Related papers: When Sensing Varies with Contexts: Context-as-Tran…
Few-shot learning (FSL) aims to learn models that generalize to novel classes with limited training samples. Recent works advance FSL towards a scenario where unlabeled examples are also available and propose semi-supervised FSL methods.…
In-context learning (ICL) excels at new tasks from minimal examples, yet we still lack a mechanistic explanation of how few-shot prompts shape a model's function vector (FV)--a causal activation direction that drives task behavior on the…
Transformers exhibit In-Context Learning (ICL), where these models solve new tasks by using examples in the prompt without additional training. In our work, we identify and analyze two key components of ICL: (1) context-scaling, where model…
Few-shot Class-Incremental Learning (FSCIL) aims at learning new concepts continually with only a few samples, which is prone to suffer the catastrophic forgetting and overfitting problems. The inaccessibility of old classes and the…
In-context learning (ICL) enables large language models to perform few-shot learning by conditioning on labeled examples in the prompt. Despite its flexibility, ICL suffers from instability -- especially as prompt length increases with more…
Incremental learning attempts to develop a classifier which learns continuously from a stream of data segregated into different classes. Deep learning approaches suffer from catastrophic forgetting when learning classes incrementally, while…
Few-shot class-incremental Learning (FSCIL) enables models to learn new classes from limited data while retaining performance on previously learned classes. Traditional FSCIL methods often require fine-tuning parameters with limited new…
Training semantic segmentation models requires a large amount of finely annotated data, making it hard to quickly adapt to novel classes not satisfying this condition. Few-Shot Segmentation (FS-Seg) tackles this problem with many…
With the increasing ability of large language models (LLMs), in-context learning (ICL) has evolved as a new paradigm for natural language processing (NLP), where instead of fine-tuning the parameters of an LLM specific to a downstream task…
Learning from large-scale pre-trained models with strong generalization ability has shown remarkable success in a wide range of downstream tasks recently, but it is still underexplored in the challenging few-shot class-incremental learning…
The remarkable ability of transformers to learn new concepts solely by reading examples within the input prompt, termed in-context learning (ICL), is a crucial aspect of intelligent behavior. Here, we focus on understanding the learning…
Despite significant progress in continual learning ranging from architectural novelty to clever strategies for mitigating catastrophic forgetting most existing methods rest on a strong but unrealistic assumption the availability of labeled…
In-context learning (ICL) suffers from oversensitivity to the prompt, making it unreliable in real-world scenarios. We study the sensitivity of ICL with respect to multiple perturbation types. First, we find that label bias obscures the…
Deep learning based models have excelled in many computer vision tasks and appear to surpass humans' performance. However, these models require an avalanche of expensive human labeled training data and many iterations to train their large…
Few-shot learning (FSL) has attracted increasing attention in recent years but remains challenging, due to the intrinsic difficulty in learning to generalize from a few examples. This paper proposes an adaptive margin principle to improve…
There has been significant recent interest in understanding the capacity of Transformers for in-context learning (ICL), yet most theory focuses on supervised settings with explicitly labeled pairs. In practice, Transformers often perform…
Designing crystal materials with desired physicochemical properties remains a fundamental challenge in materials science. While large language models (LLMs) have demonstrated strong in-context learning (ICL) capabilities, existing LLM-based…
Automatic Pill Recognition (APR) systems are crucial for enhancing hospital efficiency, assisting visually impaired individuals, and preventing cross-infection. However, most existing deep learning-based pill recognition systems can only…
In-context learning (ICL) enables models to adapt to new tasks via inference-time demonstrations. Despite its success in large language models, the extension of ICL to multimodal settings remains poorly understood in terms of its internal…
Few-shot class incremental learning (FSCIL) is a more realistic and challenging paradigm in continual learning to incrementally learn unseen classes and overcome catastrophic forgetting on base classes with only a few training examples.…