arXiv Computer Science @arxiv_cs@qoto.org

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

An improved PINN framework integrating localized collocation scheme and PIKF https://arxiv.org/abs/2606.02585 #cs.CE

Fewer, Better Frames: A Compute-Normalized Proof of Concept for Coherence-First World-Model Rendering with Model-Guided FSR4 Frame Generation https://arxiv.org/abs/2606.02586 #cs.GR

Numerical simulations for two-dimensional reaction-diffusion problems with formation of multiple dead zones https://arxiv.org/abs/2606.02587 #math.NA #cs.NA

Lean-GAP: A Dataset of Formalized Graduate Algebra Problems https://arxiv.org/abs/2606.02588 #cs.LO #cs.AI #cs.PL

Human-in-the-Loop Contextual Bandits for Short-Term Rental Dynamic Pricing: Structural Equivalence of Historical Warm-Up and Approval-Gated Live Learning https://arxiv.org/abs/2606.02595 #cs.LG

Spectral Asymptotics of Neural Network Loss Landscapes: An Exact Decomposition of the Curvature Exponent https://arxiv.org/abs/2606.02596 #cs.LG

Plausibility Is Not Prediction: Contrastive Evidence for LLM-Based Cellular Perturbation Reasoning https://arxiv.org/abs/2606.01042 #cs.LG #cs.AI

Ask4VG: Risk-Aware Question Selection for Reducing Prior-Driven Answers in Medical VQA https://arxiv.org/abs/2606.01044 #cs.CV

Child-directed speech facilitates production, not comprehension, in BabyLMs https://arxiv.org/abs/2606.01045 #cs.CL

TravelEval: A Comprehensive Benchmarking Framework for Evaluating LLM-Powered Travel Planning Agents https://arxiv.org/abs/2606.01046 #cs.AI

Learning Multi-Modal Trajectory Policies for Data-Efficient Robotic Manipulation https://arxiv.org/abs/2606.01047 #cs.RO

Decoupled Residual Denoising Diffusion Models for Unified and Data Efficient Image-to-Image Translation https://arxiv.org/abs/2606.01048 #cs.CV

PMC-InterCPT: Rethinking Biomedical Interleaved Data for Multimodal Continued Pretraining https://arxiv.org/abs/2606.01049 #cs.CL

TextFake: Benchmarking AI-Generated Image Detection on Text-Rich Images https://arxiv.org/abs/2606.01050 #cs.CV

Interaction-Limited Safe Continuous-Time RL for Dynamical Medical Treatment https://arxiv.org/abs/2606.01051 #cs.LG

AnyEdit++: Adaptive Long-Form Knowledge Editing via Bayesian Surprise https://arxiv.org/abs/2606.01053 #cs.AI