1273993 results (page 108 of 50960)
-
StateScribe: Towards Accessible Change Awareness Across Real-World Revisits
Real-world environments evolve continuously, yet blind and low-vision (BLV) individuals often have limited access to understanding how they change over time. Unexpected or relocated objects, layout modifications, and content updates (e.g., price changes) can introduce safety risks and cognitive burden. While existing visual assistive technologies can describe immediate surroundings, they operate a…
-
Enforcing TSP-Optimality in Fair Vehicle Routing by Cutting Planes
We study the fair capacitated vehicle routing problem, in which a fleet of vehicles must serve a set of customers such that the difference between the longest and shortest route, the range, is minimized. A key challenge is that the range objective is non-monotonic: it can be reduced by artificially lengthening routes, leading to solutions that violate TSP-optimality of individual routes. Existing …
-
SFT-then-RL Outperforms Mixed-Policy Methods for LLM Reasoning
Recent mixed-policy optimization methods for LLM reasoning that interleave or blend supervised and reinforcement learning signals report improvements over the standard SFT-then-RL pipeline. We show that numerous recently published research papers rely on a faulty baseline caused by two distinct bugs: a CPU-offloaded optimizer bug in DeepSpeed that silently drops intermediate micro-batches during g…
-
Fixed-Reservoir vs Variational Quantum Architectures for Chaotic Dynamics: Benchmarking QRC and QPINN on the Lorenz System
Deploying quantum machine learning on NISQ devices requires architectures where training overhead does not negate computational advantages. We systematically compare two quantum approaches for chaotic time-series prediction on the Lorenz system: a variational Quantum Physics-Informed Neural Network (QPINN) and a Quantum Reservoir Computing (QRC) framework utilizing a fixed transverse-field Ising H…
-
On gravitating dyonic configurations in nonlinear electrodynamics
We consider static, spherically symmetric configurations of nonlinear electromagnetic fields with Lagrangians $L(f)$, where $f = F_{μν} F^{μν}$, in general relativity (GR) and other metric theories of gravity. The corresponding exact solutions are well known in the framework of GR in cases where only an electric charge ($q_e$) or a magnetic charge ($q_m$) are present, but only a few solutions in p…
-
RTCFake: Speech Deepfake Detection in Real-Time Communication
With the rapid advancement of speech generation technologies, the threat posed by speech deepfakes in real-time communication (RTC) scenarios has intensified. However, existing detection studies mainly focus on offline simulations and struggle to cope with the complex distortions introduced during RTC transmission, including unknown speech enhancement processes (e.g., noise suppression) and codec …
-
Transformer as an Euler Discretization of Score-based Variational Flow
Despite the Transformer's dominance across machine learning, its architecture remains largely heuristic and lacks a unified theoretical foundation. We introduce Score-based Variational Flow (SVFlow), a continuous-time dynamical system for representation learning in which the state evolves according to a variational posterior-weighted average of conditional log-likelihood scores, and provide a prin…
-
Prism-Reranker: Beyond Relevance Scoring -- Jointly Producing Contributions and Evidence for Agentic Retrieval
Modern retrieval pipelines increasingly serve downstream consumers like retrieval-augmented generation (RAG) and autonomous agents that need more than a scalar relevance score. A reranker that only tells the caller "how relevant" forces the agent to dump entire documents into the language-model context, wasting tokens on tangential passages and boilerplate. We introduce Prism-Reranker, a family of…
-
Multimodal QUD: Inquisitive Questions from Scientific Figures
Asking inquisitive questions while reading, and looking for their answers, is an important part in human discourse comprehension, curiosity, and creative ideation, and prior work has investigated this in text-only scenarios. However, in scientific or research papers, many of the critical takeaways are conveyed through both figures and the text that analyzes them. While scientific visualizations ha…
-
Impact of Age Specialized Models for Hypoglycemia Classification
Disease progression varies with age and is influenced by underlying genetic, biochemical, and hormonal etiologies, suggesting the need for tailored monitoring, care, and medication beyond standard clinical guidelines. Specifically, in autoimmune diseases like type 1 diabetes (T1D), where patients depend on exogenous insulin to compensate for insulin deficiency, medication dosing and the physiologi…
-
Expert Evaluation of LLM's Open-Ended Legal Reasoning on the Japanese Bar Exam Writing Task
Large language models (LLMs) have shown strong performance on legal benchmarks, including multiple-choice components of bar exams. However, their capacity for generating open-ended legal reasoning in realistic scenarios remains insufficiently explored. Notably, to our best knowledge, there are no prior studies or datasets addressing this issue in the Japanese context. This study presents the fir…
-
DynProto: Dynamic Prototype Evolution for Out-of-Distribution Detection
Recent studies show that using potential out-of-distribution (OOD) labels from large corpora as auxiliary information can improve OOD detection in vision-language models (VLMs). However, these methods often fail when real-world OOD samples fall outside the predefined OOD label set. To address this limitation, we propose DynProto, a novel approach that learns OOD prototypes dynamically during testi…
-
ESIA: An Energy-Based Spatiotemporal Interaction-Aware Framework for Pedestrian Intention Prediction
Recent advances in autonomous driving have motivated research on pedestrian intention prediction, which aims to infer future crossing decisions and actions by modeling temporal dynamics, social interactions, and environmental context. However, existing studies remain constrained by oversimplified multi-agent interaction patterns, opaque reasoning logic, and a lack of global consistency in behavior…
