Related papers: AHC: Meta-Learned Adaptive Compression for Continu…

The linear memory growth of the KV cache poses a significant bottleneck for LLM inference in long-context tasks. Existing static compression methods often fail to preserve globally important information. Although recent dynamic retrieval…

The primary objective of Continual Anomaly Detection (CAD) is to learn the normal patterns of new tasks under dynamic data distribution assumptions while mitigating catastrophic forgetting. Existing embedding-based CAD approaches…

We introduce and study the problem of Online Continual Compression, where one attempts to simultaneously learn to compress and store a representative dataset from a non i.i.d data stream, while only observing each sample once. A naive…

Modern pre-trained architectures struggle to retain previous information while undergoing continuous fine-tuning on new tasks. Despite notable progress in continual classification, systems designed for complex vision tasks such as detection…

Deep learning has emerged as a leading approach for Automatic Modulation Classification (AMC), demonstrating superior performance over traditional methods. However, vulnerability to adversarial attacks and susceptibility to data…

Large Language Models (LLMs) have become a mainstay for many everyday applications. However, as data evolve their knowledge quickly becomes outdated. Continual learning aims to update LLMs with new information without erasing previously…

Managing heterogeneous datasets that vary in complexity, size, and similarity in continual learning presents a significant challenge. Task-agnostic continual learning is necessary to address this challenge, as datasets with varying…

Mobile edge Large Language Model (LLM) deployments face inherent constraints, such as limited computational resources and network bandwidth. Although Retrieval-Augmented Generation (RAG) mitigates some challenges by integrating external…

Low-rank compression is an important model compression strategy for obtaining compact neural network models. In general, because the rank values directly determine the model complexity and model accuracy, proper selection of layer-wise rank…

Foundation Models (FMs) have become the hallmark of modern AI, however, these models are trained on massive data, leading to financially expensive training. Updating FMs as new data becomes available is important, however, can lead to…

One of the objectives of continual learning is to prevent catastrophic forgetting in learning multiple tasks sequentially, and the existing solutions have been driven by the conceptualization of the plasticity-stability dilemma. However,…

Traditional continual learning methods prioritize knowledge retention and focus primarily on mitigating catastrophic forgetting, implicitly assuming that the data distribution of previously learned tasks remains static. This overlooks the…

Wearable sensors in Internet of Things (IoT) ecosystems increasingly support applications such as remote health monitoring, elderly care, and smart home automation, all of which rely on robust human activity recognition (HAR). Continual…

Recent advances in Model Predictive Control (MPC) leveraging a combination of first-order methods, such as the Alternating Direction Method of Multipliers (ADMM), and offline precomputation and caching of select operations, have excitingly…

Brain-inspired hyperdimensional computing (HDC) has been recently considered a promising learning approach for resource-constrained devices. However, existing approaches use static encoders that are never updated during the learning…

Hyperdimensional Computing (HDC) is an emerging computational framework that mimics important brain functions by operating over high-dimensional vectors, called hypervectors (HVs). In-memory computing implementations of HDC are desirable…

Class-Incremental Learning aims to update a deep classifier to learn new categories while maintaining or improving its accuracy on previously observed classes. Common methods to prevent forgetting previously learned classes include…

The enhanced Deep Hierarchical Video Compression-DHVC 2.0-has been introduced. This single-model neural video codec operates across a broad range of bitrates, delivering not only superior compression performance to representative methods…

For object detection detectors, enhancing model performance hinges on the ability to simultaneously consider inconsistencies across tasks and focus on difficult-to-train samples. Achieving this necessitates incorporating information from…

Visual Autoregressive (VAR) models adopt a next-scale prediction paradigm, offering high-quality content generation with substantially fewer decoding steps. However, existing VAR models suffer from significant attention complexity and…