1614479 results (page 9 of 64580)
-
Statistical Properties of Training & Generalization
Deep learning has managed to evade numerous intuitions from classical statistics to achieve unprecedented performance on a number of real-world tasks. In this article, we investigate the key features and surprises of deep learning from a physics-informed perspective, taking care to point out and justify where possible the many choices inherent in constructing a deep learning model. In particular, …
-
Spectral and size conditions for spanning k-trees in tough graphs
The toughness of a graph is a crucial parameter for characterizing its structural properties. The toughness of a non-complete graph $G$ is defined as $τ(G) = \min \{ \dfrac{|S|}{c(G - S)} : S \subseteq V(G), c(G-S) > 1 \}$, where $c(G)$ denotes the number of components of $G$. We define $τ(K_n) = \infty$. A graph $G$ is said to be $τ$-tough if $|S| \ge τ\cdot c(G-S)$ for every vertex cut $S$ of $G…
-
Token-Operations-Oriented Inference Optimization Techniques for Large Models
Large model inference optimization serves as a key foundation for supporting the scalable, low-cost, and highly stable operation of large model services. Centered on token-oriented inference optimization technology, this paper proposes for the first time a four-layer technical architecture consisting of Multi-model Fusion, Model Optimization, Compute-Model Fusion, and Compute-Network-Model Fusion.…
-
Shifting-based Optimizable Linear Relaxations for General Activation Functions
The use of neural networks (NNs) is rapidly increasing, including in safety- and security-critical domains. To provide formal guarantees about NN behavior, many verification methods rely on optimizable linear relaxations of activation functions. However, existing techniques depend on hand-crafted relaxations for each activation function. Extension to state-of-the-art activation functions therefore…
-
Integrating national forest inventory, airborne lidar, and satellite imagery for wall-to-wall mapping of forest structure with computer vision
Remote sensing is increasingly relied upon to deliver actionable science for forest and wildfire risk management across large landscapes. Wall-to-wall, annually updated maps are a persistent need for effective forest management. Many planning systems and data collections combine disparate data sources with different purposes, vintages, and prediction quality, which leads to confounding behavior in…
-
Dimension-free bounds for {R}iesz transforms on the {H}amming cube via a {B}ellman function
We give a Bellman-function proof of the dimension-free estimate \[ \Big\| \vec{R} f \Big\|_{L^p(Ω;\,\ell^2)} \lesssim (p-1) \,\|f\|_{L^p(Ω)}, \qquad 2\le p<\infty, \] for the vector of Riesz transforms associated with the Walsh number operator on the Hamming cube $Ω=\{-1,1\}^n$, as well as for locally compact abelian groups, in particular $Ω=\mathbb{Z}^n$. The argument is based on a Poisson semigr…
-
PsyScore: A Psychometrically-Aware Framework for Trait-Adaptive Essay Scoring and ZPD-Scaffolded Feedback
Effective Automated Essay Scoring (AES) are expected to support both reliable assessment and actionable instructional feedback. However, existing approaches often treat scoring and feedback as separate components: neural scoring models provide limited interpretability, while Large Language Model (LLM)-based feedback is typically insensitive to learners proficiency levels. To address this fragmenta…
-
Co-VLA: Coordination-Aware Structured Action Modeling for Dual-Arm Vision-Language-Action Systems
Vision-language-action (VLA) models show strong capabilities in single and dual-arm robotic manipulation. Prior works show coordinated bimanual behaviors can emerge from end-to-end learning, leveraging large vision-language backbones with continuous action prediction. However, as bimanual tasks become tightly coupled and execution constraints become critical, implicit coordination alone is insuffi…
-
Constitutive birefringence and critical curves in the rotating García--Díaz black hole
We study high-frequency electromagnetic propagation in the rotating García--Díaz solution of Einstein gravity coupled to NLED. In this system, light is not governed only by the null cone of the spacetime metric, because the NLED field also behaves as an optical medium whose constitutive response determines the physical optical cones. Starting from the mixed electromagnetic potentials, we project t…
-
Boundary Embedding Shaping with Adaptive Contrastive Learning for Graph Structural Disentanglement
Graph neural networks (GNNs) excel at aggregating neighbor information for classification, yet their performance is hindered by graph structural entanglement, where spurious correlations from semantically irrelevant neighbors contaminate node embeddings. This challenge is most acute for nodes near class boundaries in the embedding space, where amplified structural noise blurs decision boundaries a…
-
U$^2$Mamba: A Two-level Nested U-structure Mamba for Salient Object Detection
Mamba-based models have emerged as a promising alternative for salient object detection (SOD), offering significant advantages in modeling long sequences. However, existing models often fail to explore contextual information and the depth of the entire architecture. This paper introduces U$^2$Mamba, a powerful and innovative U-structured network for salient object detection. We propose multiscale …
-
Arrival times of an atomic Bose-Einstein condensate
The times of flight of an atomic Bose-Einstein condensate are theoretically investigated in the experimentally unexplored regime corresponding to detection close to the trap of the condensate. In this regime, there is no consensus on how to calculate the distribution of times of arrival onto the detector. For non-interacting particles, distinct theoretical predictions have been made in the past. T…
-
ELVA: Exploring Ranking-Driven Universal Multimodal Retrieval
