arXiv Computer Science @arxiv_cs@qoto.org

AppAgent-Claw: CLI Is All You Need for GUI Automation https://arxiv.org/abs/2606.05171 #cs.HC #cs.SE

Is This Edit Correct? A Multi-Dimensional Benchmark for Reasoning-Aware Image Editing https://arxiv.org/abs/2606.05172 #cs.HC #cs.CV

Predict and Reconstruct: Joint Objectives for Self-Supervised Language Representation Learning https://arxiv.org/abs/2606.05173 #cs.CL #cs.AI

Improving Heart-Focused Medical Question Answering in LLMs via Variance-Aware Rubric Rewards with GRPO https://arxiv.org/abs/2606.05174 #cs.CL #cs.AI

Generic Triple-Latent Compression with Gated Associative Retrieval https://arxiv.org/abs/2606.05175 #cs.CL

PEFT of SLM for Telecommunications Customer Support: A Comparative Study of LoRA Configurations with Energy Consumption Analysis https://arxiv.org/abs/2606.05176 #cs.CL #cs.AI

Early Detection of Alzheimer's Disease Using Explainable Machine Learning on Clinical Biomarkers: A Multi-Class Classification Study Using the Alzheimer's Disease Neuroimaging Initiative (ADNI) Dataset https://arxiv.org/abs/2606.03995 #q-bio.QM #cs.LG #cs.AI

Witness-split + window-cardinality refinement for $r_3(N)$: Architecture, empirical results, and a structural hard pocket https://arxiv.org/abs/2606.04016 #cs.LO

Neither Layer Alone: Epistemic Integrity Requires Hierarchical Joint Design for Long-Running AI Agents https://arxiv.org/abs/2606.04017 #cs.SE

The Coercivity Gap in Neural PDE Solvers: Parameter Escape and Functional Convergence https://arxiv.org/abs/2606.04018 #math.NA #cs.NA

CodegenBench: Can LLMs Write Efficient Code Across Architectures? https://arxiv.org/abs/2606.04023 #cs.SE #cs.AI

The Biomimetic Architecture of Software 4.0 https://arxiv.org/abs/2606.04025 #cs.SE #cs.AI

MaskForge: Structure-Aware Adaptive Attacks for Jailbreaking Diffusion Large Language Models https://arxiv.org/abs/2606.04027 #cs.CR #cs.AI

Novel Aspects of IEEE SA P3109 Arithmetic Formats for Machine Learning https://arxiv.org/abs/2606.04028 #cs.LG

Position: Deployed Reinforcement Learning should be Continual https://arxiv.org/abs/2606.04029 #cs.LG #cs.AI

Reduced order modeling for spatio-temporal pattern approximation in diffusive Lotka-Volterra equations https://arxiv.org/abs/2606.04030 #math.NA #cs.NA

Cost-Aware Query Routing in RAG: Empirical Analysis of Retrieval Depth Tradeoffs https://arxiv.org/abs/2606.02581 #cs.IR #cs.AI

Applying Two-Grid Preconditioner for Subsurface Flow Simulation using Attention-enhanced Hybrid Network to Accelerate Multiscale Discretization in High-contrast Media https://arxiv.org/abs/2606.02582 #math.NA #cs.CE #cs.LG #cs.NA

A complete simulation framework for stone degradation on 3D real geometries https://arxiv.org/abs/2606.02583 #cs.CE

IdiomX A Multilingual Benchmark for Idiom Understanding, Retrieval, and Interpretation https://arxiv.org/abs/2606.02584 #cs.CL #cs.AI #cs.IR