Related papers: Routing without Forgetting
We study Latent Recurrent Transformer (LRT), a lightweight augmentation of autoregressive transformers that reuses a high-level source-layer hidden state from the previous token as recurrent memory for the next token. Because this source…
This paper studies the problem of continual learning in an open-world scenario, referred to as Open-world Continual Learning (OwCL). OwCL is increasingly rising while it is highly challenging in two-fold: i) learning a sequence of tasks…
Inspired by the \emph{Well-initialized Lottery Ticket Hypothesis (WLTH)}, we introduce Soft-Transformer (Soft-TF), a parameter-efficient framework for continual learning that leverages soft, real-valued subnetworks over a frozen pre-trained…
Machine learning models deployed in real-world settings must operate under evolving data distributions and constrained computational resources. This challenge is particularly acute in non-stationary domains such as energy time series,…
Federated learning enables cooperative training among massively distributed clients by sharing their learned local model parameters. However, with increasing model size, deploying federated learning requires a large communication bandwidth,…
Catastrophic forgetting(CF) is a significant challenge in continual learning (CL). In regularization-based approaches to mitigate CF, modifications to important training parameters are penalized in subsequent tasks using an appropriate loss…
Residual connections have been proposed as an architecture-based inductive bias to mitigate the problem of exploding and vanishing gradients and increased task performance in both feed-forward and recurrent networks (RNNs) when trained with…
Unlearning in large foundation models (e.g., LLMs) is essential for enabling dynamic knowledge updates, enforcing data deletion rights, and correcting model behavior. However, existing unlearning methods often require full-model fine-tuning…
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…
Offline reinforcement learning (RL) enables learning control policies by utilizing only prior experience, without any online interaction. This can allow robots to acquire generalizable skills from large and diverse datasets, without any…
With the exponential growth of smart devices connected to wireless networks, data production is increasing rapidly, requiring machine learning (ML) techniques to unlock its value. However, the centralized ML paradigm raises concerns over…
Machine learning applied to architecture design presents a promising opportunity with broad applications. Recent deep reinforcement learning (DRL) techniques, in particular, enable efficient exploration in vast design spaces where…
Standard Transformers excel at semantic modeling but struggle with rigid sequential logic and state tracking. Theoretical work establishes that self-attention is limited to $\AC^0$ (under hard attention) or $\TC^0$ (under soft attention),…
Deep Reinforcement Learning has enabled the learning of policies for complex tasks in partially observable environments, without explicitly learning the underlying model of the tasks. While such model-free methods achieve considerable…
Online continual learning requires the models to learn from constant, endless streams of data. While significant efforts have been made in this field, most were focused on mitigating the catastrophic forgetting issue to achieve better…
Interacting with the actual environment to acquire data is often costly and time-consuming in robotic tasks. Model-based offline reinforcement learning (RL) provides a feasible solution. On the one hand, it eliminates the requirements of…
The ability of neural networks (NNs) to learn and remember multiple tasks sequentially is facing tough challenges in achieving general artificial intelligence due to their catastrophic forgetting (CF) issues. Fortunately, the latest OWM…
The rapid proliferation of wireless devices makes robust identity authentication essential. Radio Frequency Fingerprinting (RFF) exploits device-specific, hard-to-forge physical-layer impairments for identification, and is promising for IoT…
Multimodal Large Language Models (MLLMs) struggle with continual learning, often suffering from catastrophic forgetting when adapting to sequential tasks. We introduce a routing-based architecture that integrates new capabilities while…
Task-free continual learning (CL) aims to learn a non-stationary data stream without explicit task definitions and not forget previous knowledge. The widely adopted memory replay approach could gradually become less effective for long data…