arXiv Computer Science @arxiv_cs@qoto.org

Same Voice, Different Lab: On the Homogenization of Frontier LLM Personalities https://arxiv.org/abs/2605.02897 #cs.HC #cs.AI

What Shapes Participant Data Quality? A Scoping Review and Case Study of Crowdsourced Webcam Eye Tracking in AI Interviews https://arxiv.org/abs/2605.02898 #cs.HC

A Study of Consumers Cognitive Load in eCommerce Websites using Eye-tracking Technology https://arxiv.org/abs/2605.02899 #cs.HC

Safety in Embodied AI: A Survey of Risks, Attacks, and Defenses https://arxiv.org/abs/2605.02900 #cs.CR #cs.AI #cs.CV #cs.RO

Towards an End-to-End System for 3D Tracking of Physical Objects in Virtual Immersive Environments https://arxiv.org/abs/2605.02901 #cs.HC #cs.CV

From Passive Feeds to Guided Discovery: AI-Initiated Interaction for Vague Intent in Content Exploration https://arxiv.org/abs/2605.02902 #cs.HC #cs.AI

A User-Centric Analysis of Explainability in AI-Based Medical Image Diagnosis https://arxiv.org/abs/2605.02903 #cs.HC #cs.AI #cs.CV

StateSMix: Online Lossless Compression via Mamba State Space Models and Sparse N-gram Context Mixing https://arxiv.org/abs/2605.02904 #math.IT #cs.LG #cs.IT

eOptShrinkQ: Near-Lossless KV Cache Compression Through Optimal Spectral Denoising and Quantization https://arxiv.org/abs/2605.02905 #math.IT #cs.LG #cs.IT

An End-to-End Framework for Building Large Language Models for Software Operations https://arxiv.org/abs/2605.02906 #cs.LG

Understanding the Performance Plateau in Text-to-Video Retrieval: A Comprehensive Empirical and Linguistic Analysis https://arxiv.org/abs/2605.00826 #cs.IR #cs.CV #cs.LG #cs.MM

Separating Intelligence from Execution: A Workflow Engine for the Model Context Protocol https://arxiv.org/abs/2605.00827 #cs.DC #cs.AI #cs.SE

Canonical LST: A Protocol-Native Liquid Staking Solution for Tezos https://arxiv.org/abs/2605.00828 #cs.DC #cs.CR

LLM-based uncertainty assessment of social media situational signals for crisis reporting https://arxiv.org/abs/2605.00829 #cs.CY

Efficient Accelerated Graph Edit Distance Computation on GPU https://arxiv.org/abs/2605.00830 #cs.DC

GhostServe: A Lightweight Checkpointing System in the Shadow for Fault-Tolerant LLM Serving https://arxiv.org/abs/2605.00831 #cs.DC #cs.AI #cs.PF

Synthetic Designed Experiments for Diagnosing Vision Model Failure https://arxiv.org/abs/2605.00832 #cs.CV #cs.LG

Agentopic: A Generative AI Agent Workflow for Explainable Topic Modeling https://arxiv.org/abs/2605.00833 #cs.LG #cs.AI

Polynomial-Time Optimal Group Selection via the Double-Commutator Eigenvalue Problem https://arxiv.org/abs/2605.00834 #math.IT #cs.LG #cs.CC #cs.IT

Sparse Regression under Correlation and Weak Signals: A Reproducible Benchmark of Classical and Bayesian Methods https://arxiv.org/abs/2605.00835 #cs.LG