Related papers: PILOT: A Pre-Trained Model-Based Continual Learnin…

Discovering novel concepts in unlabelled datasets and in a continuous manner is an important desideratum of lifelong learners. In the literature such problems have been partially addressed under very restricted settings, where novel classes…

Attention-based architectures trained on internet-scale language data have demonstrated state of the art reasoning ability for various language-based tasks, such as logic problems and textual reasoning. Additionally, these Large Language…

Meta-learning can extract an inductive bias from previous learning experience and assist the training of new tasks. It is often realized through optimizing a meta-model with the evaluation loss of task-specific solvers. Most existing…

Continual learning (CL) aims to incrementally train a model on a sequence of tasks while retaining performance on prior ones. However, storing and replaying data is often infeasible due to privacy or security constraints and impractical for…

Reinforcement Learning (RL) is notoriously data-inefficient, which makes training on a real robot difficult. While model-based RL algorithms (world models) improve data-efficiency to some extent, they still require hours or days of…

Humans often interact with large language models (LLMs) in multi-turn interaction to obtain desired answers or more information. However, most existing studies overlook the multi-turn instruction following ability of LLMs, in terms of…

This article develops iterative machine learning (IML) for output tracking. The input-output data generated during iterations to develop the model used in the iterative update. The main contribution of this article to propose the use of…

It is crucial that robots' performance can be improved after deployment, as they are inherently likely to encounter novel scenarios never seen before. This paper presents an innovative solution: an interactive learning-based robot system…

Prompt tuning is a parameter-efficient tuning (PETuning) method for utilizing pre-trained models (PTMs) that simply prepends a soft prompt to the input and only optimizes the prompt to adapt PTMs to downstream tasks. Although it is…

Precise trajectory tracking for legged robots can be challenging due to their high degrees of freedom, unmodeled nonlinear dynamics, or random disturbances from the environment. A commonly adopted solution to overcome these challenges is to…

AI tasks encompass a wide range of domains and fields. While numerous AI models have been designed for specific tasks and applications, they often require considerable human efforts in finding the right model architecture, optimization…

Recently, the emergence of pre-trained models (PTMs) has brought natural language processing (NLP) to a new era. In this survey, we provide a comprehensive review of PTMs for NLP. We first briefly introduce language representation learning…

Reinforcement learning provides a general framework for flexible decision making and control, but requires extensive data collection for each new task that an agent needs to learn. In other machine learning fields, such as natural language…

Incremental learning is the ability of systems to acquire knowledge over time, enabling their adaptation and generalization to novel tasks. It is a critical ability for intelligent, real-world systems, especially when data changes…

The deployment of pre-trained models (PTMs) has greatly advanced the field of continual learning (CL), enabling positive knowledge transfer and resilience to catastrophic forgetting. To sustain these advantages for sequentially arriving…

The competitive performance of neural machine translation (NMT) critically relies on large amounts of training data. However, acquiring high-quality translation pairs requires expert knowledge and is costly. Therefore, how to best utilize a…

Continual learning (CL) is a paradigm that aims to replicate the human ability to learn and accumulate knowledge continually without forgetting previous knowledge and transferring it to new tasks. Recent instruction tuning (IT) involves…

Training machine learning (ML) algorithms is a computationally intensive process, which is frequently memory-bound due to repeatedly accessing large training datasets. As a result, processor-centric systems (e.g., CPU, GPU) suffer from…

In this work, we introduce Reinforcement Pre-Training (RPT) as a new scaling paradigm for large language models and reinforcement learning (RL). Specifically, we reframe next-token prediction as a reasoning task trained using RL, where it…

In order to be effective general purpose machines in real world environments, robots not only will need to adapt their existing manipulation skills to new circumstances, they will need to acquire entirely new skills on-the-fly. A great…