Related papers: CoDERT: Distilling Encoder Representations with Co…

Knowledge distillation from large language models (LLMs) assumes that the teacher's output distribution is a high-quality training signal. On reasoning tasks, this assumption is frequently violated. A model's intermediate representations…

Deep learning has shown promise in enhancing channel state information (CSI) feedback. However, many studies indicate that better feedback performance often accompanies higher computational complexity. Pursuing better performance-complexity…

Learned image compression sits at the intersection of machine learning and image processing. With advances in deep learning, neural network-based compression methods have emerged. In this process, an encoder maps the image to a…

Neural transducer (RNNT)-based target-speaker speech recognition (TS-RNNT) directly transcribes a target speaker's voice from a multi-talker mixture. It is a promising approach for streaming applications because it does not incur the extra…

Knowledge distillation is an effective machine learning technique to transfer knowledge from a teacher model to a smaller student model, especially with unlabeled data. In this paper, we focus on knowledge distillation for the RNN-T model,…

Speech recognition on smart devices is challenging owing to the small memory footprint. Hence small size ASR models are desirable. With the use of popular transducer-based models, it has become possible to practically deploy streaming…

Transformers recently are adapted from the community of natural language processing as a promising substitute of convolution-based neural networks for visual learning tasks. However, its supremacy degenerates given an insufficient amount of…

Scarcity of parallel sentence-pairs poses a significant hurdle for training high-quality Neural Machine Translation (NMT) models in bilingually low-resource scenarios. A standard approach is transfer learning, which involves taking a model…

Knowledge distillation can be a cost-effective technique to distill knowledge in Large Language Models, if the teacher output logits can be pre-computed and cached. However, successfully applying this to pre-training remains largely…

Knowledge distillation has been widely used to compress existing deep learning models while preserving the performance on a wide range of applications. In the specific context of Automatic Speech Recognition (ASR), distillation from…

Transducer is one of the mainstream frameworks for streaming speech recognition. There is a performance gap between the streaming and non-streaming transducer models due to limited context. To reduce this gap, an effective way is to ensure…

The smaller memory bandwidth in smart devices prompts development of smaller Automatic Speech Recognition (ASR) models. To obtain a smaller model, one can employ the model compression techniques. Knowledge distillation (KD) is a popular…

Knowledge distillation is typically conducted by training a small model (the student) to mimic a large and cumbersome model (the teacher). The idea is to compress the knowledge from the teacher by using its output probabilities as…

DEtection TRansformer (DETR) becomes a dominant paradigm, mainly due to its common architecture with high accuracy and no post-processing. However, DETR suffers from unstable training dynamics. It consumes more data and epochs to converge…

Neural retrievers based on pre-trained language models (PLMs), such as dual-encoders, have achieved promising performance on the task of open-domain question answering (QA). Their effectiveness can further reach new state-of-the-arts by…

Recently, the recurrent neural network transducer (RNN-T) architecture has become an emerging trend in end-to-end automatic speech recognition research due to its advantages of being capable for online streaming speech recognition. However,…

Distillation has shown remarkable success in transferring knowledge from a Large Language Model (LLM) teacher to a student LLM. However, current distillation methods require similar tokenizers between the teacher and the student,…

This paper proposes a novel knowledge distillation-based learning method to improve the classification performance of convolutional neural networks (CNNs) without a pre-trained teacher network, called exit-ensemble distillation. Our method…

Resource-constrained perception systems such as edge computing and vision-for-robotics require vision models to be both accurate and lightweight in computation and memory usage. While knowledge distillation is a proven strategy to enhance…

Knowledge distillation, which involves extracting the "dark knowledge" from a teacher network to guide the learning of a student network, has emerged as an important technique for model compression and transfer learning. Unlike previous…