Related papers: Task-recency bias strikes back: Adapting covarianc…

In continual time series analysis using neural networks, catastrophic forgetting (CF) of previously learned models when training on new data domains has always been a significant challenge. This problem is especially challenging in vehicle…

Continual Learning (CL) methods have traditionally focused on mitigating catastrophic forgetting through gradient-based retraining, an approach ill-suited for deployed agents that must adapt in real time. We introduce our Adaptive Teaching…

Continual learning is a challenging problem in machine learning, especially for image classification tasks with imbalanced datasets. It becomes even more challenging when it involves learning new classes incrementally. One method for…

In federated healthcare systems, Federated Class-Incremental Learning (FCIL) has emerged as a key paradigm, enabling continuous adaptive model learning among distributed clients while safeguarding data privacy. However, in practical…

Deep reinforcement learning (DRL) is one promising approach to teaching robots to perform complex tasks. Because methods that directly reuse the stored experience data cannot follow the change of the environment in robotic problems with a…

The deployment of pre-trained perception models in novel environments often leads to performance degradation due to distributional shifts. Although recent artificial intelligence approaches for metacognition use logical rules to…

Federated learning enables multiple actors to collaboratively train models without sharing private data. Existing algorithms are successful and well-justified in this task when the intended target domain, where the trained model will be…

Diffusion models have demonstrated impressive generative capabilities, but their \textit{exposure bias} problem, described as the input mismatch between training and sampling, lacks in-depth exploration. In this paper, we systematically…

Federated Continual Learning (FCL) has recently emerged as a crucial research area, as data from distributed clients typically arrives as a stream, requiring sequential learning. This paper explores a more practical and challenging FCL…

Generative listwise reranking leverages global context for superior retrieval but is plagued by intrinsic position bias, where models exhibit structural sensitivity to input order independent of relevance. Existing mitigations present a…

Batch Normalization (BN) and its variants has been extensively studied for neural nets in various computer vision tasks, but relatively little work has been dedicated to studying the effect of BN in continual learning. To that end, we…

Current approaches to embodied AI tend to learn policies from expert demonstrations. However, without a mechanism to evaluate the quality of demonstrated actions, they are limited to learning from optimal behaviour, or they risk replicating…

We introduce EfficientCL, a memory-efficient continual pretraining method that applies contrastive learning with novel data augmentation and curriculum learning. For data augmentation, we stack two types of operation sequentially: cutoff…

This study presents a novel approach to Generative Class Incremental Learning (GCIL) by introducing the forgetting mechanism, aimed at dynamically managing class information for better adaptation to streaming data. GCIL is one of the hot…

Continual learning aims to learn new tasks without forgetting previously learned ones. We hypothesize that representations learned to solve each task in a sequence have a shared structure while containing some task-specific properties. We…

Recently, major AI providers such as Google and OpenAI have introduced Finetuning-as-a-Service (FaaS), which allows users to customize Large Language Models (LLMs) using their own data. However, this service is vulnerable to safety…

We design a new adaptive learning algorithm for misclassification cost problems that attempt to reduce the cost of misclassified instances derived from the consequences of various errors. Our algorithm (adaptive cost sensitive learning -…

Continual learning (CL) with Vision-Language Models (VLMs) has overcome the constraints of traditional CL, which only focuses on previously encountered classes. During the CL of VLMs, we need not only to prevent the catastrophic forgetting…

Few-shot class-incremental learning (FSCIL) aims to adapt the model to new classes from very few data (5 samples) without forgetting the previously learned classes. Recent works in many-shot CIL (MSCIL) (using all available training data)…

Class-incremental learning (CIL) aims to continuously introduce novel categories into a classification system without forgetting previously learned ones, thus adapting to evolving data distributions. Researchers are currently focusing on…