940675 results (page 33 of 37627)
-
CS3: Efficient Online Capability Synergy for Two-Tower Recommendation
To balance effectiveness and efficiency in recommender systems, multi-stage pipelines commonly use lightweight two-tower models for large-scale candidate retrieval. However, the isolated two-tower architecture restricts representation capacity, embedding-space alignment, and cross-feature interactions. Existing solutions such as late interaction and knowledge distillation can mitigate these issues…
-
Comparison of model order reduction techniques with one-shot procedure for topology optimization for thermal applications
Density-based topology optimization has become a powerful method for automatically generating optimized designs in a wide variety of applications. However, it comes with a large computational cost when solving the physical model requires large-scale simulations. Here, we investigate the use of model order reduction (MOR) techniques to accelerate the simulations in the context of thermal design app…
-
Multimodal embodiment-aware navigation transformer
Goal-conditioned navigation models for ground robots trained using supervised learning show promising zero-shot transfer, but their collision-avoidance capability nevertheless degrades under distribution shift, i.e. environmental, robot or sensor configuration changes. We propose ViLiNT a multimodal, attention-based policy for goal navigation, trained on heterogeneous data from multiple platforms …
-
From design of experiments to analysis of variance of multivariate data: a tutorial review on ANOVA simultaneous component analysis
ANOVA Simultaneous Component Analysis (ASCA) is the current state-of-theart chemometric tool for analyzing and interpreting high-dimensional experimental data from a Design of Experiment (DoE). Being a multivariate extension of the ANOVA, ASCA makes a perfect tandem with DoE. This tutorial review recommends best practices for using ASCA, building upon the long-established combination of ANOVA and …
-
DR-MMSearchAgent: Deepening Reasoning in Multimodal Search Agents
Agentic multimodal models have garnered significant attention for their ability to leverage external tools to tackle complex tasks. However, it is observed that such agents often meet premature interaction collapse, caused by two primary reasons: 1) the terminal reward often appending on the last token prevents the advantage from distinguishing trajectories with exploratory behavior; 2) excessivel…
-
Graph-Theoretic Models for the Prediction of Molecular Measurements
Graph-theoretic approaches offer simplicity, interpretability, and low computational cost for molecular property prediction. Among these, the model proposed by Mukwembi and Nyabadza, based on the external activity $D(G)$ and internal activity $ζ(G)$ indices, achieved strong results on a small flavonoid dataset. However, its ability to generalize to larger and chemically diverse datasets has not be…
-
Uplink Signal Detection For Large-Scale MIMO-ISAC Systems
Next-generation wireless communication systems are unifying large-scale multiple-input multiple-output (MIMO) and integrated sensing and communication (ISAC) to enhance sensing and communication performance. In this paper, the signal detection problem for MIMO-ISAC systems is modeled as a mixed-integer least squares (MILS) problem. To solve it efficiently, we propose a projection-based neighborhoo…
-
CulturALL: Benchmarking Multilingual and Multicultural Competence of LLMs on Grounded Tasks
Large language models (LLMs) are now deployed worldwide, inspiring a surge of benchmarks that measure their multilingual and multicultural abilities. However, these benchmarks prioritize generic language understanding or superficial cultural trivia, leaving the evaluation of grounded tasks -- where models must reason within real-world, context-rich scenarios -- largely unaddressed. To fill this ga…
-
Towards a Linguistic Evaluation of Narratives: A Quantitative Stylistic Framework
The evaluation of narrative quality remains a complex challenge, as it involves subjective factors such as plot, character development, and emotional impact. This work proposes a quantitative approach to narrative assessment by focusing on the linguistic dimension as a primary indicator of quality. The paper presents a methodology for the automatic evaluation of narrative based on the extraction o…
-
Feature Perturbation Pool-based Fusion Network for Unified Multi-Class Industrial Defect Detection
Multi-class defect detection constitutes a critical yet challenging task in industrial quality inspection, where existing approaches typically suffer from two fundamental limitations: (i) the necessity of training separate models for each defect category, resulting in substantial computational and memory overhead, and (ii) degraded robustness caused by inter-class feature perturbation when heterog…
-
Unposed-to-3D: Learning Simulation-Ready Vehicles from Real-World Images
Creating realistic and simulation-ready 3D assets is crucial for autonomous driving research and virtual environment construction. However, existing 3D vehicle generation methods are often trained on synthetic data with significant domain gaps from real-world distributions. The generated models often exhibit arbitrary poses and undefined scales, resulting in poor visual consistency when integrated…
-
Rapidly oscillating Ap stars observed with TESS. The LAMOST Ap sample and 49 Cam
The rapidly oscillating chemically peculiar A-type (roAp) stars offer valuable insights into the internal physical processes of all stars, but their study is challenged by their rarity. The large-scale TESS surveys have allowed for the collection of data for a sizeable dataset of roAp stars. Nevertheless, asteroseismic data obtained with TESS and Gaia has not been explored to its full potential. W…
-
ShadowPEFT: Shadow Network for Parameter-Efficient Fine-Tuning
Parameter-efficient fine-tuning (PEFT) reduces the training cost of full-parameter fine-tuning for large language models (LLMs) by training only a small set of task-specific parameters while freezing the pretrained backbone. However, existing approaches, such as Low-Rank Adaptation (LoRA), achieve adaptation by inserting independent low-rank perturbations directly to individual weights, resulting …
