3468 papers
This study of financial professionals using AI reveals that while AI-generated content improves task quality, unsolicited proactive interventions significantly increase extraneous cognitive load—particularly for less experienced users—thereby degrading performance more severely than intrinsic task complexity.
This study introduces and evaluates the Adiabatic Quantum Power Flow (AQPF) and Optimal Power Flow (AQOPF) algorithms, which reformulate power system analysis as discrete combinatorial optimization problems solvable by quantum and digital annealers, demonstrating their feasibility and promising scalability across various test systems from 4 to 1354 buses.
This paper introduces a novel representation of local protein environments derived from atomistic foundation models that effectively captures structural and chemical features, enabling the construction of data-driven priors and achieving state-of-the-art accuracy in physics-informed NMR chemical shift prediction.
This paper presents an unsupervised approach that leverages vision-language reasoning and clustering to automatically discover semantically coherent failure taxonomies from large-scale robotic deployment logs, thereby enabling scalable failure analysis, targeted data collection, and improved runtime monitoring across diverse domains.
This paper proposes a novel task allocation framework for multitasking robots that accounts for physical constraints ignored by existing single-tasking methods, utilizing both a weighted MAX-SAT compilation and a greedy heuristic to demonstrate improved efficiency through synthetic, simulated, and physical experiments.
The paper introduces ContextMatters, a framework that combines Large Language Models with classical planning to dynamically relax goals based on environmental context, significantly improving 3D scene planning success rates and enabling successful real-world robot deployment.
This study introduces a variance-penalized GAN based on pyramid pix2pix that generates high-fidelity HER2-specific immunohistochemistry (IHC) images from routine hematoxylin and eosin (H&E) slides, effectively mitigating mode collapse and outperforming baseline models to enable cost-effective, scalable precision oncology diagnostics.
This paper introduces LINO UniPS, a unified photometric stereo framework that achieves state-of-the-art performance under arbitrary lighting by employing Light Register Tokens and Interleaved Attention for robust illumination-normal decoupling, alongside a Wavelet-based Dual-branch Architecture to preserve high-frequency geometric details, all trained on the newly proposed large-scale PS-Verse dataset.
This paper proposes a novel VLM-guided cascaded framework for Open-Vocabulary Camouflaged Object Segmentation that leverages Vision Language Model features to explicitly prompt the Segment Anything Model for precise localization and utilizes soft spatial priors to retain full-image context, thereby overcoming domain gaps and improving both segmentation and classification of camouflaged objects across arbitrary categories.
This paper introduces WaLi, a novel attack framework that leverages standard HVAC pressure sensors to reconstruct intelligible human speech from noisy, low-resolution data using a complex-valued conformer and Complex Global Attention Block, thereby revealing a significant, previously unaddressed privacy vulnerability in building infrastructure.
The paper proposes SUBARU, a power-efficient framework for hearables that intentionally employs sub-Nyquist sampling and low bit-resolution ADCs to achieve a 3.31x reduction in power consumption while maintaining high-quality multimodal speech enhancement through a novel wideband reconstruction methodology.
This paper proposes VTOPA, a vision-aided algorithm that autonomously extracts environmental data to dynamically optimize UAV positioning for obstacle-aware Line of Sight connectivity, resulting in significant throughput and delay improvements in urban wireless networks.
LD-RPS proposes a novel, dataset-free, and unified image restoration framework that leverages recurrent posterior sampling on a pretrained latent diffusion model, enhanced by multimodal semantic priors and a lightweight alignment module, to achieve superior performance across various degradation types without task-specific training.
This paper proposes Query-based Adaptive Aggregation (QAA), a novel feature aggregation technique that utilizes learned queries as reference codebooks to effectively address dataset divergences in multi-dataset joint training, thereby achieving robust universal Visual Place Recognition with balanced generalization and state-of-the-art performance.
This paper introduces hPGA-DP, a hybrid diffusion policy that integrates Projective Geometric Algebra into the network architecture to embed geometric inductive biases, thereby significantly improving training efficiency and task performance in robot manipulation compared to standard approaches.
This paper proposes MCULoRA, a novel parameter-efficient framework featuring modality combination aware low-rank adaptation and dynamic parameter fine-tuning to resolve gradient conflicts and improve performance in incomplete multimodal emotion recognition.
The paper proposes Mamba Snake, a novel deep snake framework enhanced by state space modeling and a dual-classification synergy mechanism, which effectively addresses the challenges of multi-scale structural heterogeneity in Unified Medical Image Segmentation by modeling inter-organ topological relationships and refining complex morphologies to achieve superior performance across five clinical datasets.
The paper introduces , a novel feed-forward neural network that achieves state-of-the-art performance in visual geometry reconstruction tasks by employing a fully permutation-equivariant architecture to predict camera poses and point maps without relying on a fixed reference view.
This paper proposes a Vision Transformer-based framework that leverages PCA-driven weak supervision to expand limited manual annotations for refining disaster-affected area segmentation using Sentinel-2 and Formosat-5 imagery, thereby enhancing the reliability and scalability of the Taiwan Space Agency's Emergent Value Added Product (EVAP) in scenarios with scarce ground truth.
This paper surveys state-of-the-art auto-scaling approaches for microservice applications since 2018, presenting a five-dimensional taxonomy and comprehensive analysis to address challenges in resource efficiency, cost optimization, and SLA assurance within cloud-native environments.