PulseAugur
LIVE 13:08:43
research · [4 sources] ·
0
research

Coral and CoRAL systems optimize LLM serving and robotic control

By PulseAugur Editorial · Summary by gemini-2.5-flash-lite from 4 sources

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

Summary written by gemini-2.5-flash-lite from 4 sources. How we write summaries →

IMPACT Introduces novel approaches for optimizing LLM serving costs and enhancing robotic manipulation capabilities through LLM integration.

RANK_REASON Two distinct research papers are presented, one on LLM serving infrastructure and another on LLM-based robotic control.

Read on arXiv cs.AI →

COVERAGE [4]

  1. arXiv cs.LG TIER_1 · Yixuan Mei, Zikun Li, Zixuan Chen, Shiqi Pan, Mengdi Wu, Xupeng Miao, Zhihao Jia, K. V. Rashmi ·

    Coral: Cost-Efficient Multi-LLM Serving over Heterogeneous Cloud GPUs

    arXiv:2605.04357v1 Announce Type: cross Abstract: The usage of large language models (LLMs) has grown increasingly fragmented, with no single model dominating. Meanwhile, cloud providers offer a wide range of mid-tier and older-generation GPUs that enjoy better availability and d…

  2. arXiv cs.AI TIER_1 · Berk \c{C}i\c{c}ek, Mert K. Er, \"Ozg\"ur S. \"O\u{g}\"uz ·

    CoRAL: Contact-Rich Adaptive LLM-based Control for Robotic Manipulation

    arXiv:2605.02600v1 Announce Type: cross Abstract: While Large Language Models (LLMs) and Vision-Language Models (VLMs) demonstrate remarkable capabilities in high-level reasoning and semantic understanding, applying them directly to contact-rich manipulation remains a challenge d…

  3. arXiv cs.CL TIER_1 · K. V. Rashmi ·

    Coral: Cost-Efficient Multi-LLM Serving over Heterogeneous Cloud GPUs

    The usage of large language models (LLMs) has grown increasingly fragmented, with no single model dominating. Meanwhile, cloud providers offer a wide range of mid-tier and older-generation GPUs that enjoy better availability and deliver comparable performance per dollar to top-ti…

  4. arXiv cs.AI TIER_1 · Özgür S. Öğüz ·

    CoRAL: Contact-Rich Adaptive LLM-based Control for Robotic Manipulation

    While Large Language Models (LLMs) and Vision-Language Models (VLMs) demonstrate remarkable capabilities in high-level reasoning and semantic understanding, applying them directly to contact-rich manipulation remains a challenge due to their lack of explicit physical grounding an…

RELATED ENTITIES

RELATED TOPICS