arXiv preprints from January 1, 2026 through July 20, 2026 — 18:29:57 EST
We propose a novel MLaaS Dataset Generator (MDG) framework that creates configurable and reproducible datasets for evaluating Machine Learning as a Service (MLaaS) selection and composition. MDG simulates realistic MLaaS behaviour by training and evaluating diverse model families across multiple real-world datasets and data...
Vision-language pre-training (VLP) models are vulnerable to adversarial examples, particularly in black-box scenarios. Existing multimodal attacks often suffer from limited perturbation diversity and unstable multi-stage pipelines. To address these challenges, we propose 2S-GDA, a two-stage globally-diverse attack framework. The...
Deep learning has achieved remarkable success in image recognition, yet their inherent opacity poses challenges for deployment in critical domains. Concept-based interpretations aim to address this by explaining model reasoning through human-understandable concepts. However, existing post-hoc methods and ante-hoc concept bottleneck...
Batch codes are of potential use for load balancing and private information retrieval in distributed data storage systems. Recently, a special case of batch codes, termed functional batch codes, was proposed in the literature. In functional batch codes, users can query linear combinations of the information symbols, and not only the...
Sequential recommendation (SR) systems excel at capturing users' dynamic preferences by leveraging their interaction histories. Most existing SR systems assign a single embedding vector to each item to represent its features, adopting various models to combine these embeddings into a sequence representation that captures user intent....
Biometric payment, i.e., biometric authentication implemented in digital payment systems, can reduce memory demands and streamline payment for older adults. However, older adults' perceptions and practices regarding biometric payment remain underexplored. We conducted semi-structured interviews with 22 Chinese older adults, including...
We prove a relative GAGA theorem for perfect and pseudo-coherent complexes in non-archimedean analytic geometry, allowing bases given by Fredholm analytic rings, including those associated from affinoid perfectoid spaces. This answers a question raised in \cite{heuer2024padicnonabelianhodgetheory}. As an application, we show that for...
Edge deployment of low-batch large language models (LLMs) faces critical memory bandwidth bottlenecks when executing memory-intensive general matrix-vector multiplications (GEMV) operations. While digital processing-in-memory (PIM) architectures promise to accelerate GEMV operations, existing PIM-equipped edge devices still suffer...
Foundation models such as Segment Anything Model 2 (SAM 2) exhibit strong generalization on natural images and videos but perform poorly on medical data due to differences in appearance statistics, imaging physics, and three-dimensional structure. To address this gap, we introduce SynthFM-3D, an analytical framework that...
An interesting phenomenon arises: Empirical Risk Minimization (ERM) sometimes outperforms methods specifically designed for out-of-distribution tasks. This motivates an investigation into the reasons behind such behavior beyond algorithmic design. In this study, we find that one such reason lies in the distribution shift across...
We investigate the thermodynamics of a spatially flat Friedmann-Robertson-Walker (FRW) universe within the framework of Generalized Proca (GP) theory, a comprehensive vector-tensor theory. By adopting two distinct dark energy models in GP, we derive the corresponding modified Friedmann equations, the thermodynamic first law for the...
Reward-guided search methods have demonstrated strong potential in enhancing tool-using agents by effectively guiding sampling and exploration over complex action spaces. As a core design, those search methods utilize process reward models (PRMs) to provide step-level rewards, enabling more fine-grained monitoring. However, there is a...
Using the data sample of $2.7\times10^9$ $ψ(3686)$ events collected with the BESIII detector at the BEPCII collider, we present an observation of the $Ξ(1530)^0$ polarization in the decay $ψ(3686)\toΞ(1530)^0\barΞ(1530)^0$ with a significance larger than $20σ$ compared with all other tested hypotheses. The helicity amplitudes for the...
We investigate quantum correlations in a hybrid qubit-qutrit system subject to both axial and planar single-ion anisotropies, dipolar spin-spin interactions, and Dzyaloshinskii-Moriya (DM) coupling. Using Negativity, Measurement-Induced Non-locality (MIN), Uncertainty-Induced Nonlocality (UIN), and Bell nonlocality (as quantified by...
Autoregressive (AR) models excel at generating temporally coherent audio by producing tokens sequentially, yet they often falter in faithfully following complex textual prompts, especially those describing complex sound events. We uncover a surprising capability in AR audio generators: their early prefix tokens implicitly encode...
Scalable and maintainable map representations are fundamental to enabling large-scale visual navigation and facilitating the deployment of robots in real-world environments. While collaborative localization across multi-session mapping enhances efficiency, traditional structure-based methods struggle with high maintenance costs and...
Indigenous languages face significant cultural oppression from official state languages, particularly in the Global South. We investigate the Bangladeshi Chakma language revitalization movement, a community grappling with language liquidity and amalgamation into the dominant Bengali language. Our six-month-long qualitative study...
Learning representative embeddings for different types of speaking styles, such as emotion, age, and gender, is critical for both recognition tasks (e.g., cognitive computing and human-computer interaction) and generative tasks (e.g., style-controllable speech generation). In this work, we introduce ParaMETA, a unified and flexible...
Probabilistic time series forecasting is crucial for quantifying future uncertainty, with significant applications in fields such as energy and finance. However, existing methods often rely on computationally expensive sampling or restrictive parametric assumptions to characterize future distributions, which limits predictive...
We investigate the excitation of quasi-normal modes (QNMs) in gravitational lensing by a Schwarzschild black hole using a scalar field model. By employing a time-domain mode-sum method, we analyze the complex interplay between an incident burst signal and the black hole spacetime. We find that the incident waves can non-resonantly...
We study open charm hadrons production in pp and Au+Au collisions at $\sqrt{s_{\mathrm{NN}}} = 200$~GeV using an improved a multi-phase transport (AMPT) model. Specifically, we show the transverse-momentum spectra and nuclear modification factors $R_{\mathrm{AA}}$ of $D^{0}$ mesons and $Λ_{c}^{+}$ baryons, as well as the...
The increasing prevalence of Large Language Models (LLMs) demands effective safeguards for their operation, particularly concerning their tendency to generate out-of-context responses. A key challenge is accurately detecting when LLMs stray from expected conversational norms, manifesting as topic shifts, factual inaccuracies, or...
We introduce a novel representation for efficient classical rendering of photorealistic 3D face avatars. Leveraging recent advances in radiance fields anchored to parametric face models, our approach achieves controllable volumetric rendering of complex facial features, including hair, skin, and eyes. At enrollment time, we learn a...
The rapid evolution of the automobile sector, driven by advancements in connected and autonomous vehicles (CAVs), has transformed how vehicles communicate, operate, and interact with their surroundings. Technologies such as Vehicle-to-Everything (V2X) communication enable autonomous cars to generate and exchange substantial amounts of...
Diffusion Transformers (DiTs) achieve state-of-the-art performance in text-to-image synthesis but remain computationally expensive due to the iterative nature of denoising and the quadratic cost of global attention. In this work, we observe that denoising dynamics are spatially non-uniform-background regions converge rapidly while...