相关论文: FastICARL: Fast Incremental Classifier and Represe…

This paper introduces a novel in-context learning (ICL) framework, inspired by large language models (LLMs), for soft-input soft-output channel equalization in coded multiple-input multiple-output (MIMO) systems. The proposed approach…

New categories may be introduced over time, or existing categories may need to be reclassified. Class incremental learning (CIL) is employed for the gradual acquisition of knowledge about new categories while preserving information about…

Imitation Learning (IL) is a widely adopted approach which enables agents to learn from human expert demonstrations by framing the task as a supervised learning problem. However, IL often suffers from causal confusion, where agents…

In cognitive Internet of Things (CIoT) networks, efficient spectrum sharing is essential to address increasing wireless demands. This paper presents a novel deep reinforcement learning (DRL)-based approach for joint cooperative caching and…

The collection of accurate and noise-free data is a crucial part of Internet of Things (IoT)-controlled environments. However, the data collected from various sensors in daily life often suffer from inaccuracies. Additionally,…

In many sequential decision-making problems (e.g., robotics control, game playing, sequential prediction), human or expert data is available containing useful information about the task. However, imitation learning (IL) from a small amount…

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…

A common challenge in continual learning (CL) is catastrophic forgetting, where the performance on old tasks drops after new, additional tasks are learned. In this paper, we propose a novel framework called ReCL to slow down forgetting in…

In-context imitation learning (ICIL) is a new paradigm that enables robots to generalize from demonstrations to unseen tasks without retraining. A well-structured action representation is the key to capturing demonstration information…

Wi-Fi fingerprinting-based indoor localization faces significant challenges in real-world deployments due to domain shifts arising from device heterogeneity and temporal variations within indoor environments. Existing approaches often…

Exemplar-free class-incremental learning (EFCIL) poses significant challenges, primarily due to catastrophic forgetting, necessitating a delicate balance between stability and plasticity to accurately recognize both new and previous…

Numerous indoor localization techniques have been proposed recently to meet the intensive demand for location based service, and Wi-Fi fingerprint-based approaches are the most popular and inexpensive solutions. Among them, one of the main…

With the excellent representation capabilities of Pre-Trained Models (PTMs), remarkable progress has been made in non-rehearsal Class-Incremental Learning (CIL) research. However, it remains an extremely challenging task due to three…

In-context learning (ICL) empowers large language models (LLMs) to tackle new tasks by using a series of training instances as prompts. Since generating the prompts needs to sample from a vast pool of instances and annotate them (e.g., add…

The performance of existing audio deepfake detection frameworks degrades when confronted with new deepfake attacks. Rehearsal-based continual learning (CL), which updates models using a limited set of old data samples, helps preserve prior…

Named entity detection and Parts-of-speech tagging are the key tasks for many NLP applications. Although the current state of the art methods achieved near perfection for long, formal, structured text there are hindrances in deploying these…

Few-shot class-incremental learning (FSCIL) aims to incrementally learn models from a small amount of novel data, which requires strong representation and adaptation ability of models learned under few-example supervision to avoid…

An evolving solution to address hallucination and enhance accuracy in large language models (LLMs) is Retrieval-Augmented Generation (RAG), which involves augmenting LLMs with information retrieved from an external knowledge source, such as…

Large language models (LLMs) have recently enabled remarkable progress in text representation. However, their embeddings are typically high-dimensional, leading to substantial storage and retrieval overhead. Although recent approaches such…

The dynamic expansion architecture is becoming popular in class incremental learning, mainly due to its advantages in alleviating catastrophic forgetting. However, task confusion is not well assessed within this framework, e.g., the…