Related papers: Productively Deploying Emerging Models on Emerging…

The exponential growth in the size and complexity of Large Language Models (LLMs) has introduced unprecedented challenges in their deployment and operational management. Traditional MLOps approaches often fail to efficiently handle the…

Large language models have emerged as a promising approach towards achieving general-purpose AI agents. The thriving open-source LLM community has greatly accelerated the development of agents that support human-machine dialogue interaction…

Manifold learning (ML) aims to seek low-dimensional embedding from high-dimensional data. The problem is challenging on real-world datasets, especially with under-sampling data, and we find that previous methods perform poorly in this case.…

The traditional Machine Learning (ML) methodology requires to fragment the development and experimental process into disconnected iterations whose feedback is used to guide design or tuning choices. This methodology has multiple efficiency…

5G technology enhances industries with high-speed, reliable, low-latency communication, revolutionizing mobile broadband and supporting massive IoT connectivity. With the increasing complexity of applications on User Equipment (UE),…

As large language models (LLMs) have shown great success in many tasks, they are used in various applications. While a lot of works have focused on the efficiency of single-LLM application (e.g., offloading, request scheduling, parallelism…

Molecule design is a multifaceted approach that leverages computational methods and experiments to optimize molecular properties, fast-tracking new drug discoveries, innovative material development, and more efficient chemical processes.…

Large Language Models (LLMs) have scaled rapidly in size and complexity, requiring increasingly intricate parallelism for distributed training, such as 3D parallelism. This sophistication motivates a shift toward simpler, more debuggable…

Deep Learning (DL) model-based AI services are increasingly offered in a variety of predictive analytics services such as computer vision, natural language processing, speech recognition. However, the quality of the DL models can degrade…

[Context] Systems incorporating Machine Learning (ML) models, often called ML-enabled systems, have become commonplace. However, empirical evidence on how ML-enabled systems are engineered in practice is still limited, especially for…

Machine learning (ML) is increasingly applied to optimize system performance in tasks such as resource management and network simulation. Unlike traditional ML tasks (e.g., image classification), networked systems often operate in…

The conventional deep learning paradigm often involves training a deep model on a server and then deploying the model or its distilled ones to resource-limited edge devices. Usually, the models shall remain fixed once deployed (at least for…

Transition Matching (TM) is an emerging paradigm for generative modeling that generalizes diffusion and flow-matching models as well as continuous-state autoregressive models. TM, similar to previous paradigms, gradually transforms noise…

Despite the exceptional reasoning capabilities of Multimodal Large Language Models (MLLMs), their adaptation into universal embedding models is significantly impeded by task conflict. To address this, we propose TSEmbed, a universal…

In-context learning (ICL) has emerged as a new approach to various natural language processing tasks, utilizing large language models (LLMs) to make predictions based on context that has been supplemented with a few examples or…

Existing work in continual learning (CL) focuses on mitigating catastrophic forgetting, i.e., model performance deterioration on past tasks when learning a new task. However, the training efficiency of a CL system is under-investigated,…

Large Language Models (LLMs) have shown remarkable prowess in text generation, yet producing long-form, factual documents grounded in extensive external knowledge bases remains a significant challenge. Existing "top-down" methods, which…

Benefiting from expanding cloud infrastructure, deep neural networks (DNNs) today have increasingly high performance when trained in the cloud. Researchers spend months of effort competing for an extra few percentage points of model…

When deploying machine learning (ML) applications, the automated allocation of computing resources-commonly referred to as autoscaling-is crucial for maintaining a consistent inference time under fluctuating workloads. The objective is to…

Large language models (LLMs) exhibit remarkable capabilities across diverse tasks, yet aligning them efficiently and effectively with human expectations remains a critical challenge. This thesis advances LLM alignment by introducing novel…