Today's trend of building ever larger language models (LLMs), while pushing the
performance of natural language processing, adds significant latency to the inference stage …

In this work, for the first time, we demonstrate that computers can automatically learn from
observing the heuristic efforts of the last four decades, stand on the shoulders of the existing …

Previous congestion control (CC) algorithms based on deep reinforcement learning (DRL)
directly adjust flow sending rate to respond to dynamic bandwidth change, resulting in high …

Recent years have witnessed a plethora of learning-based solutions for congestion control
(CC) that demonstrate better performance over traditional TCP schemes. However, they fail …

Previous congestion control (CC) algorithms based on deep reinforcement learning (DRL)
directly adjust flow sending rate to respond to dynamic bandwidth change, resulting in high …

Recent years have witnessed a plethora of learning-based solutions for congestion control
(CC) that demonstrate better performance over traditional TCP schemes. However, they fail …

Low Latency, Low Loss, and Scalable Throughput (L4S), as an emerging router-queue
management technique, has seen steady deployment in the industry. An L4S-enabled router …

Amid the rapid advancements in large machine learning (ML) models, universities
worldwide are investing substantial funds and efforts into GPU clusters. However, managing …

Distributed edge inference emerges to be a promising paradigm to speed up inference.
Previous works make physical partitions on CNNs to realize it, but there are the following …

This paper presents a lightweight in-kernel design of RNN-CUBIC, a loss-based machine
learning (ML)-based congestion control algorithm (CCA), which optimizes the TCP sending …