5 papers
Kairos: A Scalable Serving System for Physical AI
Yinwei Dai, Ganesh Ananthanarayanan, Landon Cox +3
Physical AI is experiencing rapid growth with frontier foundation models increasing its capabilities across general environments. Physical AI tasks are characterized by inference p…
Offload or Overload: A Platform Measurement Study of Mobile Robotic Manipulation Workloads
Sara Pohland, Xenofon Foukas, Ganesh Ananthanarayanan +4
Mobile robotic manipulation--the ability of robots to navigate spaces and interact with objects--is a core capability of physical AI. Foundation models have led to breakthroughs in…
Distributed AI Platform for the 6G RAN
Ganesh Ananthanarayanan, Matthew Balkwill, Xenofon Foukas +4
Cellular Radio Access Networks (RANs) are rapidly evolving towards 6G, driven by the need to reduce costs and introduce new revenue streams for operators and enterprises. In this c…
Hades: Hierarchical Adaptable Decoding for Efficient and Elastic vRAN
Jincao Zhu, Kobus Van Der Merwe, Xenofon Foukas +1
In cellular networks, virtualized Radio Access Networks (vRANs) enable replacing traditional specialized hardware at cell sites with software running on commodity servers distribut…
AutoSpec: Automated Generation of Neural Network Specifications
Shuowei Jin, Francis Y. Yan, Taobo Liao +5
The increasing adoption of neural networks in learning-augmented systems highlights the growing need for model safety and robustness, especially in safety-critical domains. While r…