arXiv preprints from January 1, 2026 through September 26, 2026 — 04:33:43 EST
Modeling fine-grained speaking styles remains challenging for language-speech representation pre-training, as existing speech-text models are typically trained with coarse captions or task-specific supervision, and scalable fine-grained style annotations are unavailable. We present FCaps, a large-scale dataset with fine-grained...
Similarity-sensitive entropy measures the uncertainty of a probability law relative to a similarity kernel that encodes the distinguishability between states. We develop a measure-theoretic treatment covering both finite similarity matrices and general probability spaces, and study how the law and similarity kernel transform under...
The rapid proliferation of wireless devices makes robust identity authentication essential. Radio Frequency Fingerprinting (RFF) exploits device-specific, hard-to-forge physical-layer impairments for identification, and is promising for IoT and unmanned systems. In practice, however, new devices continuously join deployed systems...
Timely leak detection in water distribution networks is critical for conserving resources and maintaining operational efficiency. Although Graph Neural Networks (GNNs) excel at capturing spatial-temporal dependencies in sensor data, their black-box nature and the limited work on graph-based explainable models for water networks hinder...
AI shopping agents are being deployed to hundreds of millions of consumers, creating a new intermediary between platforms, sellers, and buyers. We identify a novel market failure: vertical tacit collusion, where platforms controlling rankings and sellers controlling product descriptions independently learn to exploit documented AI...
We study the Choquard equation involving mixed local and nonlocal operators \[-\varepsilon^{2}Δu+\varepsilon^{2s}(-Δ)^{s}u+V(x)u=\varepsilon^{μ-2}\left(\frac{1}{|x|^μ}*F(u)\right)f(u)\quad \text{in }\R^{2},\] where \(\varepsilon>0\), \(s\in(0,1)\), \(0<μ<2\), \(f\) has Trudinger--Moser critical exponential growth, and...
The Hoover index is a widely used measure of inequality with an intuitive interpretation, yet little is known about the finite-sample properties of its empirical estimator. In this paper, we derive a simple expression for the expected value of the Hoover index estimator for general non-negative populations, based on Laplace transform...
We investigate a series of liquid-crystalline phthalocyanines (metal-free and Cu, Zn, Ni, Co complexes) by correlating their vibrational signatures with their electronic performance in organic thin-film transistors (OTFTs). Raman spectroscopy reveals metal-dependent distortions of the phthalocyanine macrocycle, reflected in systematic...
This study examines the relationship between online buzz and local election outcomes in Taiwan, with a focus on Taitung County. As social media becomes a major channel for public discourse, online buzz is increasingly seen as a factor influencing elections. However, its impact on local elections in Taiwan remains underexplored. This...
Fine-Grained Domain Generalization (FGDG) presents greater challenges than conventional domain generalization due to the subtle inter-class differences and relatively pronounced intra-class variations inherent in fine-grained recognition tasks. Under domain shifts, the model becomes overly sensitive to fine-grained cues, leading to...
Solving optimal control problems (OCPs) of autonomous agents operating under spatial and temporal constraints fast and accurately is essential in applications ranging from eco-driving of autonomous vehicles to quadrotor navigation. However, the nonlinear programs approximating the OCPs are inherently nonconvex due to the coupling...
Recent research on medical MLLMs has gradually shifted its focus from image-level understanding to fine-grained, pixel-level comprehension. Although segmentation serves as the foundation for pixel-level understanding, existing approaches face two major challenges. First, they introduce implicit segmentation tokens and require...
The single-neutron transfer reaction $^{19}$O(d,p$γ$)$^{20}$O has been performed at GANIL, populating states up to and above the neutron separation energy. Bound states populated by s-wave and d-wave transfer have been observed with improved experimental angular distributions. Critically, several unbound states between 7.6 MeV and 9.8...
The Retrieval-augmented generation (RAG) system based on Large language model (LLM) has made significant progress. It can effectively reduce factuality hallucinations, but faithfulness hallucinations still exist. Previous methods for detecting faithfulness hallucinations either neglect to capture the models' internal reasoning...
Hallucinations can be produced by conversational AI systems, particularly in multi-turn conversations where context changes and contradictions may eventually surface. By representing the entire conversation as a temporal graph, we present a novel graph-based method for detecting dialogue-level hallucinations. Our framework models each...
Taiwan Cultural Memory Bank 2.0 is an online curation platform that invites the public to become curators, fostering diverse perspectives on Taiwan's society, humanities, natural landscapes, and daily life. Built on a material bank concept, the platform encourages users to co-create and curate their own works using shared resources or...
Let $G$ be a real reductive Lie group and $H$ a reductive subgroup of $G$. Benoist-Kobayashi studied when $L^2(G/H)$ is a tempered representation of $G$. They introduced the functions $ρ$ on Lie algebras and gave a necessary and sufficient condition for the temperedness of $L^2(G/H)$ in terms of an inequality on $ρ$. In a joint work...
Vision Transformers (ViTs) excel in semantic recognition but exhibit systematic failures in spatial reasoning tasks such as mental rotation. While often attributed to data scale, this work argues that the limitation arises from the intrinsic circuit complexity of the architecture. By formalizing spatial understanding as learning a...
Electroencephalography (EEG)-based brain-computer interfaces facilitate direct communication with a computer, enabling promising applications in human-computer interactions. However, their utility is currently limited because EEG decoding often suffers from poor generalization due to distribution shifts across domains (e.g.,...
Recent work by Anthropic on Mechanistic interpretability claims to understand and control Large Language Models by extracting human-interpretable features from their neural activation patterns using sparse autoencoders (SAEs). If successful, this approach offers one of the most promising routes for human oversight in AI safety. We...
Motion blur caused by camera shake produces ghosting artifacts that substantially degrade edge side object detection. Existing approaches either suppress blur as noise and lose discriminative structure, or apply full image restoration that increases latency and limits deployment on resource constrained devices. We propose DFRCP, a...
Interactions among electronic and lattice degrees-of-freedom are foundational to various phases in condensed-matter physics, yet the dynamic interplay between excitonic and phononic quasiparticles represents an equivalent, underexplored frontier. Moiré superlattices provide an ideal platform for realizing these interactions by...
Vision-language-action (VLA) models achieve strong generalization through large-scale pre-training, but real-world deployment requires expert-level task proficiency in addition to broad generality. Existing post-training approaches for VLA models are typically offline, single-robot, or task-specific, limiting effective on-policy...
Large language models (LLMs) demonstrate strong capabilities across a wide range of complex tasks and are increasingly deployed at scale, placing significant demands on inference efficiency. Prior work typically decomposes inference into prefill and decode stages, with the decode stage dominating total latency. To reduce time and...
Reliable confidence is essential for trusting the outputs of LLMs, yet widely deployed post-trained LLMs (PoLLMs) typically compromise this trust with severe overconfidence. In contrast, we observe that their corresponding base LLMs often remain well-calibrated. This naturally motivates us to calibrate PoLLM confidence using the base...