相关论文: MUSE: Multi-Tenant Model Serving With Seamless Mod…
Indexes are critical for efficient data retrieval and updates in modern databases. Recent advances in machine learning have led to the development of learned indexes, which model the cumulative distribution function of data to predict…
Measuring Mutual Information (MI) between high-dimensional, continuous, random variables from observed samples has wide theoretical and practical applications. Recent work, MINE (Belghazi et al. 2018), focused on estimating tight…
Computation offloading has become a popular solution to support computationally intensive and latency-sensitive applications by transferring computing tasks to mobile edge servers (MESs) for execution, which is known as mobile/multi-access…
Automated decision systems increasingly rely on human oversight to ensure accuracy in uncertain cases. This paper presents a practical framework for optimizing such human-in-the-loop classification systems using a double-threshold policy.…
Pairwise dot product-based attention allows Transformers to exchange information between tokens in an input-dependent way, and is key to their success across diverse applications in language and vision. However, a typical Transformer model…
Scalable decentralized optimization in large-scale systems hinges on efficient communication. A common way to reduce communication overhead is to perform multiple local updates between two communication rounds, as in federated learning.…
Mixture-of-Experts (MoE) models have shown remarkable capability in instruction tuning, especially when the number of tasks scales. However, previous methods simply merge all training tasks (e.g. creative writing, coding, and mathematics)…
We propose a new approach to the semiparametric analysis of panel data binary choice models with fixed effects and dynamics (lagged dependent variables). The model we consider has the same random utility framework as in Honore and…
Automated scoring of written constructed responses typically relies on separate models per task, straining computational resources, storage, and maintenance in real-world education settings. We propose UniMoE-Guided, a knowledge-distilled…
The MISE Project (Mediation Information System Engineering) aims at providing collaborating organizations with a Mediation Information System (MIS) in charge of supporting interoperability of a collaborative network. MISE proposes an…
To address the modality imbalance caused by data heterogeneity, existing multi-modal learning (MML) approaches primarily focus on balancing this difference from the perspective of optimization objectives. However, almost all existing…
In many applications of machine learning (ML), updates are performed with the goal of enhancing model performance. However, current practices for updating models rely solely on isolated, aggregate performance analyses, overlooking important…
Autonomous agents often require multiple strategies to solve complex tasks, but determining when to switch between strategies remains challenging. This research introduces a reinforcement learning technique to learn switching thresholds…
The robust application of wireless sensor networks has increased during the past decade due to the potential use of wireless nodes in transmission of information by decreasing latency for surveillance and monitoring. The study proposes an…
Cloud systems have rapidly expanded worldwide in the last decade, shifting computational tasks to cloud servers where clients submit their requests. Among cloud workloads, latency-critical applications -- characterized by high-percentile…
Adopting serverless computing to edge networks benefits end-users from the pay-as-you-use billing model and flexible scaling of applications. This paradigm extends the boundaries of edge computing and remarkably improves the quality of…
Network management on multi-tenant container-based data centers has critical impact on performance. Tenants encapsulate applications in containers abstracting away details on hosting infrastructures, and entrust data centers management…
In the era of large language models, model merging is a promising way to combine multiple task-specific models into a single multitask model without extra training. However, two challenges remain: (a) interference between different models…
The rapid adoption of complex Artificial Intelligence (AI) and Machine Learning (ML) models has led to their characterization as black boxes due to the difficulty of explaining their internal decision-making processes. This lack of…
Reward-based fine-tuning steers a pretrained diffusion or flow-based generative model toward higher-reward samples while remaining close to the pretrained model. Although existing methods are derived from different perspectives, we show…