CUEBES

Prompt Sensitivity and Answer Consistency of Small Open-Source Large Language Models on Clinical Question Answering: Implications for Low-Resource Healthcare Deployment

arXiv:2603.00917v2 Announce Type: replace Abstract: Small open-source language models are gaining attention for healthcare applications in low-resource settings where cloud infrastructure and GPU hardware may...

Hardware Health

arXiv CS Mar 5

Dr.Occ: Depth- and Region-Guided 3D Occupancy from Surround-View Cameras for Autonomous Driving

arXiv:2603.01007v2 Announce Type: replace Abstract: 3D semantic occupancy prediction is crucial for autonomous driving perception, offering comprehensive geometric scene understanding and semantic recognition. However, existing...

Robotics Psychology

arXiv CS Mar 5

Improved MambdaBDA Framework for Robust Building Damage Assessment Across Disaster Domains

arXiv:2603.01116v2 Announce Type: replace Abstract: Reliable post-disaster building damage assessment (BDA) from satellite imagery is hindered by severe class imbalance, background clutter, and domain shift...

Software Policy

arXiv CS Mar 5

vEcho: A Paradigm Shift from Vulnerability Verification to Proactive Discovery with Large Language Models

arXiv:2603.01154v2 Announce Type: replace Abstract: Static Application Security Testing (SAST) tools often suffer from high false positive rates, leading to alert fatigue that consumes valuable...

Software Policy

arXiv CS Mar 5

Digital Twin-Based Cooling System Optimization for Data Center

arXiv:2603.01198v2 Announce Type: replace Abstract: Data center cooling systems consume significant auxiliary energy, yet optimization studies rarely quantify the gap between theoretically optimal and operationally...

Technology Energy

arXiv CS Mar 5

A Study on Building Efficient Zero-Shot Relation Extraction Models

arXiv:2603.01266v2 Announce Type: replace Abstract: Zero-shot relation extraction aims to identify relations between entity mentions using textual descriptions of novel types (i.e., previously unseen) instead...

Software Policy

arXiv CS Mar 5

The Sentience Readiness Index: A Preliminary Framework for Measuring National Preparedness for the Possibility of Artificial Sentience

arXiv:2603.01508v2 Announce Type: replace Abstract: The scientific study of consciousness has begun to generate testable predictions about artificial systems. A landmark collaborative assessment evaluated current...

Artificial Intelligence Biology

arXiv CS Mar 5

ToolRLA: Multiplicative Reward Decomposition for Tool-Integrated Agents

arXiv:2603.01620v2 Announce Type: replace Abstract: Tool-integrated agents that interleave reasoning with API calls are promising for complex tasks, yet aligning them for high-stakes, domain-specific deployment...

Software Biology

arXiv CS Mar 5

Modeling and Analysis of Fish Interaction Networks under Projected Visual Stimuli

arXiv:2603.01682v2 Announce Type: replace Abstract: This paper addresses the estimation of a dynamic interaction network, a network of influence among individuals, under projected visual stimuli...

Psychology Policy

arXiv CS Mar 5

Causal Circuit Tracing Reveals Distinct Computational Architectures in Single-Cell Foundation Models: Inhibitory Dominance, Biological Coherence, and Cross-Model Convergence

arXiv:2603.01752v2 Announce Type: replace Abstract: Motivation: Sparse autoencoders (SAEs) decompose foundation model activations into interpretable features, but causal feature-to-feature interactions across network depth remain unknown...

Software Biology

arXiv CS Mar 5

Importance sampling and active subspace in quasi-Monte Carlo

arXiv:2603.01763v2 Announce Type: replace Abstract: The quasi-Monte Carlo method is widely used in computational finance, whose efficiency strongly depends on the smoothness and effective dimension...

Software Finance

arXiv CS Mar 5

Systematic Survey on Privacy-Preserving Architectures for IoT and Vehicular Data Sharing: Techniques, Challenges, and Future Directions

arXiv:2603.01876v2 Announce Type: replace Abstract: The proliferation of IoT and V2X systems generates unprecedented sensitive data at the network edge, demanding privacy-preserving architectures that enable...

