Related papers: METL: a modern ETL pipeline with a dynamic mapping…
Machine learning has shown tremendous potential for improving the capabilities of network traffic analysis applications, often outperforming simpler rule-based heuristics. However, ML-based solutions remain difficult to deploy in practice.…
Diffusion Multi-modal Large Language Models (dMLLMs) have recently emerged as a novel architecture unifying image generation and understanding. However, developing effective and efficient Test-Time Scaling (TTS) methods to unlock their full…
Diffusion and flow-based models have become the de facto approaches for generating continuous data, e.g., in domains such as images and videos. Their success has attracted growing interest in applying them to language modeling. Unlike their…
The embedded topic model (ETM) is a widely used approach that assumes the sampled document-topic distribution conforms to the logistic normal distribution for easier optimization. However, this assumption oversimplifies the real…
Topic modeling is a key component in unsupervised learning, employed to identify topics within a corpus of textual data. The rapid growth of social media generates an ever-growing volume of textual data daily, making online topic modeling…
What is a systematic way to efficiently apply a wide spectrum of advanced ML programs to industrial scale problems, using Big Models (up to 100s of billions of parameters) on Big Data (up to terabytes or petabytes)? Modern parallelization…
Diffusion language models (DLMs) enable parallel, non-autoregressive text generation, yet existing DLM mixture-of-experts (MoE) models inherit token-choice (TC) routing from autoregressive systems, leading to load imbalance and rigid…
We study the AutoML problem of automatically configuring machine learning pipelines by jointly selecting algorithms and their appropriate hyper-parameters for all steps in supervised learning pipelines. This black-box (gradient-free)…
Autonomous driving systems require real-time environmental perception to ensure user safety and experience. Streaming perception is a task of reporting the current state of the world, which is used to evaluate the delay and accuracy of…
Modern machine learning accelerators are designed to efficiently execute deep neural networks (DNNs) by optimizing data movement, memory hierarchy, and compute throughput. However, emerging DNN models such as large language models, state…
5G communication brings substantial improvements in the quality of service provided to various applications by achieving higher throughput and lower latency. However, interactive multimedia applications (e.g., ultra high definition video…
Mobile mapping, in particular, Mobile Lidar Scanning (MLS) is increasingly widespread to monitor and map urban scenes at city scale with unprecedented resolution and accuracy. The resulting point cloud sampling of the scene geometry can be…
Today, massive amounts of streaming data from smart devices need to be analyzed automatically to realize the Internet of Things. The Complex Event Processing (CEP) paradigm promises low-latency pattern detection on event streams. However,…
Distributed networks and real-time systems are becoming the most important components for the new computer age, the Internet of Things (IoT), with huge data streams or data sets generated from sensors and data generated from existing legacy…
Unstructured text has long been difficult to automatically analyze at scale. Large language models (LLMs) now offer a way forward by enabling {\em semantic data processing}, where familiar data processing operators (e.g., map, reduce,…
Machine Learning models are being utilized extensively to drive recommender systems, which is a widely explored topic today. This is especially true of the music industry, where we are witnessing a surge in growth. Besides a large chunk of…
The Internet of Things generates massive data streams, with edge computing emerging as a key enabler for online IoT applications and 5G networks. Edge solutions facilitate real-time machine learning inference, but also require continuous…
EDML is a recently proposed algorithm for learning MAP parameters in Bayesian networks. In this paper, we present a number of new advances and insights on the EDML algorithm. First, we provide the multivalued extension of EDML, originally…
The proliferation of emergent network applications (e.g., AR/VR, telesurgery, real-time communications) is increasing the difficulty of managing modern communication networks. These applications typically have stringent requirements (e.g.,…
Being able to effectively read scientific plots, or chart understanding, is a central part toward building effective agents for science. However, existing multimodal large language models (MLLMs), especially open-source ones, are still…