arXiv Computer Science @arxiv_cs@qoto.org

Kernel Foundry: A Diagnosis-driven Evolutionary Kernel Optimizer with Multi-Experts https://arxiv.org/abs/2605.30359 #eess.SY #cs.NE #cs.DC #cs.LG #cs.PF #cs.SE #cs.SY

Polynomial Histograms for Memory-Efficient Representation of Long-tailed System Distributions https://arxiv.org/abs/2605.30360 #stat.AP #cs.DC

Gradient-Free Training of Spiking Neural Networks via Low-Rank Evolution Strategies https://arxiv.org/abs/2605.30361 #cs.NE #cs.AI #cs.LG

XOResNet: Exclusive-OR Meta-Residuals Facilitate Deep Spiking Neural Networks Learning https://arxiv.org/abs/2605.30362 #cs.NE #cs.AI #cs.CV

Mental Damage: Caption Poisoning Attacks on Retrieval-Augmented Text-to-Music Generation https://arxiv.org/abs/2605.30365 #eess.AS #cs.SD #cs.AI

Escaping the Linearity Trap: Manifold Detours for Black-Box Adversarial Attacks on Singing Audio Deepfake Detection https://arxiv.org/abs/2605.30366 #eess.AS #cs.CR #cs.SD

Lightweight Multimodal LLM-Enabled Cost-Effective Defect Grading of Power Transmission Equipment https://arxiv.org/abs/2605.28822 #cs.CL

What are They Thinking? Delineation, Probing and Tracking of Concepts in LLMs https://arxiv.org/abs/2605.28823 #cs.CL

A Modular Architecture for Typologically Controlled Lexicon Generation https://arxiv.org/abs/2605.28824 #cs.CL

MechELK: A Mechanistic Interpretability Framework for Eliciting Latent Knowledge in Large Language Models https://arxiv.org/abs/2605.28825 #cs.CL

From Context Shift to Stylistic Collapse: Why Training Objectives Matter More Than Scale https://arxiv.org/abs/2605.28826 #cs.CL

RightNow-Arabic-0.5B-Turbo: An Open Sub-1B Arabic Language Model via Vocabulary Injection and Edge-First Deployment https://arxiv.org/abs/2605.28827 #cs.CL #cs.LG

Micro-Macro Retrieval: Reducing Long-Form Hallucination in Large Language Models https://arxiv.org/abs/2605.28828 #cs.CL #cs.AI

Aryabhata 2: Scaling Reinforcement Learning for Advanced STEM Reasoning https://arxiv.org/abs/2605.28829 #cs.CL #cs.AI #cs.CY

Benchmarking Open-Source Safety Guard Models: A Comprehensive Evaluation https://arxiv.org/abs/2605.28830 #cs.CL #cs.AI #cs.SE

S3Mem: Structured Spatiotemporal Scene-Event Memory for Long-Horizon Interactive Question Answering https://arxiv.org/abs/2605.28831 #cs.CL #cs.AI

Identifying and Understanding Human Values in Text: A Tailorable LLM-based Architecture https://arxiv.org/abs/2605.27373 #cs.AI #cs.CL #cs.CY

ICG: Improving Cover Image Generation via MLLM-based Prompting and Personalized Preference Alignment https://arxiv.org/abs/2605.27374 #cs.CL

LCO: LLM-based Constraint Optimization for Safer Agentic LLMs in Real-world Tasks https://arxiv.org/abs/2605.27375 #cs.CL

Unlocking Fine-Grained and Within-Utterance Speaking Style Control in Prompt-Based Text-to-Speech Models https://arxiv.org/abs/2605.27376 #cs.CL #cs.AI