Related papers: Dynamical Adapter Fusion: Constructing A Global Ad…

Recent advancements in on-device training for deep neural networks have underscored the critical need for efficient activation compression to overcome the memory constraints of mobile and edge devices. As activations dominate memory usage…

Domain-Adaptive Pre-training (DAP) has recently gained attention for its effectiveness in fine-tuning pre-trained models. Building on this, continual DAP has been explored to develop pre-trained models capable of incrementally incorporating…

We present the ADaptive Adversarial Imitation Learning (ADAIL) algorithm for learning adaptive policies that can be transferred between environments of varying dynamics, by imitating a small number of demonstrations collected from a single…

Lifelong Person Re-identification (LReID) suffers from a key challenge in preserving old knowledge while adapting to new information. The existing solutions include rehearsal-based and rehearsal-free methods to address this challenge.…

Learning domain adaptive policies that can generalize to unseen transition dynamics, remains a fundamental challenge in learning-based control. Substantial progress has been made through domain representation learning to capture…

Vision-language-action (VLA) models provide a promising paradigm for scalable robotic manipulation, yet their reliance on success-only behavioral cloning leaves them brittle; lacking corrective training signals, minor execution errors…

Domain adaptation (DA) enables knowledge transfer from a labeled source domain to an unlabeled target domain by reducing the cross-domain distribution discrepancy. Most prior DA approaches leverage complicated and powerful deep neural…

Continual learning (CL) is essential for Large Language Models (LLMs) to adapt to evolving real-world demands, yet they are susceptible to catastrophic forgetting (CF). While traditional CF solutions rely on expensive data rehearsal, recent…

Continual learning is an essential capability of human cognition, yet it poses significant challenges for current deep learning models. The primary issue is that new knowledge can interfere with previously learned information, causing the…

Incremental Learning (IL) aims to accumulate knowledge from sequential input tasks while overcoming catastrophic forgetting. Existing IL methods typically assume that an incoming task has only increments of classes or domains, referred to…

We present a parameter-efficient method for continual video question-answering (VidQA) learning. Our method, named DAM, uses the proposed Dynamic Adapter Merging to (i) mitigate catastrophic forgetting, (ii) enable efficient adaptation to…

We propose Adapter Merging with Centroid Prototype Mapping (ACMap), an exemplar-free framework for class-incremental learning (CIL) that addresses both catastrophic forgetting and scalability. While existing methods involve a trade-off…

Approaches to continual learning aim to successfully learn a set of related tasks that arrive in an online manner. Recently, several frameworks have been developed which enable deep learning to be deployed in this learning scenario. A key…

Improving the reasoning capabilities of large language models (LLMs) typically relies either on the model's ability to sample a correct solution to be reinforced or on the existence of a stronger model able to solve the problem. However,…

Despite the great success of pre-trained language models, it is still a challenge to use these models for continual learning, especially for the class-incremental learning (CIL) setting due to catastrophic forgetting (CF). This paper…

To imitate the ability of keeping learning of human, continual learning which can learn from a never-ending data stream has attracted more interests recently. In all settings, the online class incremental learning (OCIL), where incoming…

Domain adaptation (DA) is a statistical learning problem that arises when the distribution of the source data used to train a model differs from that of the target data used to evaluate the model. While many DA algorithms have demonstrated…

Imitation learning aims to solve the problem of defining reward functions in real-world decision-making tasks. The current popular approach is the Adversarial Imitation Learning (AIL) framework, which matches expert state-action occupancy…

Using task-specific components within a neural network in continual learning (CL) is a compelling strategy to address the stability-plasticity dilemma in fixed-capacity models without access to past data. Current methods focus only on…

In real-world applications, dynamic scenarios require the models to possess the capability to learn new tasks continuously without forgetting the old knowledge. Experience-Replay methods store a subset of the old images for joint training.…