相关论文: How Few-Shot Examples Add Up: A Causal Decompositi…

In-context learning (ICL) research often considers learning a function in-context through a uniform sample of input-output pairs. Here, we investigate how presenting a compositional subtask curriculum in context may alter the computations a…

Few-shot Continual Relation Extraction is a crucial challenge for enabling AI systems to identify and adapt to evolving relationships in dynamic real-world domains. Traditional memory-based approaches often overfit to limited samples,…

Large Language Models (LLMs) have proven effective at In-Context Learning (ICL), an ability that allows them to create predictors from labeled examples. Few studies have explored the interplay between ICL and specific properties of…

Generative Large Language Models (LLMs) are capable of being in-context learners. However, the underlying mechanism of in-context learning (ICL) is still a major research question, and experimental research results about how models exploit…

Few-Shot Class-Incremental Learning (FSCIL) aims to enable deep neural networks to learn new tasks incrementally from a small number of labeled samples without forgetting previously learned tasks, closely mimicking human learning patterns.…

Causal influence measures for machine learnt classifiers shed light on the reasons behind classification, and aid in identifying influential input features and revealing their biases. However, such analyses involve evaluating the classifier…

Large-scale models trained on extensive datasets, have emerged as the preferred approach due to their high generalizability across various tasks. In-context learning (ICL), a popular strategy in natural language processing, uses such models…

Large language models (LLMs) have exhibited remarkable capabilities in learning from explanations in prompts, but there has been limited understanding of exactly how these explanations function or why they are effective. This work aims to…

Transformers have demonstrated a strong ability for in-context learning (ICL), enabling models to solve previously unseen tasks using only example input output pairs provided at inference time. While prior theoretical work has established…

We propose a few-shot learning method for unsupervised feature selection, which is a task to select a subset of relevant features in unlabeled data. Existing methods usually require many instances for feature selection. However, sufficient…

Scene graph prediction --- classifying the set of objects and predicates in a visual scene --- requires substantial training data. However, most predicates only occur a handful of times making them difficult to learn. We introduce the first…

For most real-world applications, robots need to adapt and learn continually with limited data in their environments. In this paper, we consider the problem of Few-Shot class Incremental Learning (FSIL), in which an AI agent is required to…

Continual learning and few-shot learning are important frontiers in progress toward broader Machine Learning (ML) capabilities. Recently, there has been intense interest in combining both. One of the first examples to do so was the…

This thesis investigates two key phenomena in large language models (LLMs): in-context learning (ICL) and model collapse. We study ICL in a linear transformer with tied weights trained on linear regression tasks, and show that minimising…

Pre-trained transformers are able to learn from examples provided as part of the prompt without any weight updates, a remarkable ability known as in-context learning (ICL). Despite its demonstrated efficacy across various domains, the…

In-Context Learning (ICL) empowers Large Language Models (LLMs) for rapid task adaptation without Fine-Tuning (FT), but its reliance on demonstration selection remains a critical challenge. While many-shot ICL shows promising performance…

In-Context Learning (ICL) is an essential emergent ability of Large Language Models (LLMs), and recent studies introduce Chain-of-Thought (CoT) to exemplars of ICL to enhance the reasoning capability, especially in mathematics tasks.…

Few-shot Learning aims to learn and distinguish new categories with a very limited number of available images, presenting a significant challenge in the realm of deep learning. Recent researchers have sought to leverage the additional…

In image classification, it is common practice to train deep networks to extract a single feature vector per input image. Few-shot classification methods also mostly follow this trend. In this work, we depart from this established direction…

Vision-language models (VLMs) are widely assumed to exhibit in-context learning (ICL), a property similar to that of their language-only counterparts. While recent work suggests VLMs can perform multimodal ICL (MM-ICL), studies show they…