arXiv Computer Science @arxiv_cs@qoto.org

Evaluating Prompt Injection Defenses for Educational LLM Tutors: Security-Usability-Latency Trade-offs https://arxiv.org/abs/2605.06669 #cs.CR #cs.AI #cs.LG

GraphDC: A Divide-and-Conquer Multi-Agent System for Scalable Graph Algorithm Reasoning https://arxiv.org/abs/2605.06671 #cs.AI #cs.MA

More Thinking, More Bias: Length-Driven Position Bias in Reasoning Models https://arxiv.org/abs/2605.06672 #cs.AI #cs.CL #cs.LG

Domain-level metacognitive monitoring in frontier LLMs: A 33-model atlas https://arxiv.org/abs/2605.06673 #cs.CL #cs.AI #cs.LG

RateQuant: Optimal Mixed-Precision KV Cache Quantization via Rate-Distortion Theory https://arxiv.org/abs/2605.06675 #math.IT #cs.LG #cs.CL #cs.IT

LKV: End-to-End Learning of Head-wise Budgets and Token Selection for LLM KV Cache Eviction https://arxiv.org/abs/2605.06676 #cs.LG #cs.CL

A Wasserstein GAN-based climate scenario generator for risk management and insurance: the case of soil subsidence https://arxiv.org/abs/2605.06678 #q-fin.RM #stat.AP #cs.LG

Breaking the Illusion: When Positive Meets Negative in Multimodal Decoding https://arxiv.org/abs/2605.06679 #cs.LG

On the Role of Strain and Vorticity in Numerical Integration Error for Flow Matching https://arxiv.org/abs/2605.06680 #physics.flu-dyn #cs.LG #cs.CV

A Hierarchical Ensemble Pipeline for Anomaly Detection in ESA Satellite Telemetry https://arxiv.org/abs/2605.06681 #cs.LG #cs.CV

A GPU-Accelerated Hybrid Method for a Class of Multi-Depot Vehicle Routing Problems https://arxiv.org/abs/2605.05208 #math.OC #cs.RO #cs.DC

Are Flat Minima an Illusion? https://arxiv.org/abs/2605.05209 #cs.LG #cs.AI

DisastRAG: A Multi-Source Disaster Information Integration and Access System Based on Retrieval-Augmented Large Language Models https://arxiv.org/abs/2605.05210 #cs.IR

Nationwide EHR-Based Chronic Rhinosinusitis Prediction Using Demographic-Stratified Models https://arxiv.org/abs/2605.05213 #q-bio.QM #cs.LG

Layout-Aware Representation Learning for Open-Set ID Fraud Discovery https://arxiv.org/abs/2605.05215 #cs.CV #cs.AI #cs.LG

SAT: Sequential Agent Tuning for Coordinator Free Plug and Play Multi-LLM Training with Monotonic Improvement Guarantees https://arxiv.org/abs/2605.05216 #cs.LG

Physics-Informed Neural Networks with Learnable Loss Balancing and Transfer Learning https://arxiv.org/abs/2605.05217 #cs.LG #cs.AI

Horizon-Constrained Rashomon Sets for Chaotic Forecasting https://arxiv.org/abs/2605.05218 #math.DS #nlin.CD #cs.LG #cs.AI

Sparse Prefix Caching for Hybrid and Recurrent LLM Serving https://arxiv.org/abs/2605.05219 #cs.LG #cs.AI

MidSteer: Optimal Affine Framework for Steering Generative Models https://arxiv.org/abs/2605.05220 #cs.LG #cs.AI