Leveraging Multimodal Large Language Models (MLLMs) via contrastive learning has become a mainstream paradigm for improving the performance of Universal Multimodal Retrieval (UMR). However, previous works have ignored the grain blindness when adapting the contrastive paradigm into retrieval tasks. Grain blindness refers to the tendency of the model to overlook grain-level information contained in …
-
Proposal of quantum arrival-time measurement with a Bose-Einstein condensate
This work shows how a Bose-Einstein condensate of ultracold atoms could be used to address a long-standing question in quantum theory: how much time does it take for a particle to reach a detector? To this end, we propose a realistic experimental setup, whose key idea is not to measure arrival times directly, but the arrival flux on the detector as a function of its position. This novel approach n…
-
Lagrange: An Open-Vocabulary, Energy-Based Sparse Framework for Generalized End-to-End Driving
Scaling end-to-end autonomous driving to complex, open-world environments requires perceptual models that generalize to anomalous scenarios and planners that produce kinematically valid trajectories. Existing paradigms face a distinct dichotomy between representational efficiency and generalization capacity. Dense models (e.g., occupancy networks), while geometrically robust, incur critical comput…
-
Efficiently Linking Real Scenes with Synthetic Data Generation for AI-based Cognitive Robotics and Computer Vision Applications
AI vision models are a driving factor for the potential use case scenarios of cognitive robotics within in the industry and household applications. A large array of methods from semantic environment analysis towards 6D and grasping pose estimation have been proposed based on the latest AI achievements. However, such advancements require further strong and efficient methods w.r.t. training data and…
-
Extracting the physical content of Liouvillian eigenmodes: Semiclassical quantization
Unlike in closed quantum systems where individual energy eigenstates are understood as physical excitations, open quantum systems have distinct right and left eigenstates of the Liouvillian that decay with time and are difficult to interpret. Here we introduce a physically motivated quasiprobability measure combining the two types of eigenstates that interprets a Liouville eigenmode as a set of co…
-
An explicit and differentiable Wilson-Daubechies-Meyer transform for gravitational-wave data analysis
The Wilson-Daubechies-Meyer (WDM) time-frequency transform has been widely used in gravitational-wave astronomy, yet a self-contained, mathematically explicit reference for practitioners remains lacking. This is especially true for those wishing to adopt the transform in modern Python and JAX inference workflows. We present wdm_transform, an open-source Python package implementing the WDM wavelet-…
-
Transcript-Free Flow-Matching Text-to-Speech via Speech Feature Conditioning
Recent flow-matching text-to-speech (TTS) models, such as F5-TTS, rely on a reference transcript at inference time, obtained from an external ASR system. This dependency makes zero-shot TTS brittle for accented or dysarthric speakers, precisely the scenarios where it is most needed. Moreover, we find that text-based reference conditioning can propagate atypical acoustic patterns from atypical spee…
-
UCLCHEM 4.0: An open source gas-grain astrochemistry simulation framework
Astrochemical modeling is a key tool for the understanding of the formation and destruction of molecules in the dense gas of the interstellar medium, as observed by modern day observational facilities. UCLCHEM is a comprehensive astrochemical modeling framework that can model the interstellar medium ranging from extra-galactic to protoplanetary disks scales. The framework consists of a core routin…
-
Confidence-Aware Automated Assessment of Student-Drawn Scientific Models
Student-generated drawings are widely used in science education to assess learners' conceptual understanding in modeling-based tasks aligned with the Next Generation Science Standards (NGSS). However, scoring such drawings requires expert human judgment to interpret complex visual representations, making large-scale assessment costly to implement and sustain in classroom settings. In this work, we…
-
Vine Codes: Low-Overhead Quantum LDPC Codes on a Planar Square Grid
The surface code is a promising route towards large-scale quantum computing, requiring only nearest-neighbour gates amenable to superconducting hardware. However, surface codes incur large qubit overheads. Novel quantum low-density parity check (qLDPC) codes promise to reduce overheads but require long-range connections that are difficult to achieve on superconducting platforms. Here, we introduce…
-
Anomalous magneto-optical response at $\mathrm{RuO_2 / WSe_2}$ van der Waals interface
Ruthenium dioxide ($\mathrm{RuO_2}$) has been proposed as an altermagnetic candidate, although its magnetic ground state remains controversial. Here, we probe weak interfacial magnetic states at the surface of (001)-oriented $\mathrm{RuO_2}$ films using the magnetic proximity effect (MPE) in a van der Waals heterostructure consisting of monolayer tungsten diselenide ($\mathrm{WSe_2}$) atop $\mathr…
-
Editorial Alignment: A Participatory Approach to Engaging Editorial Expertise in LLM-mediated Knowledge Dissemination
The emergence of LLM-driven information services is reshaping the conditions under which public knowledge institutions operate, threatening to absorb the editorial function these institutions exist to exercise. While LLMs offer powerful new affordances for knowledge dissemination, editorial authority is challenged by pretrained LLMs that arrive already aligned with the values and dissemination str…
-
Tree-independence number of $K_{1,d}$-free graph classes
In this paper, we investigate the tree-independence number of graph classes that do not contain $K_{1,d}$ as an induced subgraph. Dallard et al. conjectured that for any positive integer $d$ and any planar graph $H$, the class of all $K_{1,d}$-free graphs without $H$ as an induced minor has bounded tree-independence number. Our main contribution towards this conjecture is showing that the conjectu…