Related papers: Knowledge Distillation vs. Pretraining from Scratc…

Deploying large language models (LLMs) of several billion parameters can be impractical in most industrial use cases due to constraints such as cost, latency limitations, and hardware accessibility. Knowledge distillation (KD) offers a…

Condensed datasets offer a compact representation of larger datasets, but training models directly on them or using them to enhance model performance through knowledge distillation (KD) can result in suboptimal outcomes due to limited…

Recent explorations of large-scale pre-trained language models (PLMs) have revealed the power of PLMs with huge amounts of parameters, setting off a wave of training ever-larger PLMs. However, it requires tremendous computational resources…

High storage and computational costs obstruct deep neural networks to be deployed on resource-constrained devices. Knowledge distillation aims to train a compact student network by transferring knowledge from a larger pre-trained teacher…

Knowledge Distillation (KD) is one proposed solution to large model sizes and slow inference speed in semantic segmentation. In our research we identify 25 proposed distillation loss terms from 14 publications in the last 4 years.…

Although large foundation models pre-trained by self-supervised learning have achieved state-of-the-art performance in many tasks including automatic speech recognition (ASR), knowledge distillation (KD) is often required in practice to…

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…

Reinforcement learning (RL) post-training has recently driven major gains in long chain-of-thought reasoning large language models (LLMs), but the high inference cost of such models motivates distillation into smaller students. Most…

As a promising solution for model compression, knowledge distillation (KD) has been applied in recommender systems (RS) to reduce inference latency. Traditional solutions first train a full teacher model from the training data, and then…

Knowledge distillation (KD) has gained much attention due to its effectiveness in compressing large-scale pre-trained models. In typical KD methods, the small student model is trained to match the soft targets generated by the big teacher…

Knowledge distillation (KD) is an efficient approach to transfer the knowledge from a large "teacher" network to a smaller "student" network. Traditional KD methods require lots of labeled training samples and a white-box teacher…

We present Knowledge Distillation with Meta Learning (MetaDistil), a simple yet effective alternative to traditional knowledge distillation (KD) methods where the teacher model is fixed during training. We show the teacher network can learn…

In real-world NLP applications, Large Language Models (LLMs) offer promising solutions due to their extensive training on vast datasets. However, the large size and high computation demands of LLMs limit their practicality in many…

Vision-Language Models (VLMs) bring powerful understanding and reasoning capabilities to multimodal tasks. Meanwhile, the great need for capable aritificial intelligence on mobile devices also arises, such as the AI assistant software. Some…

Knowledge Distillation (KD) has emerged as a promising technique for model compression but faces critical limitations: (1) sensitivity to hyperparameters requiring extensive manual tuning, (2) capacity gap when distilling from very large…

Knowledge distillation (KD) is an effective tool for compressing deep classification models for edge devices. However, the performance of KD is affected by the large capacity gap between the teacher and student networks. Recent methods have…

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…

Dataset distillation (DD) generates small synthetic datasets that can efficiently train deep networks with a limited amount of memory and compute. Despite the success of DD methods for supervised learning, DD for self-supervised…

Pre-trained language models such as BERT have proven to be highly effective for natural language processing (NLP) tasks. However, the high demand for computing resources in training such models hinders their application in practice. In…

Knowledge Distillation (KD) emerges as one of the most promising compression technologies to run advanced deep neural networks on resource-limited devices. In order to train a small network (student) under the guidance of a large network…