Related papers: Task-adaptive Pre-training and Self-training are C…
While LLM-based TTS models exhibit zero-shot emotion and speaker cloning, their cloning fidelity and pronunciation clarity degrade on unseen domains. Fine-tuning is essential for adaptation, yet uniform approaches overlook specific…
Natural Language Inference (NLI) or Recognizing Textual Entailment (RTE) aims at predicting the relation between a pair of sentences (premise and hypothesis) as entailment, contradiction or semantic independence. Although deep learning…
Vision-language models have showcased impressive zero-shot classification capabilities when equipped with suitable text prompts. Previous studies have shown the effectiveness of test-time prompt tuning; however, these methods typically…
This paper introduces a novel application of Test-Time Training (TTT) for Speech Enhancement, addressing the challenges posed by unpredictable noise conditions and domain shifts. This method combines a main speech enhancement task with a…
Natural language inference (NLI) is among the most challenging tasks in natural language understanding. Recent work on unsupervised pretraining that leverages unsupervised signals such as language-model and sentence prediction objectives…
Prior work on language models (LMs) shows that training on a large number of diverse tasks improves few-shot learning (FSL) performance on new tasks. We take this to the extreme, automatically extracting 413,299 tasks from internet tables -…
While few-shot learning (FSL) aims for rapid generalization to new concepts with little supervision, self-supervised learning (SSL) constructs supervisory signals directly computed from unlabeled data. Exploiting the complementarity of…
Semi-supervised learning (SSL) has achieved significant progress by leveraging both labeled data and unlabeled data. Existing SSL methods overlook a common real-world scenario when labeled data is extremely scarce, potentially as limited as…
Prompt learning has emerged as a promising method for adapting pre-trained visual-language models (VLMs) to a range of downstream tasks. While optimizing the context can be effective for improving performance on specific tasks, it can often…
Structured tabular data is a fundamental data type in numerous fields, and the capacity to reason over tables is crucial for answering questions and validating hypotheses. However, constructing labeled data for complex reasoning tasks is…
Language models (LMs) have demonstrated remarkable capabilities in NLP, yet adapting them efficiently and robustly to specific tasks remains challenging. As their scale and complexity grow, fine-tuning LMs on labelled data often…
Recent progress in NLP witnessed the development of large-scale pre-trained language models (GPT, BERT, XLNet, etc.) based on Transformer (Vaswani et al. 2017), and in a range of end tasks, such models have achieved state-of-the-art…
Spoken language understanding (SLU) requires a model to analyze input acoustic signal to understand its linguistic content and make predictions. To boost the models' performance, various pre-training methods have been proposed to learn rich…
Pre-trained language models (PTLM) have achieved impressive results in a range of natural language understanding (NLU) and generation (NLG) tasks. However, current pre-training objectives such as masked token prediction (for BERT-style…
Large-scale vision-language models (VLMs) such as CLIP exhibit strong zero-shot generalization, but adapting them to downstream tasks typically requires costly labeled data. Existing unsupervised self-training methods rely on…
Instruction tuning of language models has demonstrated the ability to enhance model generalization to unseen tasks via in-context learning using a few examples. However, typical supervised learning still requires a plethora of downstream…
Recently, neural networks based purely on self-attention, such as the Vision Transformer (ViT), have been shown to outperform deep learning models constructed with convolutional neural networks (CNNs) on various vision tasks, thus extending…
Traditional NLP has long held (supervised) syntactic parsing necessary for successful higher-level semantic language understanding (LU). The recent advent of end-to-end neural models, self-supervised via language modeling (LM), and their…
Models capable of leveraging unlabelled data are crucial in overcoming large distribution gaps between the acquired datasets across different imaging devices and configurations. In this regard, self-training techniques based on…
Pre-trained vision-language models (e.g., CLIP) have shown promising zero-shot generalization in many downstream tasks with properly designed text prompts. Instead of relying on hand-engineered prompts, recent works learn prompts using the…