Related papers: Analysis of Trim Commands on Overprovisioning and …

Recommendation systems must continuously adapt to evolving user behavior, yet the volume of data generated in large-scale streaming environments makes frequent full retraining impractical. This work investigates how targeted data selection…

Multi-sample aggregation strategies, such as majority voting and best-of-N sampling, are widely used in contemporary large language models (LLMs) to enhance predictive accuracy across various tasks. A key challenge in this process is…

Output-length prediction is important for efficient LLM serving, as it directly affects batching, memory reservation, and scheduling. For prompt-only length prediction, most existing methods use a one-shot sampled length as the label,…

This paper summarizes the idea of Adaptive-Latency DRAM (AL-DRAM), which was published in HPCA 2015, and examines the work's significance and future potential. AL-DRAM is a mechanism that optimizes DRAM latency based on the DRAM module and…

Benefiting from prompt tuning, recent years have witnessed the promising performance of pre-trained vision-language models, e.g., CLIP, on versatile downstream tasks. In this paper, we focus on a particular setting of learning adaptive…

Short-term load forecasting is one of the crucial sections in smart grid. Precise forecasting enables system operators to make reliable unit commitment and power dispatching decisions. With the advent of big data, a number of artificial…

This paper addresses developing cost-effective strategies to respond to excessive demand in the service network design problem in a multi-period setting. The common assumption states that the capacity of freight carriers' assets is capable…

Recent advances in generative modelling have led many to see synthetic data as the go-to solution for a range of problems around data access, scarcity, and under-representation. In this paper, we study three prominent use cases: (1) Sharing…

As research and deployment of AI grows, the computational burden to support and sustain its progress inevitably does too. To train or fine-tune state-of-the-art models in NLP, computer vision, etc., some form of AI hardware acceleration is…

This thesis concerns sequential-access data compression, i.e., by algorithms that read the input one or more times from beginning to end. In one chapter we consider adaptive prefix coding, for which we must read the input character by…

Distribution feeder and load model reduction methods are essential for maintaining a good tradeoff between accurate representation of grid behavior and reduced computational complexity in power system studies. An effective algorithm to…

This paper considers a demand response agent that must find a near-optimal sequence of decisions based on sparse observations of its environment. Extracting a relevant set of features from these observations is a challenging task and may…

Computations, where the number of results is much smaller than the input data and are produced through some sort of accumulation, are called Reductions. Reductions appear in many scientific applications. Usually, reductions admit an…

Reasoning large language models (LLMs) excel in complex tasks, which has drawn significant attention to reinforcement learning (RL) for LLMs. However, existing approaches allocate an equal number of rollouts to all questions during the RL…

In this thesis, we study the downlink multiuser scheduling and power allocation problem for systems with simultaneous wireless information and power transfer (SWIPT). In the first part of the thesis, we focus on multiuser scheduling. We…

The proliferation of GPS-enabled devices has led to the development of numerous location-based services. These services need to process massive amounts of spatial data in real-time. The current scale of spatial data cannot be handled using…

Industrial Non-Intrusive Load Monitoring (NILM) is limited by the scarcity of high-quality datasets and the complex variability of industrial energy consumption patterns. To address data scarcity and privacy issues, we introduce the…

The goal of Optimal Transmission Switching (OTS) problem for power systems is to identify a topology of the power grid that minimizes the cost of the system operation while satisfying the operational and physical constraints. Among the most…

Packet trimming is a primitive that has been proposed for datacenter networks: to minimize latency, switches run small queues; when the queue overflows, rather than dropping packets the switch trims off the packet payload and either…

Machine learning models for text classification often excel on in-distribution (ID) data but struggle with unseen out-of-distribution (OOD) inputs. Most techniques for improving OOD robustness are not applicable to settings where the model…