Related papers: MorphingDB: A Task-Centric AI-Native DBMS for Mode…

Model merging has attracted attention as an effective path toward multi-task adaptation by integrating knowledge from multiple task-specific models. Among existing approaches, dynamic merging mitigates performance degradation caused by…

Transformers have reached remarkable success in sequence modeling. However, these models have efficiency issues as they need to store all the history token-level representations as memory. We present Memformer, an efficient neural network…

The article addresses the problem of storing data in extreme environmental conditions with limited computing resources and memory. There is a requirement to create portable, fault-tolerant, modular database management systems (DBMS) that…

In today world, organizations like Google, Yahoo, Amazon, Facebook etc. are facing drastic increase in data. This leads to the problem of capturing, storing, managing and analyzing terabytes or petabytes of data, stored in multiple formats,…

Artificial intelligence, and particularly machine learning (ML), is increasingly developed and deployed to support healthcare in a variety of settings. However, clinical decision support (CDS) technologies based on ML need to be portable if…

A new emerging class of parallel database management systems (DBMS) is designed to take advantage of the partitionable workloads of on-line transaction processing (OLTP) applications. Transactions in these systems are optimized to execute…

Modern approach to artificial intelligence (AI) aims to design algorithms that learn directly from data. This approach has achieved impressive results and has contributed significantly to the progress of AI, particularly in the sphere of…

Recent trends in information management involve the periodic transcription of data onto secondary devices in a networked environment, and the proper scheduling of these transcriptions is critical for efficient data management. To assist in…

Alongside the continuous process of improving AI performance through the development of more sophisticated models, researchers have also focused their attention to the emerging concept of data-centric AI, which emphasizes the important role…

Supervised learning models are typically trained on a single dataset and the performance of these models rely heavily on the size of the dataset, i.e., amount of data available with the ground truth. Learning algorithms try to generalize…

The key to success in machine learning (ML) is the use of effective data representations. Traditionally, data representations were hand-crafted. Recently it has been demonstrated that, given sufficient data, deep neural networks can learn…

Transformative innovations in model architectures have introduced hierarchical embedding augmentation as a means to redefine the representation of tokens through multi-level semantic structures, offering enhanced adaptability to complex…

Many problems in sequential decision making and stochastic control often have natural multiscale structure: sub-tasks are assembled together to accomplish complex goals. Systematically inferring and leveraging hierarchical structure,…

Deep learning has proven to be a highly effective tool for a wide range of applications, significantly when leveraging the power of multi-loss functions to optimize performance on multiple criteria simultaneously. However, optimal selection…

Predictive modeling over relational databases (RDBs) powers applications, yet remains challenging due to capturing both cross-table dependencies and complex feature interactions. Relational Deep Learning (RDL) methods automate feature…

Deep learning recommendation models have grown to the terabyte scale. Traditional serving schemes--that load entire models to a single server--are unable to support this scale. One approach to support this scale is with distributed serving,…

Real-world AI/ML workflows often apply inference computations to feature vectors joined from multiple datasets. To avoid the redundant AI/ML computations caused by repeated data records in the join's output, factorized ML has been proposed…

With the recent proliferation of sensor data, there is an increasing need for the efficient evaluation of analytical queries over multiple sensor datasets. The magnitude of such datasets makes exact query answering infeasible, leading…

There are massive amounts of textual data residing in databases, valuable for many machine learning (ML) tasks. Since ML techniques depend on numerical input representations, word embeddings are increasingly utilized to convert symbolic…

Catastrophic forgetting poses a substantial challenge for managing intelligent agents controlled by a large model, causing performance degradation when these agents face new tasks. In our work, we propose a novel solution - the Progressive…