CUEBES

Energy-Aware Holistic Optimization in UAV-Assisted Fog Computing: Attitude, Trajectory, Task Assignment

arXiv:2407.14894v3 Announce Type: replace Abstract: Unmanned Aerial Vehicles (UAVs) have significantly enhanced fog computing by acting as both flexible computation platforms and communication mobile relays....

Software Technology

arXiv CS Feb 13

Accelerating Large Language Model Inference with Self-Supervised Early Exits

arXiv:2407.21082v2 Announce Type: replace Abstract: This paper presents a modular approach to accelerate inference in large language models (LLMs) by adding early exit heads at...

Software Policy

arXiv CS Feb 13

KeySpace: Enhancing Public Key Infrastructure for Interplanetary Networks

arXiv:2408.10963v5 Announce Type: replace Abstract: As the use of satellites continues to grow, new networking paradigms are emerging to support the scale and long distance...

Space & Astronomy Technology

arXiv CS Feb 13

Effective Wordle Heuristics

arXiv:2408.11730v2 Announce Type: replace Abstract: While previous researchers have performed an exhaustive search to determine an optimal Wordle strategy, that computation is very time consuming...

Policy Biology

arXiv CS Feb 13

SeqRisk: Transformer-augmented latent variable model for robust survival prediction with longitudinal data

arXiv:2409.12709v2 Announce Type: replace Abstract: In healthcare, risk assessment of patient outcomes has been based on survival analysis for a long time, i.e. modeling time-to-event...

Health Software

arXiv CS Feb 13

DiSPo: Diffusion-SSM based Policy Learning for Coarse-to-Fine Action Discretization

arXiv:2409.14719v3 Announce Type: replace Abstract: We aim to solve the problem of generating coarse-to-fine skills learning from demonstrations (LfD). To scale precision, traditional LfD approaches...

Software Policy

arXiv CS Feb 13

An Anatomy-Aware Shared Control Approach for Assisted Teleoperation of Lung Ultrasound Examinations

arXiv:2409.17395v2 Announce Type: replace Abstract: Although fully autonomous systems still face challenges due to patients' anatomical variability, teleoperated systems appear to be more practical in...

Health Robotics

arXiv CS Feb 13

Learning a Neural Solver for Parametric PDE to Enhance Physics-Informed Methods

arXiv:2410.06820v5 Announce Type: replace Abstract: Physics-informed deep learning often faces optimization challenges due to the complexity of solving partial differential equations (PDEs), which involve exploring...

Software Artificial Intelligence

arXiv CS Feb 13

LabSafety Bench: Benchmarking LLMs on Safety Issues in Scientific Labs

arXiv:2410.14182v4 Announce Type: replace Abstract: Artificial Intelligence (AI) is revolutionizing scientific research, yet its growing integration into laboratory environments presents critical safety challenges. Large language...

Artificial Intelligence Environment

arXiv CS Feb 13

Shallow Diffuse: Robust and Invisible Watermarking through Low-Dimensional Subspaces in Diffusion Models

arXiv:2410.21088v5 Announce Type: replace Abstract: The widespread use of AI-generated content from diffusion models has raised significant concerns regarding misinformation and copyright infringement. Watermarking is...

Software Technology

arXiv CS Feb 13

Scale Contrastive Learning with Selective Attentions for Blind Image Quality Assessment

arXiv:2411.09007v2 Announce Type: replace Abstract: Human visual perception naturally evaluates image quality across multiple scales, a hierarchical process that existing blind image quality assessment (BIQA)...

Technology Psychology

arXiv CS Feb 13

NewsInterview: a Dataset and a Playground to Evaluate LLMs' Ground Gap via Informational Interviews

arXiv:2411.13779v2 Announce Type: replace Abstract: Large Language Models (LLMs) have demonstrated impressive capabilities in generating coherent text but often struggle with grounding language and strategic...

