Tag: Resource Allocation
All the articles with the tag "Resource Allocation".
-
Task-Oriented Semantic Communication in Large Multimodal Models-based Vehicle Networks
This paper proposes a task-oriented semantic communication framework for LMM-based vehicle AI, using LLaVA with Semantic Matching for efficient image slicing and Fusion Attention-based power allocation to prioritize critical data transmission, achieving significant accuracy improvements (up to 33.1% at low SNR) in traffic VQA tasks.
-
StreamRL: Scalable, Heterogeneous, and Elastic RL for LLMs with Disaggregated Stream Generation
本文提出 StreamRL 框架,通过分离式流生成架构优化 RL 训练,解决了流水线和偏斜气泡问题,提高了 LLMs RL 训练的吞吐量和成本效率。