-
A Unified Explanation of Gamma-Ray and Neutrino Spectra from Astrophysical Sources Based on the Gluon Condensation Model
The advent of multi-messenger astronomy has provided abundant information for understanding the acceleration and particle-production mechanisms of cosmic rays. In this work, we present a unified study of cosmic gamma-ray and neutrino spectra within the Gluon Condensation (GC) model. Derived from Quantum Chromodynamics (QCD), the GC model predicts that, in high-energy hadronic processes, gluons may…
-
Uncertainty-Aware Fuzzy Centrality Measures for Influential Node Identification: A Structural Modeling Approach Toward E-Commerce Applications
In recent years, e-commerce platforms have become one of the most prominent examples of large-scale interaction networks, where understanding influence dynamics among users, products, and digital entities is essential for applications such as online marketing, recommendation systems, and customer behavior analysis. A key challenge in these platforms is that interactions are often uncertain, noisy,…
-
Zoom In, Reason Out: Efficient Far-field Anomaly Detection in Expressway Surveillance Videos via Focused VLM Reasoning Guided by Bayesian Inference
Expressway video anomaly detection is essential for safety management. However, identifying anomalies across diverse scenes remains challenging, particularly for far-field targets exhibiting subtle abnormal vehicle motions. While Vision-Language Models (VLMs) demonstrate strong semantic reasoning capabilities, processing global frames causes attention dilution for these far-field objects and incur…
-
An Individual-Delay-Reflected Generalized Consensus Analysis for Multi-Agent Systems with Heterogeneous Time-Varying Delays
In multi-agent systems, heterogeneous time delays exist for all agents because of the difference in communication environments. Therefore, the consensus analysis of a system considering a homogeneous time-varying delay among all agents results in conservatism. In this study, an individual-delay-reflected generalized consensus is proposed for multi-agent systems with heterogeneous time-varying dela…
-
Photon regions, shadow observables and constraints from M87* of a Kerr-Newman-like black hole in Bumblebee gravity surrounded by plasma
In this paper, we investigate the photon regions, shadow, and observational constraints of a Kerr-Newman-like black hole in Bumblebee gravity within a plasma medium. By employing a specific non-homogeneous power-law plasma model to ensure the separability of the Hamilton-Jacobi equation, we derive the null geodesic equations, analyze the photon regions, and construct the black hole shadow. Further…
-
Quasi-Equivariant Metanetworks
Metanetworks are neural architectures designed to operate directly on pretrained weights to perform downstream tasks. However, the parameter space serves only as a proxy for the underlying function class, and the parameter-function mapping is inherently non-injective: distinct parameter configurations may yield identical input-output behaviors. As a result, metanetworks that rely solely on raw par…
-
AIPsy-Affect: A Keyword-Free Clinical Stimulus Battery for Mechanistic Interpretability of Emotion in Language Models
Mechanistic interpretability research on emotion in large language models -- linear probing, activation patching, sparse autoencoder (SAE) feature analysis, causal ablation, steering vector extraction -- depends on stimuli that contain the words for the emotions they test. When a probe fires on "I am furious", it is unclear whether the model has detected anger or detected the word "furious". The t…
-
Caries DETR: Tooth Structure-aware Prior and Lesion-aware Dynamic Loss Refinement for DETR Based Caries Detection
As dental caries appear as subtle, low-contrast lesions in intraoral imaging, existing deep learning models face significant challenges in the early detection of caries. While recent Transformer-based detectors have shown promising results in natural images, they often fail to capture the domain-specific anatomical priors crucial for dental caries detection. In this paper, we propose Caries-DETR, …
-
HeadRouter: Dynamic Head-Weight Routing for Task-Adaptive Audio Token Pruning in Large Audio Language Models
Recent large audio language models (LALMs) demonstrate remarkable capabilities in processing extended multi-modal sequences, yet incur high inference costs. Token compression is an effective method that directly reduces redundant tokens in the sequence. Existing compression methods usually assume that all attention heads in LALMs contribute equally to various audio tasks and calculate token import…
-
Information-Theoretic Measures in AI: A Practical Decision Guide
Information-theoretic (IT) measures are ubiquitous in artificial intelligence: entropy drives decision-tree splits and uncertainty quantification, cross-entropy is the default classification loss, mutual information underpins representation learning and feature selection, and transfer entropy reveals directed influence in dynamical systems. A second, less consolidated family of measures, integra…
-
Temporal connection probabilities in real networks
Principled prediction of when and where links form in complex networks is a fundamental problem. We derive a closed-form non-Markovian expression for next-step connection probabilities that unifies latent hyperbolic geometry with long-range memory of past interactions. This expression yields interpretable forecasts governed by a small set of parameters. Applied to large-scale real networks, we fin…
-
OptProver: Bridging Olympiad and Optimization through Continual Training in Formal Theorem Proving
Recent advances in formal theorem proving have focused on Olympiad-level mathematics, leaving undergraduate domains largely unexplored. Optimization, fundamental to machine learning, operations research, and scientific computing, remains underserved by existing provers. Its reliance on domain-specific formalisms (convexity, optimality conditions, and algorithmic analysis) creates significant distr…