Related papers: BabyLM Challenge: Exploring the Effect of Variatio…
Modern Artificial Intelligence applications show great potential for language-related tasks that rely on next-word prediction. The current generation of Large Language Models (LLMs) have been linked to claims about human-like linguistic…
In the development of neural text-to-speech systems, model pre-training with a large amount of non-target speakers' data is a common approach. However, in terms of ultimately achieved system performance for target speaker(s), the actual…
Automatic Speech Recognition (ASR) systems often struggle to accurately process children's speech due to its distinct and highly variable acoustic and linguistic characteristics. While recent advancements in self-supervised learning (SSL)…
Diffusion Language Models (DLMs) offer a promising parallel generation paradigm but suffer from slow inference due to numerous refinement steps and the inability to use standard KV caching. We introduce CDLM (Consistency Diffusion Language…
Protein Language Models (PLMs) have emerged as performant and scalable tools for predicting the functional impact and clinical significance of protein-coding variants, but they still lag experimental accuracy. Here, we present a novel…
For specialized domains, there is often not a wealth of data with which to train large machine learning models. In such limited data / compute settings, various methods exist aiming to $\textit{do more with less}$, such as finetuning from a…
With the emergence of neural audio codecs, which encode multiple streams of discrete tokens from audio, large language models have recently gained attention as a promising approach for zero-shot Text-to-Speech (TTS) synthesis. Despite the…
In recent years, pre-trained large language models (LLMs) have demonstrated remarkable efficiency in achieving an inference-time few-shot learning capability known as in-context learning. However, existing literature has highlighted the…
Large Language Models (LLMs) are of great interest in vulnerability detection and repair. The effectiveness of these models hinges on the quality of the datasets used for both training and evaluation. Our investigation reveals that a number…
Vision-language models (VLMs) integrate visual and textual information, enabling a wide range of applications such as image captioning and visual question answering, making them crucial for modern AI systems. However, their high…
Large language models (LLMs) often necessitate extensive labeled datasets and training compute to achieve impressive performance across downstream tasks. This paper explores a self-training paradigm, where the LLM autonomously curates its…
Recent research has revealed that deep neural networks often take dataset biases as a shortcut to make decisions rather than understand tasks, leading to failures in real-world applications. In this study, we focus on the spurious…
Large language models (LLMs) are commonly trained on datasets consisting of fixed-length token sequences. These datasets are created by randomly concatenating documents of various lengths and then chunking them into sequences of a…
Despite rapid progress in large language models (LLMs), their performance on a vast majority of languages remains unsatisfactory. In this paper, we study building language-specific LLMs by adapting monolingual and multilingual LLMs. We…
Speech representation learning with self-supervised algorithms has resulted in notable performance boosts in many downstream tasks. Recent work combined self-supervised learning (SSL) and visually grounded speech (VGS) processing mechanisms…
Outcome-reward reinforcement learning (RL) is a common and increasingly significant way to refine the step-by-step reasoning of multimodal large language models (MLLMs). In the multiple-choice setting - a dominant format for multimodal…
Large language models (LLMs) are very proficient text generators. We leverage this capability of LLMs to generate task-specific data via zero-shot prompting and promote cross-lingual transfer for low-resource target languages. Given…
State-of-the-art neural network language models (NNLMs) represented by long short term memory recurrent neural networks (LSTM-RNNs) and Transformers are becoming highly complex. They are prone to overfitting and poor generalization when…
Large language models (LLMs) have exerted a considerable impact on diverse language-related tasks in recent years. Their demonstrated state-of-the-art performance is achieved through methodologies such as zero-shot or few-shot prompting.…
Self-Supervised Learning (SSL) has gained traction for its ability to learn rich representations with low labeling costs, applicable across diverse downstream tasks. However, assessing the downstream-task performance remains challenging due…