Related papers: TensorHub: Scalable and Elastic Weight Transfer fo…

This paper presents a novel and sustainable approach for improving beam selection in 5G and beyond networks using transfer learning and Reinforcement Learning (RL). Traditional RL-based beam selection models require extensive training time…

Low-rank adapters (LoRAs) are a parameter-efficient finetuning technique that injects trainable low-rank matrices into pretrained models to adapt them to new tasks. Mixture-of-LoRAs models expand neural networks efficiently by routing each…

Modern AI models are growing rapidly in size and redundancy, leading to significant storage and distribution challenges in model hubs. We present TStore, a tensor-centric system for reducing storage overhead through fine-grained…

Passive resistive random access memory (ReRAM) crossbar arrays, a promising emerging technology used for analog matrix-vector multiplications, are far superior to their active (1T1R) counterparts in terms of the integration density.…

Reinforcement Learning (RL) has become the most effective post-training approach for improving the capabilities of Large Language Models (LLMs). In practice, because of the high demands on latency and memory, it is particularly challenging…

Scientific problems require resolving multi-scale phenomena across different resolutions and learning solution operators in infinite-dimensional function spaces. Neural operators provide a powerful framework for this, using…

Resistive memory (RM) based neuromorphic systems can emulate synaptic plasticity and thus support continual learning, but they generally lack biologically inspired mechanisms for active forgetting, which are critical for meeting modern data…

The recursive least-squares (RLS) algorithm is one of the most well-known algorithms used in adaptive filtering, system identification and adaptive control. Its popularity is mainly due to its fast convergence speed, which is considered to…

Due to the highly variable execution context in which edge services run, adapting their behavior to the execution context is crucial to comply with their requirements. However, adapting service behavior is a challenging task because it is…

Model merging aims to combine multiple fine-tuned models into a single set of weights that performs well across all source tasks. While prior work has shown that merging can approximate the performance of individual fine-tuned models for…

Recurrent Neural Network (RNN) are a popular choice for modeling temporal and sequential tasks and achieve many state-of-the-art performance on various complex problems. However, most of the state-of-the-art RNNs have millions of parameters…

In large-scale reinforcement learning (RL) systems with decoupled Trainer-Rollout execution, the Trainer must regularly synchronize policy weights to the Rollout side to limit policy staleness. When inter-node bandwidth is abundant, such…

The rapid growth of deploying machine learning (ML) models within embedded systems on a chip (SoCs) has led to transformative shifts in fields like healthcare and autonomous vehicles. One of the primary challenges for training such embedded…

Distributed inference of large language models (LLMs) using tensor parallelism can introduce communication overheads of $20$% even over GPUs connected via NVLink, a high-speed GPU interconnect. Several techniques have been proposed to…

Smart and connected mobility systems rely on 5G edge infrastructure to support real-time communication, control, and service differentiation. Achieving this requires adaptive resource management mechanisms that can react to rapidly changing…

Collaborative edge computing uses edge nodes in different locations to execute tasks, necessitating dynamic task offloading decisions to maintain low latency and high reliability, especially under unpredictable node failures. Although deep…

The paradigm shift in the electric power grid necessitates a revisit of existing control methods to ensure the grid's security and resilience. In particular, the increased uncertainties and rapidly changing operational conditions in power…

Pre-trained language models (PLMs) demonstrate remarkable intelligence but struggle with emerging tasks unseen during training in real-world applications. Training separate models for each new task is usually impractical. Multi-task…

An indoor, real-time location system (RTLS) can benefit both hospitals and patients by improving clinical efficiency through data-driven optimization of procedures. Bluetooth-based RTLS systems are cost-effective but lack accuracy and…

Table structure recognition (TSR) aims at extracting tables in images into machine-understandable formats. Recent methods solve this problem by predicting the adjacency relations of detected cell boxes or learning to directly generate the…