Related papers: Garbage Collection Techniques for Flash-Resident P…

Retrieval-Augmented Generation (RAG) enhances Large Language Models (LLMs) by grounding generation in external knowledge to improve factuality and reduce hallucinations. Yet most deployments assume a centralized corpus, which is infeasible…

We consider the min-max $r$-gathering problem described as follows: We are given a set of users and facilities in a metric space. We open some of the facilities and assign each user to an opened facility such that each facility has at least…

In modern GPU inference, cache efficiency remains a major bottleneck, and heuristic policies such as \textsc{LRU} can perform far worse than the offline optimum. Existing learning-based caching systems improve hit rates mainly through…

Embedding-based vector search underpins many important applications, such as recommendation and retrieval-augmented generation (RAG). It relies on vector indices to enable efficient search. However, these indices require storing…

Temporal graph representation learning (TGRL) is essential for modeling dynamic systems in real-world networks. However, traditional TGRL methods, despite their effectiveness, often face significant computational challenges and inference…

Large language models (LLMs) are widely used but expensive to run, especially as inference workloads grow. To lower costs, maximizing the request batch size by managing GPU memory efficiently is crucial. While PagedAttention has recently…

For a write request, today flash storage cannot distinguish the logical object it comes from. In such object-oblivious flash devices, concurrent writes from different objects are simply packed in their arrival order to flash memory blocks;…

Cache replacement algorithms are used to optimize the time taken by processor to process the information by storing the information needed by processor at that time and possibly in future so that if processor needs that information, it can…

Federated fine-tuning offers a promising approach for tuning Large Language Models (LLMs) on edge devices while preserving data privacy. However, fine-tuning these models on edge devices remains challenging due to high memory,…

Recent advances in 3D Gaussian Splatting (3DGS) have enabled Simultaneous Localization and Mapping (SLAM) systems to build photorealistic maps. However, these maps lack the open-vocabulary semantic understanding required for advanced…

Virtual-to-physical address translation is a critical performance bottleneck in paging-based virtual memory systems. The Translation Lookaside Buffer (TLB) accelerates address translation by caching frequently accessed mappings, but TLB…

Our paper presents solutions that can significantly improve the delay performance of putting and retrieving data in and out of cloud storage. We first focus on measuring the delay performance of a very popular cloud storage service Amazon…

Since local LLM inference on resource-constrained edge devices imposes a severe performance bottleneck, this paper proposes distributed prompt caching to enhance inference performance by cooperatively sharing intermediate processing states…

Federated Learning (FL) is a collaborative machine learning (ML) framework that combines on-device training and server-based aggregation to train a common ML model among distributed agents. In this work, we propose an asynchronous FL design…

The read channel in Flash memory systems degrades over time because the Fowler-Nordheim tunneling used to apply charge to the floating gate eventually compromises the integrity of the cell because of tunnel oxide degradation. While…

Image galleries provide a rich source of diverse information about a product which can be leveraged across many recommendation and retrieval applications. We study the problem of building a universal image gallery encoder through multi-task…

We present LatentAM, an online 3D Gaussian Splatting (3DGS) mapping framework that builds scalable latent feature maps from streaming RGB-D observations for open-vocabulary robotic perception. Instead of distilling high-dimensional…

With the emergence of Cloud-RAN as one of the dominant architectural solutions for next-generation mobile networks, the reliability and latency on the fronthaul (FH) segment become critical performance metrics for applications such as the…

Efficient continual learning techniques have been a topic of significant research over the last few years. A fundamental problem with such learning is severe degradation of performance on previously learned tasks, known also as catastrophic…

Using task-specific components within a neural network in continual learning (CL) is a compelling strategy to address the stability-plasticity dilemma in fixed-capacity models without access to past data. Current methods focus only on…