arXiv Computer Science @arxiv_cs@qoto.org

Optimal Unlabeled Pebble Motion on Trees and its Application to Multi-Agent Path Finding https://arxiv.org/abs/2603.23503 #cs.DS

Smooth Routing in Decaying Trees https://arxiv.org/abs/2603.23504 #cs.DS #cs.MA

The HyperFrog Cryptosystem: High-Genus Voxel Topology as a Trapdoor for Post-Quantum KEMs https://arxiv.org/abs/2603.23505 #quant-ph #cs.CR

Leveraging Computerized Adaptive Testing for Cost-effective Evaluation of Large Language Models in Medical Benchmarking https://arxiv.org/abs/2603.23506 #cs.CL #cs.AI

Beyond Masks: Efficient, Flexible Diffusion Language Models via Deletion-Insertion Processes https://arxiv.org/abs/2603.23507 #cs.CL #cs.AI #cs.LG

Fast and Faithful: Real-Time Verification for Long-Document Retrieval-Augmented Generation Systems https://arxiv.org/abs/2603.23508 #cs.CL #cs.IR

Internal Safety Collapse in Frontier Large Language Models https://arxiv.org/abs/2603.23509 #cs.CL #cs.AI #cs.CR

Visuospatial Perspective Taking in Multimodal Language Models https://arxiv.org/abs/2603.23510 #cs.CL #cs.AI

DISCO: Document Intelligence Suite for COmparative Evaluation https://arxiv.org/abs/2603.23511 #cs.CL #cs.AI #cs.CV

S-Path-RAG: Semantic-Aware Shortest-Path Retrieval Augmented Generation for Multi-Hop Knowledge Graph Question Answering https://arxiv.org/abs/2603.23512 #cs.CL #cs.AI #cs.IR

Founder effects shape the evolutionary dynamics of multimodality in open LLM families https://arxiv.org/abs/2603.22287 #cs.CV #cs.AI #cs.CL

Evaluating Prompting Strategies for Chart Question Answering with Large Language Models https://arxiv.org/abs/2603.22288 #cs.CL #cs.AI #cs.LG

MERIT: Memory-Enhanced Retrieval for Interpretable Knowledge Tracing https://arxiv.org/abs/2603.22289 #cs.CL #cs.AI

Less is More: Adapting Text Embeddings for Low-Resource Languages with Small Scale Noisy Synthetic Data https://arxiv.org/abs/2603.22290 #cs.CL #cs.IR

Evaluating Large Language Models' Responses to Sexual and Reproductive Health Queries in Nepali https://arxiv.org/abs/2603.22291 #cs.CL

Beyond Hard Constraints: Budget-Conditioned Reachability For Safe Offline Reinforcement Learning https://arxiv.org/abs/2603.22292 #cs.LG #cs.AI #cs.RO

TIPS: Turn-Level Information-Potential Reward Shaping for Search-Augmented LLMs https://arxiv.org/abs/2603.22293 #cs.CL #cs.AI #cs.LG

Efficient Embedding-based Synthetic Data Generation for Complex Reasoning Tasks https://arxiv.org/abs/2603.22294 #cs.LG #cs.AI

Whether, Not Which: Mechanistic Interpretability Reveals Dissociable Affect Reception and Emotion Categorization in LLMs https://arxiv.org/abs/2603.22295 #cs.CL #cs.AI

Between the Layers Lies the Truth: Uncertainty Estimation in LLMs Using Intra-Layer Local Information Scores https://arxiv.org/abs/2603.22299 #cs.LG #cs.AI