Technology Cybersecurity

arXiv CS Mar 5

Agentic Code Reasoning

arXiv:2603.01896v2 Announce Type: replace Abstract: Can LLM agents explore codebases and reason about code semantics without executing the code? We study this capability, which we...

Software World News

arXiv CS Mar 5

Performance comparison of Python, MATLAB and R for numerical solutions of SI and SIR epidemiological models

arXiv:2603.01916v2 Announce Type: replace Abstract: Mathematical modeling plays a vital role in epidemiology, offering insights into the spread and control of infectious diseases. The compartmental...

Technology Psychology

arXiv CS Mar 5

From Variance to Invariance: Qualitative Content Analysis for Narrative Graph Annotation

arXiv:2603.01930v2 Announce Type: replace Abstract: Narratives in news discourse play a critical role in shaping public understanding of economic events, such as inflation. Annotating and...

Economics Psychology

arXiv CS Mar 5

Rich Insights from Cheap Signals: Efficient Evaluations via Tensor Factorization

arXiv:2603.02029v2 Announce Type: replace Abstract: Moving beyond evaluations that collapse performance across heterogeneous prompts toward fine-grained evaluation at the prompt level, or within relatively homogeneous...

Software Policy

arXiv CS Mar 5

Federated Inference: Toward Privacy-Preserving Collaborative and Incentivized Model Serving

arXiv:2603.02214v2 Announce Type: replace Abstract: Federated Inference (FI) studies how independently trained and privately owned models can collaborate at inference time without sharing data or...

Psychology Engineering

arXiv CS Mar 5

Structured vs. Unstructured Pruning: An Exponential Gap

arXiv:2603.02234v2 Announce Type: replace Abstract: The Strong Lottery Ticket Hypothesis (SLTH) posits that large, randomly initialized neural networks contain sparse subnetworks capable of approximating a...

Neuroscience Software

arXiv CS Mar 5

Detecting AI-Generated Essays in Writing Assessment: Responsible Use and Generalizability Across LLMs

arXiv:2603.02353v2 Announce Type: replace Abstract: Writing is a foundational literacy skill that underpins effective communication, fosters critical thinking, facilitates learning across disciplines, and enables individuals...

Software Policy

arXiv CS Mar 5

Can machines be uncertain?

arXiv:2603.02365v2 Announce Type: replace Abstract: The paper investigates whether and how AI systems can realize states of uncertainty. By adopting a functionalist and behavioral perspective,...

Psychology Policy

arXiv CS Mar 5

A Unified Revisit of Temperature in Classification-Based Knowledge Distillation

arXiv:2603.02430v2 Announce Type: replace Abstract: A central idea of knowledge distillation is to expose relational structure embedded in the teacher's weights for the student to...

Embedded Systems Software

arXiv CS Mar 5

A Novel Modular Cable-Driven Soft Robotic Arm with Multi-Segment Reconfigurability

arXiv:2603.02468v2 Announce Type: replace Abstract: This paper presents a novel, modular, cable-driven soft robotic arm featuring multi-segment reconfigurability. The proposed architecture enables a stackable system...

Embedded Systems Software

arXiv CS Mar 5

NeuroProlog: Multi-Task Fine-Tuning for Neurosymbolic Mathematical Reasoning via the Cocktail Effect

arXiv:2603.02504v2 Announce Type: replace Abstract: Large Language Models (LLMs) achieve strong performance on natural language tasks but remain unreliable in mathematical reasoning, frequently generating fluent...

Artificial Intelligence Chemistry

arXiv CS Mar 5

Human-Certified Module Repositories for the AI Age

arXiv:2603.02512v2 Announce Type: replace Abstract: Human-Certified Module Repositories (HCMRs) are introduced in this work as a new architectural model for constructing trustworthy software in the...

Software Biology