相关论文: PILOT: A Pre-Trained Model-Based Continual Learnin…

Prompt learning is a new paradigm in the Natural Language Processing (NLP) field which has shown impressive performance on a number of natural language tasks with common benchmarking text datasets in full, few-shot, and zero-shot…

As the applications of large language models (LLMs) expand across diverse fields, the ability of these models to adapt to ongoing changes in data, tasks, and user preferences becomes crucial. Traditional training methods, relying on static…

The fine-tuning of deep pre-trained models has revealed compositional properties, with multiple specialized modules that can be arbitrarily composed into a single, multi-task model. However, identifying the conditions that promote…

Pre-trained language models (PLMs) serve as backbones for various real-world systems. For high-stake applications, it's equally essential to have reasonable confidence estimations in predictions. While the vanilla confidence scores of PLMs…

Large Language Models (LLMs), trained on extensive web-scale corpora, have demonstrated remarkable abilities across diverse tasks, especially as they are scaled up. Nevertheless, even state-of-the-art models struggle in certain cases,…

In-context learning, where pre-trained language models learn to perform tasks from task examples and instructions in their contexts, has attracted much attention in the NLP community. However, the ability of in-context learning is not fully…

Recently introduced language model prompting methods can achieve high accuracy in zero- and few-shot settings while requiring few to no learned task-specific parameters. Nevertheless, these methods still often trail behind full model…

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…

In this paper, we consider the supervised pre-trained transformer for a class of sequential decision-making problems. The class of considered problems is a subset of the general formulation of reinforcement learning in that there is no…

Large language models are typically adapted to downstream tasks through supervised fine-tuning on domain-specific data. While standard fine-tuning focuses on minimizing generation loss to optimize model parameters, we take a deeper step by…

Most recent successes in robot reinforcement learning involve learning a specialized single-task agent. However, robots capable of performing multiple tasks can be much more valuable in real-world applications. Multi-task reinforcement…

Pre-trained point cloud models have found extensive applications in 3D understanding tasks like object classification and part segmentation. However, the prevailing strategy of full fine-tuning in downstream tasks leads to large per-task…

This paper provides a preliminary study for an efficient learning algorithm by reasoning the error from first principle physics to generate learning signals in near real time. Motivated by iterative learning control (ILC), this learning…

Incremental learning is a form of online learning. Incremental learning can modify the parameters and structure of the deep learning model so that the model does not forget the old knowledge while learning new knowledge. Preventing…

Although reinforcement learning has seen tremendous success recently, this kind of trial-and-error learning can be impractical or inefficient in complex environments. The use of demonstrations, on the other hand, enables agents to benefit…

Pre-trained models have become indispensable for efficiently building models across a broad spectrum of downstream tasks. The advantages of pre-trained models have been highlighted by empirical studies on scaling laws, which demonstrate…

We propose an AI-based pilot trainer to help students learn how to fly aircraft. First, an AI agent uses behavioral cloning to learn flying maneuvers from qualified flight instructors. Later, the system uses the agent's decisions to detect…

The mainstream paradigm behind continual learning has been to adapt the model parameters to non-stationary data distributions, where catastrophic forgetting is the central challenge. Typical methods rely on a rehearsal buffer or known task…

Attaining prototypical features to represent class distributions is well established in representation learning. However, learning prototypes online from streaming data proves a challenging endeavor as they rapidly become outdated, caused…

Prompt tuning has become a popular strategy for adapting Vision-Language Models (VLMs) to zero/few-shot visual recognition tasks. Some prompting techniques introduce prior knowledge due to its richness, but when learnable tokens are…