Psychology Biology

arXiv CS Feb 13

Neural numerical homogenization based on Deep Ritz corrections

arXiv:2411.14084v3 Announce Type: replace Abstract: Numerical homogenization methods aim at providing appropriate coarse-scale approximations of solutions to (elliptic) partial differential equations that involve highly oscillatory...

Neuroscience Software

arXiv CS Feb 13

Normative Feeling: Socially Patterned Affective Mechanisms

arXiv:2411.18037v4 Announce Type: replace Abstract: Breaking a norm elicits both material and emotional consequences, yet how this coupling arose evolutionarily remains unclear. We investigate this...

Policy Materials Science

arXiv CS Feb 13

PBP: Post-training Backdoor Purification for Malware Classifiers

arXiv:2412.03441v4 Announce Type: replace Abstract: In recent years, the rise of machine learning (ML) in cybersecurity has brought new challenges, including the increasing threat of...

Cybersecurity Software

arXiv CS Feb 13

A Survey on Dynamic Neural Networks: from Computer Vision to Multi-modal Sensor Fusion

arXiv:2501.07451v3 Announce Type: replace Abstract: Model compression is essential in the deployment of large Computer Vision models on embedded devices. However, static optimization techniques (e.g....

Embedded Systems Technology

arXiv CS Feb 13

FaceQSORT: a Multi-Face Tracking Method based on Biometric and Appearance Features

arXiv:2501.11741v4 Announce Type: replace Abstract: In this work, a novel multi-face tracking method named FaceQSORT is proposed. To mitigate multi-face tracking challenges (e.g., partially occluded...

Psychology Software

arXiv CS Feb 13

Dual Frequency Branch Framework with Reconstructed Sliding Windows Attention for AI-Generated Image Detection

arXiv:2501.15253v3 Announce Type: replace Abstract: The rapid advancement of Generative Adversarial Networks (GANs) and diffusion models has enabled the creation of highly realistic synthetic images,...

Energy Biology

arXiv CS Feb 13

Compositional Generalization from Learned Skills via CoT Training: A Theoretical and Structural Analysis for Reasoning

arXiv:2502.04667v3 Announce Type: replace Abstract: Chain-of-Thought (CoT) training has markedly advanced the reasoning capabilities of large language models (LLMs), yet the mechanisms by which CoT...

Biology Engineering

arXiv CS Feb 13

Teaching LLMs According to Their Aptitude: Adaptive Reasoning for Mathematical Problem Solving

arXiv:2502.12022v5 Announce Type: replace Abstract: Existing approaches to mathematical reasoning with large language models (LLMs) rely on Chain-of-Thought (CoT) for generalizability or Tool-Integrated Reasoning (TIR)...

Robotics Software

arXiv CS Feb 13

Translate Policy to Language: Flow Matching Generated Rewards for LLM Explanations

arXiv:2502.12530v3 Announce Type: replace Abstract: As humans increasingly share environments with diverse agents powered by RL, LLMs, and beyond, the ability to explain agent policies...

Policy Artificial Intelligence

arXiv CS Feb 13

PASER: Post-Training Data Selection for Efficient Pruned Large Language Model Recovery

arXiv:2502.12594v3 Announce Type: replace Abstract: Model pruning is an effective approach for compressing large language models (LLMs). However, this process often leads to significant degradation...

Software Technology

arXiv CS Feb 13

Efficient and Sharp Off-Policy Learning under Unobserved Confounding

arXiv:2502.13022v2 Announce Type: replace Abstract: We develop a novel method for personalized off-policy learning in scenarios with unobserved confounding. Thereby, we address a key limitation...

Health Policy

arXiv CS Feb 13

A Leaf-Level Dataset for Soybean-Cotton Detection and Segmentation

arXiv:2503.01605v2 Announce Type: replace Abstract: Soybean and cotton are major drivers of many countries' agricultural sectors, offering substantial economic returns but also facing persistent challenges...

Software Psychology