相关论文: Understanding and Improving Knowledge Distillation…

Knowledge Distillation (KD) methods are capable of transferring the knowledge encoded in a large and complex teacher into a smaller and faster student. Early methods were usually limited to transferring the knowledge only between the last…

Knowledge Distillation (KD) is increasingly adopted to transfer capabilities from large language models to smaller ones, offering significant improvements in efficiency and utility while often surpassing standard fine-tuning. Beyond…

Dataset Distillation (DD) compresses large datasets into compact synthetic ones that maintain training performance. However, current methods mainly target sample reduction, with limited consideration of data precision and its impact on…

In the era of large scale pretrained models, Knowledge Distillation (KD) serves an important role in transferring the wisdom of computationally heavy teacher models to lightweight, efficient student models while preserving performance.…

Knowledge Distillation (KD) has proven effective for compressing large teacher models into smaller student models. While it is well known that student models can achieve similar accuracies as the teachers, it has also been shown that they…

As pretrained transformer language models continue to achieve state-of-the-art performance, the Natural Language Processing community has pushed for advances in model compression and efficient attention mechanisms to address high…

Large generative models such as large language models (LLMs) and diffusion models have revolutionized the fields of NLP and computer vision respectively. However, their slow inference, high computation and memory requirement makes it…

This technical report presents quantization-aware distillation (QAD) and our best practices for recovering accuracy of NVFP4-quantized large language models (LLMs) and vision-language models (VLMs). QAD distills a full-precision teacher…

Knowledge Distillation (KD) compresses neural networks by learning a small network (student) via transferring knowledge from a pre-trained large network (teacher). Many endeavours have been devoted to the image domain, while few works focus…

LLMs are increasingly explored for bundle generation, thanks to their reasoning capabilities and knowledge. However, deploying large-scale LLMs introduces significant efficiency challenges, primarily high computational costs during…

Tiny, causal models are crucial for embedded audio machine learning applications. Model compression can be achieved via distilling knowledge from a large teacher into a smaller student model. In this work, we propose a novel two-step…

Knowledge distillation (KD), a technique widely employed in computer vision, has emerged as a de facto standard for improving the performance of small neural networks. However, prevailing KD-based approaches in video tasks primarily focus…

Knowledge distillation (KD) has been a popular and effective method for model compression. One important assumption of KD is that the teacher's original dataset will also be available when training the student. However, in situations such…

Knowledge distillation (KD) is an effective model compression method that can transfer the internal capabilities of large language models (LLMs) to smaller ones. However, the multi-modal probability distribution predicted by teacher LLMs…

Deep Neural Networks (DNNs) have achieved notable performance in the fields of computer vision and natural language processing with various applications in both academia and industry. However, with recent advancements in DNNs and…

Pre-trained language models (e.g., BERT (Devlin et al., 2018) and its variants) have achieved remarkable success in varieties of NLP tasks. However, these models usually consist of hundreds of millions of parameters which brings challenges…

This study proposes a method for knowledge distillation (KD) of fine-tuned Large Language Models (LLMs) into smaller, more efficient, and accurate neural networks. We specifically target the challenge of deploying these models on…

Knowledge distillation (KD) enables a smaller "student" model to mimic a larger "teacher" model by transferring knowledge from the teacher's output or features. However, most KD methods treat all samples uniformly, overlooking the varying…

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…

Significant improvement has been achieved in automated audio captioning (AAC) with recent models. However, these models have become increasingly large as their performance is enhanced. In this work, we propose a knowledge distillation (KD)…