such fairness concerns in the context of social biases, relatively little prior work has examined the […]
Large Language Models Can Help Mitigate Barren Plateaus in Quantum Neural Networks
arXiv:2502.13166v3 Announce Type: replace-cross Abstract: In the era of noisy intermediate-scale quantum (NISQ) computing, Quantum Neural Networks (QNNs) have emerged as a promising approach for various applications, yet their training is often hindered by barren plateaus (BPs), where gradient variance vanishes exponentially as the qubit size increases. Most initialization-based mitigation strategies rely heavily on pre-designed […]
FREE-Switch: Frequency-based Dynamic LoRA Switch for Style Transfer
arXiv:2604.10023v1 Announce Type: cross Abstract: With the growing availability of open-sourced adapters trained on the same diffusion backbone for diverse scenes and objects, combining these pretrained weights enables low-cost customized generation. However, most existing model merging methods are designed for classification or text generation, and when applied to image generation, they suffer from content drift […]
Evaluating Reliability Gaps in Large Language Model Safety via Repeated Prompt Sampling
arXiv:2604.09606v1 Announce Type: new Abstract: Traditional benchmarks for large language models (LLMs), such as HELM and AIR-BENCH, primarily assess safety risk through breadth-oriented evaluation across diverse tasks. However, real-world deployment often exposes a different class of risk: operational failures arising from repeated generations of the same prompt rather than broad task generalization. In high-stakes settings, […]
Degradation-Consistent Paired Training for Robust AI-Generated Image Detection
arXiv:2604.10102v1 Announce Type: cross Abstract: AI-generated image detectors suffer significant performance degradation under real-world image corruptions such as JPEG compression, Gaussian blur, and resolution downsampling. We observe that state-of-the-art methods, including B-Free, treat degradation robustness as a byproduct of data augmentation rather than an explicit training objective. In this work, we propose Degradation-Consistent Paired Training […]
COXNet: Cross-Layer Fusion with Adaptive Alignment and Scale Integration for RGBT Tiny Object Detection
arXiv:2508.09533v2 Announce Type: replace-cross Abstract: Detecting tiny objects in multimodal Red-Green-Blue-Thermal (RGBT) imagery is a critical challenge in computer vision, particularly in surveillance, search and rescue, and autonomous navigation. Drone-based scenarios exacerbate these challenges due to spatial misalignment, low-light conditions, occlusion, and cluttered backgrounds. Current methods struggle to leverage the complementary information between visible and […]
A Temporally Augmented Graph Attention Network for Affordance Classification
arXiv:2604.10149v1 Announce Type: cross Abstract: Graph attention networks (GATs) provide one of the best frameworks for learning node representations in relational data; but, existing variants such as Graph Attention Network (GAT) mainly operate on static graphs and rely on implicit temporal aggregation when applied to sequential data. In this paper, we introduce Electroencephalography-temporal Graph Attention […]