Related papers: Incremental Learning of Retrievable Skills For Eff…
Class-Incremental Learning (CIL) aims to learn new classes sequentially while retaining the knowledge of previously learned classes. Recently, pre-trained models (PTMs) combined with parameter-efficient fine-tuning (PEFT) have shown…
Continual learning enables incremental learning of new tasks without forgetting those previously learned, resulting in positive knowledge transfer that can enhance performance on both new and old tasks. However, continual learning poses new…
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…
This paper studies the challenging continual learning (CL) setting of Class Incremental Learning (CIL). CIL learns a sequence of tasks consisting of disjoint sets of concepts or classes. At any time, a single model is built that can be…
Class-incremental learning (CIL) aims to enable models to continuously learn new classes while overcoming catastrophic forgetting. The introduction of pre-trained models has brought new tuning paradigms to CIL. In this paper, we revisit…
Consider learning an imitation policy on the basis of demonstrated behavior from multiple environments, with an eye towards deployment in an unseen environment. Since the observable features from each setting may be different, directly…
Continual learning aims to acquire new knowledge while retaining past information. Class-incremental learning (CIL) presents a challenging scenario where classes are introduced sequentially. For video data, the task becomes more complex…
Class-Incremental Learning (CIL) aims to train a reliable model with the streaming data, which emerges unknown classes sequentially. Different from traditional closed set learning, CIL has two main challenges: 1) Novel class detection. The…
Class incremental learning (CIL) trains a network on sequential tasks with separated categories in each task but suffers from catastrophic forgetting, where models quickly lose previously learned knowledge when acquiring new tasks. The…
In-context learning (ICL) is an effective approach to help large language models (LLMs) adapt to various tasks by providing demonstrations of the target task. Considering the high cost of labeling demonstrations, many methods propose…
Continual learning aims to provide intelligent agents that are capable of learning continually a sequence of tasks, building on previously learned knowledge. A key challenge in this learning paradigm is catastrophically forgetting…
In-context learning (ICL), teaching a large language model (LLM) to perform a task with few-shot demonstrations rather than adjusting the model parameters, has emerged as a strong paradigm for using LLMs. While early studies primarily used…
In this paper, we present \textbf{C}ont\textbf{E}xtual \textbf{I}mitation \textbf{L}earning~(CEIL), a general and broadly applicable algorithm for imitation learning (IL). Inspired by the formulation of hindsight information matching, we…
Class incremental learning (CIL) algorithms aim to continually learn new object classes from incrementally arriving data while not forgetting past learned classes. The common evaluation protocol for CIL algorithms is to measure the average…
This paper proposes a simple but highly efficient expansion-based model for continual learning. The recent feature transformation, masking and factorization-based methods are efficient, but they grow the model only over the global or shared…
The emergence of in-context learning (ICL) enables large pre-trained language models (PLMs) to make predictions for unseen inputs without updating parameters. Despite its potential, ICL's effectiveness heavily relies on the quality,…
Exemplar-Free Class Incremental Learning (efCIL) aims to continuously incorporate the knowledge from new classes while retaining previously learned information, without storing any old-class exemplars (i.e., samples). For this purpose,…
Skill Incremental Learning (SIL) is the process by which an embodied agent expands and refines its skill set over time by leveraging experience gained through interaction with its environment or by the integration of additional data. SIL…
In-context learning (ICL) allows transformer-based language models that are pre-trained on general text to quickly learn a specific task with a few "task demonstrations" without updating their parameters, significantly boosting their…
Imitation learning (IL) algorithms have shown promising results for robots to learn skills from expert demonstrations. However, they need multi-task demonstrations to be provided at once for acquiring diverse skills, which is difficult in…