Related papers: Memory-Integrated Reconfigurable Adapters: A Unifi…

Learning models of artificial intelligence can nowadays perform very well on a large variety of tasks. However, in practice different task environments are best handled by different learning models, rather than a single, universal,…

Continual learning allows the system to learn and adapt to new tasks while retaining the knowledge acquired from previous tasks. However, deep learning models suffer from catastrophic forgetting of knowledge learned from earlier tasks while…

In many real-world scenarios, data to train machine learning models become available over time. However, neural network models struggle to continually learn new concepts without forgetting what has been learnt in the past. This phenomenon…

Biological neural networks are capable of recruiting different sets of neurons to encode different memories. However, when training artificial neural networks on a set of tasks, typically, no mechanism is employed for selectively producing…

Inspired by the human learning and memory system, particularly the interplay between the hippocampus and cerebral cortex, this study proposes a dual-learner framework comprising a fast learner and a meta learner to address continual…

LLM-based agents have been extensively applied across various domains, where memory stands out as one of their most essential capabilities. Previous memory mechanisms of LLM-based agents are manually predefined by human experts, leading to…

Lifelong Person Re-Identification (LReID) extends traditional ReID by requiring systems to continually learn from non-overlapping datasets across different times and locations, adapting to new identities while preserving knowledge of…

Continual learning (CL) aims to continually accumulate knowledge from a non-stationary data stream without catastrophic forgetting of learned knowledge, requiring a balance between stability and adaptability. Relying on the generalizable…

Lifelong learning aims to create AI systems that continuously and incrementally learn during a lifetime, similar to biological learning. Attempts so far have met problems, including catastrophic forgetting, interference among tasks, and the…

Continual RL requires an agent to learn new tasks without forgetting previous ones, while improving on both past and future tasks. The most common approaches use model-free algorithms and replay buffers can help to mitigate catastrophic…

Making neural networks remember over the long term has been a longstanding issue. Although several external memory techniques have been introduced, most focus on retaining recent information in the short term. Regardless of its importance,…

This paper addresses the challenge of creating a neural architecture for very long sequences that requires constant time for processing new information at each time step. Our approach, Associative Recurrent Memory Transformer (ARMT), is…

Continual learning in large language models (LLMs) typically encounters the critical challenge of catastrophic forgetting, where previously acquired knowledge deteriorates upon exposure to new data. While techniques like replay buffers and…

Humans and animals show remarkable learning efficiency, adapting to new environments with minimal experience. This capability is not well captured by standard reinforcement learning algorithms that rely on incremental value updates. Rapid…

Online reinforcement learning agents are currently able to process an increasing amount of data by converting it into a higher order value functions. This expansion of the information collected from the environment increases the agent's…

Parameter efficient adaptation methods have become a key mechanism to train large pre-trained models for downstream tasks. However, their per-task parameter overhead is considered still high when the number of downstream tasks to adapt for…

Although deep neural networks perform extremely well in controlled environments, they fail in real-world scenarios where data isn't available all at once, and the model must adapt to a new data distribution that may or may not follow the…

Artificial neural networks (ANNs) exhibit a narrow scope of expertise on stationary independent data. However, the data in the real world is continuous and dynamic, and ANNs must adapt to novel scenarios while also retaining the learned…

Large transformer models, trained on diverse datasets, have demonstrated impressive few-shot performance on previously unseen tasks without requiring parameter updates. This capability has also been explored in Reinforcement Learning (RL),…

Recent Vision-Language Models (VLMs) exhibit strong perceptual reasoning abilities, yet they often struggle to adapt efficiently when encountering novel tasks at test time. In contrast, humans leverage the metacognitive model with memory,…