Related papers: Are Your Epochs Too Epic? Batch Free Can Be Harmfu…

Continual learning methods are known to suffer from catastrophic forgetting, a phenomenon that is particularly hard to counter for methods that do not store exemplars of previous tasks. Therefore, to reduce potential drift in the feature…

Erasure coding techniques are getting integrated in networked distributed storage systems as a way to provide fault-tolerance at the cost of less storage overhead than traditional replication. Redundancy is maintained over time through…

Retrieval, the initial stage of a recommendation system, is tasked with down-selecting items from a pool of tens of millions of candidates to a few thousands. Embedding Based Retrieval (EBR) has been a typical choice for this problem,…

The widespread adoption of Electronic Health Records (EHR) has significantly increased the amount of available healthcare data. This has allowed models inspired by Natural Language Processing (NLP) and Computer Vision, which scale…

Entity resolution (ER) is a key data integration problem. Despite the efforts in 70+ years in all aspects of ER, there is still a high demand for democratizing ER - humans are heavily involved in labeling data, performing feature…

Retrieval-Augmented Generation (RAG) systems enhance the performance of large language models (LLMs) by incorporating supplementary retrieved documents, enabling more accurate and context-aware responses. However, integrating these external…

The memory hierarchy has a high impact on the performance and power consumption in the system. Moreover, current embedded systems, included in mobile devices, are specifically designed to run multimedia applications, which are memory…

The main purpose of this work is the one of providing an efficient scheme for constructing reduced interpolation models for kernel bases. In literature such problem is mainly addressed via the well-established knot insertion or knot removal…

Automatically repairing software issues remains a fundamental challenge at the intersection of software engineering and AI. Although recent advances in Large Language Models (LLMs) have demonstrated potential for repository-level repair…

Large Language Model-based generative recommendation (LLMRec) has achieved notable success, but it suffers from high inference latency due to massive computational overhead and memory pressure of KV Cache. Existing KV Cache reduction…

Dense retrieval techniques employ pre-trained large language models to build a high-dimensional representation of queries and passages. These representations compute the relevance of a passage w.r.t. to a query using efficient similarity…

Compared with the fixed-run designs, the sequential adaptive designs (SAD) are thought to be more efficient and effective. Efficient global optimization (EGO) is one of the most popular SAD methods for expensive black-box optimization…

One of the major bottlenecks for efficient deployment of neural network based recommendation systems is the memory footprint of their embedding tables. Although many neural network based recommendation systems could benefit from the faster…

We present a family of safe memory reclamation schemes, Hyaline, which are fast, scalable, and transparent to the underlying lock-free data structures. Hyaline is based on reference counting - considered impractical for memory reclamation…

In Continual Learning, a Neural Network is trained on a stream of data whose distribution shifts over time. Under these assumptions, it is especially challenging to improve on classes appearing later in the stream while remaining accurate…

Applications in the AI and HPC fields require much memory capacity, and the amount of energy consumed by main memory of server machines is ever increasing. Energy consumption of main memory can be greatly reduced by applying approximate…

For deep neural network accelerators, memory movement is both energetically expensive and can bound computation. Therefore, optimal mapping of tensors to memory hierarchies is critical to performance. The growing complexity of neural…

Retrieving the correct set of files from a large codebase is a crucial step in Automated Program Repair (APR). High recall is necessary to ensure that the relevant files are included, but simply increasing the number of retrieved files…

Inefficient data transfer between computation and memory inspired emerging processing-in-memory (PIM) technologies. Many PIM solutions enable storage and processing using memristors in a crossbar-array structure, with techniques such as…

Reliable abstention is critical for retrieval-augmented generation (RAG) systems, particularly in safety-critical domains such as women's health, where incorrect answers can lead to harm. We present an energy-based model (EBM) that learns a…