Researchers have developed two distinct systems named Coral and CoRAL. Coral is an adaptive system designed for cost-efficient serving of multiple large language models across heterogeneous cloud GPUs, aiming to optimize resource allocation and reduce serving costs by up to 2.79x. CoRAL, on the other hand, is a framework for robotic manipulation that uses LLMs for adaptive control, enabling zero-shot planning by decoupling high-level reasoning from low-level control and improving success rates by over 50% in contact-rich scenarios. AI
影响 Introduces novel approaches for optimizing LLM serving costs and enhancing robotic manipulation capabilities through LLM integration.
排序理由 Two distinct research papers are presented, one on LLM serving infrastructure and another on LLM-based robotic control.
AI 生成摘要 · Google Gemini · 来自 4 个来源。 我们如何撰写摘要 →
