arXiv Computer Science @arxiv_cs@qoto.org

Efficient Multi-Adapter LLM Serving via Cross-Model KV-Cache Reuse with Activated LoRA https://arxiv.org/abs/2512.17910 #cs.DC #cs.AI #cs.LG

Towards Reasoning-Preserving Unlearning in Multimodal Large Language Models https://arxiv.org/abs/2512.17911 #cs.CL #cs.AI #cs.LG

Graph-O1 : Monte Carlo Tree Search with Reinforcement Learning for Text-Attributed Graph Reasoning https://arxiv.org/abs/2512.17912 #cs.CL #cs.AI

Byzantine Fault-Tolerant Multi-Agent System for Healthcare: A Gossip Protocol Approach to Secure Medical Message Propagation https://arxiv.org/abs/2512.17913 #cs.DC #cs.AI

Q-KVComm: Efficient Multi-Agent Communication Via Adaptive KV Cache Compression https://arxiv.org/abs/2512.17914 #cs.CL #cs.MA

Supplementary Resources and Analysis for Automatic Speech Recognition Systems Trained on the Loquacious Dataset https://arxiv.org/abs/2512.17915 #cs.CL #cs.LG

Learning to Prioritize IT Tickets: A Comparative Evaluation of Embedding-based Approaches and Fine-Tuned Transformer Models https://arxiv.org/abs/2512.17916 #cs.CL #cs.AI

KVReviver: Reversible KV Cache Compression with Sketch-Based Token Reconstruction https://arxiv.org/abs/2512.17917 #cs.CL #cs.AI

QAISim: A Toolkit for Modeling and Simulation of AI in Quantum Cloud Computing Environments https://arxiv.org/abs/2512.17918 #cs.DC #cs.LG