arXiv Computer Science @arxiv_cs@qoto.org

M-RAG: Making RAG Faster, Stronger, and More Efficient https://arxiv.org/abs/2603.26667 #cs.IR #cs.AI

Bridge-RAG: An Abstract Bridge Tree Based Retrieval Augmented Generation Algorithm With Cuckoo Filter https://arxiv.org/abs/2603.26668 #cs.IR #cs.AI #cs.CL

ReCQR: Incorporating conversational query rewriting to improve Multimodal Image Retrieval https://arxiv.org/abs/2603.26669 #cs.IR #cs.AI #cs.LG

SRAG: RAG with Structured Data Improves Vector Retrieval https://arxiv.org/abs/2603.26670 #cs.IR #cs.CL

Mitigating Forgetting in Continual Learning with Selective Gradient Projection https://arxiv.org/abs/2603.26671 #math.OC #cs.LG

Can AI be a Teaching Partner? Evaluating ChatGPT, Gemini, and DeepSeek across Three Teaching Strategies https://arxiv.org/abs/2603.26673 #cs.CY #cs.AI

Co-designing a Social Robot for Newcomer Children's Cultural and Language Learning https://arxiv.org/abs/2603.26674 #cs.RO #cs.CY #cs.HC

GeoBlock: Inferring Block Granularity from Dependency Geometry in Diffusion Language Models https://arxiv.org/abs/2603.26675 #cs.CL #cs.LG

Evaluating Human-AI Safety: A Framework for Measuring Harmful Capability Uplift https://arxiv.org/abs/2603.26676 #cs.CY #cs.AI #cs.HC

Why Do We Suffer for Fun? Ordeal Pleasure in Souls-like Games https://arxiv.org/abs/2603.26677 #cs.CY

BeSafe-Bench: Unveiling Behavioral Safety Risks of Situated Agents in Functional Environments https://arxiv.org/abs/2603.25747 #cs.AI

Sommelier: Scalable Open Multi-turn Audio Pre-processing for Full-duplex Speech Language Models https://arxiv.org/abs/2603.25750 #eess.AS #cs.SD #cs.AI

Relational graph-driven differential denoising and diffusion attention fusion for multimodal conversation emotion recognition https://arxiv.org/abs/2603.25752 #eess.AS #cs.CL #cs.SD

DUGC-VRNet: Joint VR Recognition and Channel Estimation for Spatially Non-Stationary XL-MIMO https://arxiv.org/abs/2603.25754 #math.IT #cs.IT

A-SelecT: Automatic Timestep Selection for Diffusion Transformer Representation Learning https://arxiv.org/abs/2603.25758 #eess.IV #cs.CV #cs.AI #cs.LG

A Survey of OCR Evaluation Methods and Metrics and the Invisibility of Historical Documents https://arxiv.org/abs/2603.25761 #cs.CV #cs.DL

CANGuard: A Spatio-Temporal CNN-GRU-Attention Hybrid Architecture for Intrusion Detection in In-Vehicle CAN Networks https://arxiv.org/abs/2603.25763 #cs.CR #cs.AI

Consistency Amplifies: How Behavioral Variance Shapes Agent Accuracy https://arxiv.org/abs/2603.25764 #cs.SE #cs.AI

Evaluating Synthetic Images as Effective Substitutes for Experimental Data in Surface Roughness Classification https://arxiv.org/abs/2603.25765 #cond-mat.mtrl-sci #cs.CV

ETA-VLA: Efficient Token Adaptation via Temporal Fusion and Intra-LLM Sparsification for Vision-Language-Action Models https://arxiv.org/abs/2603.25766 #cs.RO #cs.AI