-
Environmental Understanding Vision-Language Model for Embodied Agent
Vision-language models (VLMs) have shown strong perception and reasoning abilities for instruction-following embodied agents. However, despite these abilities and their generalization performance, they still face limitations in environmental understanding, often failing on interactions or relying on environment metadata during execution. To address this challenge, we propose a novel framework name…
-
Streamliners for Answer Set Programming
Streamliner constraints reduce the search space of combinatorial problems by ruling out portions of the solution space. We adapt the StreamLLM approach, which uses Large Language Models (LLMs) to generate streamliners for Constraint Programming, to Answer Set Programming (ASP). Given an ASP encoding and a few small training instances, we prompt multiple LLMs to propose candidate constraints. Candi…
-
Robust Path Following Control for Vehicles with Uncertain Steering Resistance Using Model Error Compensation
This paper presents a robust path following control method for vehicles that explicitly considers steering resistance dynamics to improve tracking accuracy. Conventional methods typically treat the steering angle as a direct control input; however, this approach introduces the steering angle as a state variable and incorporates the steering resistance effect into the control model. The steering re…
-
BONSAI: A Mixed-Initiative Workspace for Human-AI Co-Development of Visual Analytics Applications
Developing Visual Analytics (VA) applications requires integrating complex machine learning models with expressive interactive interfaces. Developers face a stark trade-off: building tightly-coupled monoliths plagued by fragile interdependencies, or relying on restrictive, simplistic frameworks. Meanwhile, unconstrained, single-shot AI code generation promises speed but yields unstructured, unaudi…
-
The Ophiuchus DIsc Survey Employing ALMA (ODISEA). Substructures as a function of SED Class and disc mass in 100 systems
Current high-resolution studies of protoplanetary discs are biased toward small samples of the brightest (flux > 50 mJy at 225 GHz) and largest systems. We present a complete flux-limited high-resolution study of about 100 discs from the Ophiuchus Disc Survey Employing ALMA (ODISEA), spanning fluxes of about 4-400 mJy at 225 GHz. We investigate substructures as a function of SED Class and disc mas…
-
Talking to a Know-It-All GPT or a Second-Guesser Claude? How Repair reveals unreliable Multi-Turn Behavior in LLMs
Repair, an important resource for resolving trouble in human-human conversation, remains underexplored in human-LLM interaction. In this study, we investigate how LLMs engage in the interactive process of repair in multi-turn dialogues around solvable and unsolvable math questions. We examine whether models initiate repair themselves and how they respond to user-initiated repair. Our results show …
-
A Simple Communication Scheme for Distributed Fast Multipole Methods
We present a simple hierarchical communication scheme for distributed Fast Multipole Methods (FMMs) based on MPI neighborhood collectives and uniform trees. The method targets the common case of extending an existing high-performance shared-memory uniform-tree FMM implementation to distributed memory with minimal redesign while preserving any shared memory optimizations optimizations. Benchmarks o…
-
UniEP: Unified Expert-Parallel MoE MegaKernel for LLM Training
The exponential growth in Large Language Model (LLM) parameters has transformed model training into an increasingly resource-intensive endeavor. With the stagnation of Moore's Law and the widening disparity between computation throughput and communication bandwidth, expert parallelism (EP) has emerged as a critical strategy for scaling mixture-of-experts (MoE) models. However, despite numerous pro…
-
Industrial Surface Defect Detection via Diffusion Generation and Asymmetric Student-Teacher Network
Industrial surface defect detection often suffers from limited defect samples, severe long-tailed distributions, and difficulties in accurately localizing subtle defects under complex backgrounds. To address these challenges, this paper proposes an unsupervised defect detection method that integrates a Denoising Diffusion Probabilistic Model (DDPM) with an asymmetric teacher-student architecture. …
-
Allo{SR}$^2$: Rectifying One-Step Super-Resolution to Stay Real via Allomorphic Generative Flows
Real-world image super-resolution (Real-SR) has been revolutionized by leveraging the powerful generative priors of large-scale diffusion and flow-based models. However, fine-tuning these models on limited LR-HR pairs often precipitates "prior collapse" that the model sacrifices its inherent generative richness to overfit specific training degradations. This issue is further exacerbated in one-ste…
-
Resolving space-sharing conflicts in road user interactions through uncertainty reduction: An active inference-based computational model
Understanding how road users resolve space-sharing conflicts is important both for traffic safety and the safe deployment of autonomous vehicles. While existing models have captured specific aspects of such interactions (e.g., explicit communication), a theoretically-grounded computational framework has been lacking. In this paper, we extend a previously developed active inference-based driver beh…
-
Numerical Studies of Accretion Flows onto a Neutron Star Engulfed in a Massive Star
Massive stars commonly form binaries that can evolve into compact systems via common envelope evolution (CEE), a critical but poorly understood phase -- especially when the companion is a neutron star. Understanding the drag force exerted on a neutron star during CEE is a key to the quantitative evaluation of orbital decay, merger timescale, and compactness of the resultant binary. In this paper, …