Related papers: Synthesizing DSLs for Few-Shot Learning
Data analysis is at the core of scientific studies, a prominent task that researchers and practitioners typically undertake by programming their own set of automated scripts. While there is no shortage of tools and languages available for…
The task of Few-shot learning (FSL) aims to transfer the knowledge learned from base categories with sufficient labelled data to novel categories with scarce known information. It is currently an important research question and has great…
Deep learning models for verification systems often fail to generalize to new users and new environments, even though they learn highly discriminative features. To address this problem, we propose a few-shot domain generalization framework…
This paper investigates a new challenging problem called defensive few-shot learning in order to learn a robust few-shot model against adversarial attacks. Simply applying the existing adversarial defense methods to few-shot learning cannot…
We propose KDSL, a new word sense disambiguation (WSD) framework that utilizes knowledge to automatically generate sense-labeled data for supervised learning. First, from WordNet, we automatically construct a semantic knowledge base called…
Deep Learning has greatly advanced the performance of semantic segmentation, however, its success relies on the availability of large amounts of annotated data for training. Hence, many efforts have been devoted to domain adaptive semantic…
Language models have become very popular recently and many claims have been made about their abilities, including for commonsense reasoning. Given the increasingly better results of current language models on previous static benchmarks for…
In this paper, we investigate the feasibility of applying few-shot learning algorithms to a speech task. We formulate a user-defined scenario of spoken term classification as a few-shot learning problem. In most few-shot learning studies,…
The significant amount of training data required for training Convolutional Neural Networks has become a bottleneck for applications like semantic segmentation. Few-shot semantic segmentation algorithms address this problem, with an aim to…
Few-shot learning (FSL) aims to recognize novel concepts from only a few labeled support samples. Recent studies enhance support features by incorporating additional semantic information or designing complex semantic fusion modules.…
Recently, we showed how to apply program-synthesis techniques to create abstract transformers in a user-provided domain-specific language (DSL) L (i.e., ''L-transformers"). However, we found that the algorithm of Kalita et al. does not…
Many applications today use large language models for code generation; however, production systems have strict latency requirements that can be difficult to meet with large models. Small language models with a few billion parameters are…
We would like industrial robots to handle unstructured environments with cameras and perception pipelines. In contrast to traditional industrial robots that replay offline-crafted trajectories, online behavior planning is required for these…
The scarcity of domain-specific dialogue datasets limits the development of dialogue systems across applications. Existing research is constrained by general or niche datasets that lack sufficient scale for training dialogue systems. To…
We propose a technique for declaratively specifying strategies for semi-supervised learning (SSL). The proposed method can be used to specify ensembles of semi-supervised learning, as well as agreement constraints and entropic…
In this paper, we provide a new neural-network based perspective on multi-task learning (MTL) and multi-domain learning (MDL). By introducing the concept of a semantic descriptor, this framework unifies MDL and MTL as well as encompassing…
We present and evaluate a method called grammar masking, which is used to guide large language models (LLMs) toward producing syntactically correct models for a given context-free grammar. Prompt engineering methods such as few-shot…
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…
We introduce RLang, a domain-specific language (DSL) for communicating domain knowledge to an RL agent. Unlike existing RL DSLs that ground to \textit{single} elements of a decision-making formalism (e.g., the reward function or policy),…
This paper presents Domain-Specific Sub-network (DoSS). It uses a set of masks obtained through pruning to define a sub-network for each domain and finetunes the sub-network parameters on domain data. This performs very closely and…