arXiv Computer Science @arxiv_cs@qoto.org

From user-understandable to technical process model: a model-driven approach using cuta4bpm https://arxiv.org/abs/2605.26117 #cs.SE

Xe-Forge: Multi-Stage LLM-Powered Kernel Optimization for Intel GPU https://arxiv.org/abs/2605.26118 #cs.DC #cs.AI

Edge AI Deployment Beyond Models: A BSP-Aware Systems Framework for Industrial Embedded Platforms https://arxiv.org/abs/2605.26119 #cs.DC #cs.AI

Semantic-aware Token Selection and Resource Optimization for Communication-efficient Split Federated Fine-tuning in Edge Intelligence https://arxiv.org/abs/2605.26120 #cs.DC

GEM: Geometric Entropy Mixing for Optimal LLM Data Curation https://arxiv.org/abs/2605.26121 #cs.LG #cs.AI

Low Latency Stand Alone Compute-Efficient Forecasting of Marine Engine Time Series Data https://arxiv.org/abs/2605.26123 #eess.SY #stat.CO #cs.SY

Inflatable devices for planetary aerocapture and aerobraking manoeuvres https://arxiv.org/abs/2605.26125 #astro-ph.EP #astro-ph.IM #eess.SY #cs.SY

The Constraint Tax: Measuring Validity-Correctness Tradeoffs in Structured Outputs for Small Language Models https://arxiv.org/abs/2605.26128 #cs.LG #cs.SE

AirCast-SR: A Foundation Model for Kilometer-Scale Atmospheric Super-Resolution via Latent Consistency Diffusion https://arxiv.org/abs/2605.26130 #physics.ao-ph #cs.LG

Self-Verified Distillation: Your Language Model Is Secretly Its Own Synthetic Data Pipeline https://arxiv.org/abs/2605.26132 #cs.CL #cs.LG

Identifying and Mitigating Systemic Measurement Bias in Production LLM Inference Benchmarks https://arxiv.org/abs/2605.24217 #cs.AI #cs.DC

QUEST: Training Frontier Deep Research Agents with Fully Synthetic Tasks https://arxiv.org/abs/2605.24218 #cs.CL

Beyond Final Answers: Auditing Trajectory-Level Hallucinations in Multi-Agent Industrial Workflows https://arxiv.org/abs/2605.24219 #cs.AI

Polar: Agentic RL on Any Harness at Scale https://arxiv.org/abs/2605.24220 #cs.DC

Analyzing the Effects of Two-Stage Peer Evaluation https://arxiv.org/abs/2605.24222 #cs.GT

ECo-MoE: Embodiment-Conditioned Mixture of Experts Increases the Evolvability of Robots https://arxiv.org/abs/2605.24225 #cs.RO

Sketch Bug: Using Sketch-Based Input for Interactive Code Debugging https://arxiv.org/abs/2605.24228 #cs.HC

How Well Do Models Follow Their Constitutions? https://arxiv.org/abs/2605.24229 #cs.AI

Accuracy Analysis of the Proxy Point Method with Applications to Some Toeplitz Matrices https://arxiv.org/abs/2605.24231 #math.NA #cs.NA

Bayesian Rational Search Engine User https://arxiv.org/abs/2605.24233 #econ.TH #cs.IR