相关论文: AdapterHub Playground: Simple and Flexible Few-Sho…

This study aims to explore efficient tuning methods for the screenshot captioning task. Recently, image captioning has seen significant advancements, but research in captioning tasks for mobile screens remains relatively scarce. Current…

Entity Matching (EM) involves identifying different data representations referring to the same entity from multiple data sources and is typically formulated as a binary classification problem. It is a challenging problem in data integration…

Recent adapter-based CLIP tuning (e.g., Tip-Adapter) is a strong few-shot learner, achieving efficiency by caching support features for fast prototype matching. However, these methods rely on global uni-modal feature vectors, overlooking…

The vulnerability of deep neural networks to imperceptible adversarial perturbations has attracted widespread attention. Inspired by the success of vision-language foundation models, previous efforts achieved zero-shot adversarial…

Prompting language models (LMs) with training examples and task descriptions has been seen as critical to recent successes in few-shot learning. In this work, we show that finetuning LMs in the few-shot setting can considerably reduce the…

Most Transformer language models are primarily pretrained on English text, limiting their use for other languages. As the model sizes grow, the performance gap between English and other languages with fewer compute and data resources…

Efficient finetuning of pretrained language transformers is becoming increasingly prevalent for solving natural language processing tasks. While effective, it can still require a large number of tunable parameters. This can be a drawback…

Transformer-based language models have achieved remarkable success in few-shot in-context learning and drawn a lot of research interest. However, these models' performance greatly depends on the choice of the example prompts and also has…

With the introduction of the transformer architecture in computer vision, increasing model scale has been demonstrated as a clear path to achieving performance and robustness gains. However, with model parameter counts reaching the…

Embedding layers in transformer-based NLP models typically account for the largest share of model parameters, scaling with vocabulary size but not yielding performance gains proportional to scale. We propose an alternative approach in which…

Adaptive learning aims to stimulate and meet the needs of individual learners, which requires sophisticated system-level coordination of diverse tasks, including modeling learning resources, estimating student states, and making…

Standard neural network architectures are non-linear only by virtue of a simple element-wise activation function, making them both brittle and excessively large. In this paper, we consider methods for making the feed-forward layer more…

Although massive pre-trained vision-language models like CLIP show impressive generalization capabilities for many tasks, still it often remains necessary to fine-tune them for improved performance on specific datasets. When doing so, it is…

Fine-tuning is known to improve NLP models by adapting an initial model trained on more plentiful but less domain-salient examples to data in a target domain. Such domain adaptation is typically done using one stage of fine-tuning. We…

Reinforcement Learning from Human Feedback (RLHF) is widely used to align Language Models (LMs) with human preferences. However, existing approaches often neglect individual user preferences, leading to suboptimal personalization. We…

Large-scale pre-trained Vision-Language Models (VLMs) have exhibited impressive zero-shot performance and transferability, allowing them to adapt to downstream tasks in a data-efficient manner. However, when only a few labeled samples are…

Self-supervised learning has emerged as a key approach for learning generic representations from speech data. Despite promising results in downstream tasks such as speech recognition, speaker verification, and emotion recognition, a…

Cross-lingual speech adaptation aims to solve the problem of leveraging multiple rich-resource languages to build models for a low-resource target language. Since the low-resource language has limited training data, speech recognition…

Few-shot learning (FSL) techniques seek to learn the underlying patterns in data using fewer samples, analogous to how humans learn from limited experience. In this limited-data scenario, the challenges associated with deep neural networks,…

Human infants, with only a few hundred hours of speech exposure, acquire basic units of new languages, highlighting a striking efficiency gap compared to the data-hungry self-supervised speech models. To address this gap, this paper…