Related papers: In-context Learning Distillation: Transferring Few…
Despite the rapid recent progress in creating accurate and compact in-context learners, most recent work focuses on in-context learning (ICL) for tasks in English. However, the ability to interact with users of languages outside English…
The advent of contextual word embeddings -- representations of words which incorporate semantic and syntactic information from their context -- has led to tremendous improvements on a wide variety of NLP tasks. However, recent contextual…
Lack of specialized data makes building a multi-domain neural machine translation tool challenging. Although emerging literature dealing with low resource languages starts to show promising results, most state-of-the-art models used…
We explore best practices for training small, memory efficient machine translation models with sequence-level knowledge distillation in the domain adaptation setting. While both domain adaptation and knowledge distillation are widely-used,…
Large Language Models (LLMs) have been shown to be able to learn different tasks without explicit finetuning when given many input-output examples / demonstrations through In-Context Learning (ICL). Increasing the number of examples, called…
We study the phenomenon of \textit{in-context learning} (ICL) exhibited by large language models, where they can adapt to a new learning task, given a handful of labeled examples, without any explicit parameter optimization. Our goal is to…
In realistic speech enhancement settings for end-user devices, we often encounter only a few speakers and noise types that tend to reoccur in the specific acoustic environment. We propose a novel personalized speech enhancement method to…
Real-world audio often mixes speech and music, yet models typically handle only one domain. This paper introduces a multi-teacher distillation framework that unifies speech and music models into a single one while significantly reducing…
In light of the remarkable success of in-context learning in large language models, its potential extension to the vision domain, particularly with visual foundation models like Stable Diffusion, has sparked considerable interest. Existing…
Model distillation aims to distill the knowledge of a complex model into a simpler one. In this paper, we consider an alternative formulation called dataset distillation: we keep the model fixed and instead attempt to distill the knowledge…
State-of-the-art Vision-Language Models (VLMs) ground the vision and the language modality primarily via projecting the vision tokens from the encoder to language-like tokens, which are directly fed to the Large Language Model (LLM)…
The conventional few-shot classification aims at learning a model on a large labeled base dataset and rapidly adapting to a target dataset that is from the same distribution as the base dataset. However, in practice, the base and the target…
Meta-learning approaches have addressed few-shot problems by finding initialisations suited for fine-tuning to target tasks. Often there are additional properties within training data (which we refer to as context), not relevant to the…
While Large Language Models (LLMs) have demonstrated significant promise as agents in interactive tasks, their substantial computational requirements and restricted number of calls constrain their practical utility, especially in…
Multi-modality image fusion aims to synthesize a single, comprehensive image from multiple source inputs. Traditional approaches, such as CNNs and GANs, offer efficiency but struggle to handle low-quality or complex inputs. Recent advances…
Recent work has shown that language models (LMs) trained with multi-task \textit{instructional learning} (MTIL) can solve diverse NLP tasks in zero- and few-shot settings with improved performance compared to prompt tuning. MTIL illustrates…
Dataset distillation, a training-aware data compression technique, has recently attracted increasing attention as an effective tool for mitigating costs of optimization and data storage. However, progress remains largely empirical.…
Partial multi-task learning where training examples are annotated for one of the target tasks is a promising idea in remote sensing as it allows combining datasets annotated for different tasks and predicting more tasks with fewer network…
The strong few-shot in-context learning capability of large pre-trained language models (PLMs) such as GPT-3 is highly appealing for application domains such as biomedicine, which feature high and diverse demands of language technologies…
Despite substantial progress in multilingual extractive Question Answering (QA), models with high and uniformly distributed performance across languages remain challenging, especially for languages with limited resources. We study…