Related papers: GenDistiller: Distilling Pre-trained Language Mode…
Fine-tuning transformer models after unsupervised pre-training reaches a very high performance on many different natural language processing tasks. Unfortunately, transformers suffer from long inference times which greatly increases costs…
The multilingual pre-trained language models (e.g, mBERT, XLM and XLM-R) have shown impressive performance on cross-lingual natural language understanding tasks. However, these models are computationally intensive and difficult to be…
Knowledge distillation has attracted a great deal of interest recently to compress pre-trained language models. However, existing knowledge distillation methods suffer from two limitations. First, the student model simply imitates the…
Dataset distillation aims to compress a training dataset by creating a small number of informative synthetic samples such that neural networks trained on them perform as well as those trained on the original training dataset. Current text…
Self-supervised learning has shown great success in Speech Recognition. However, it has been observed that finetuning all layers of the learned model leads to lower performance compared to resetting top layers. This phenomenon is attributed…
The enhancement of mathematical capabilities in large language models (LLMs) fosters new developments in mathematics education within primary and secondary schools, particularly as they relate to intelligent tutoring systems. However, LLMs…
As large language models (LLMs) tackle increasingly complex tasks and longer documents, their computational and memory costs during inference become a major bottleneck. To address this, we propose PromptDistill, a novel, training-free…
Speech data has rich acoustic and paralinguistic information with important cues for understanding a speaker's tone, emotion, and intent, yet traditional large language models such as BERT do not incorporate this information. There has been…
We generalize deep self-attention distillation in MiniLM (Wang et al., 2020) by only using self-attention relation distillation for task-agnostic compression of pretrained Transformers. In particular, we define multi-head self-attention…
Deploying large language models (LLMs) is challenging because they are memory inefficient and compute-intensive for practical applications. In reaction, researchers train smaller task-specific models by either finetuning with human labels…
Generative retrieval is a promising new paradigm in text retrieval that generates identifier strings of relevant passages as the retrieval target. This paradigm leverages powerful generative language models, distinct from traditional sparse…
Diffusion language models intrinsically fail to capture correlations between decoded tokens, which leads to a harsh trade-off between sampling quality and throughput. To solve this issue, we propose DiLaDiff, a variant of masked diffusion…
Transformer-based models have shown promising performance on tabular data compared to their classical counterparts such as neural networks and Gradient Boosted Decision Trees (GBDTs) in scenarios with limited training data. They utilize…
Many recent breakthroughs in machine learning have been enabled by the pre-trained foundation models. By scaling up model parameters, training data, and computation resources, foundation models have significantly advanced the…
Unifying acoustic and linguistic representation learning has become increasingly crucial to transfer the knowledge learned on the abundance of high-resource language data for low-resource speech recognition. Existing approaches simply…
In large part due to their implicit semantic modeling, self-supervised learning (SSL) methods have significantly increased the performance of valence recognition in speech emotion recognition (SER) systems. Yet, their large size may often…
Advances in self-distillation have shown that when knowledge is distilled from a teacher to a student using the same deep learning (DL) architecture, the student performance can surpass the teacher particularly when the network is…
Large language models (LLMs) excel at clinical information extraction but their computational demands limit practical deployment. Knowledge distillation--the process of transferring knowledge from larger to smaller models--offers a…
Retrieval-augmented generation framework can address the limitations of large language models by enabling real-time knowledge updates for more accurate answers. An efficient way in the training phase of retrieval-augmented models is…
While several self-supervised approaches for learning discrete speech representation have been proposed, it is unclear how these seemingly similar approaches relate to each other. In this paper, we consider a generative model with discrete…