Related papers: Efficient Mathematical Reasoning Models via Dynami…
With the increasing size of datasets used for training neural networks, data pruning becomes an attractive field of research. However, most current data pruning algorithms are limited in their ability to preserve accuracy compared to models…
Knowledge distillation (KD) in transformers often faces challenges due to misalignment in the number of attention heads between teacher and student models. Existing methods either require identical head counts or introduce projectors to…
Multi-head attention, a collection of several attention mechanisms that independently attend to different parts of the input, is the key ingredient in the Transformer. Recent work has shown, however, that a large proportion of the heads in…
Synaptic pruning in biological brains removes weak connections to improve efficiency. In contrast, dropout regularization in artificial neural networks randomly deactivates neurons without considering activity-dependent pruning. We propose…
We present a novel class incremental learning approach based on deep neural networks, which continually learns new tasks with limited memory for storing examples in the previous tasks. Our algorithm is based on knowledge distillation and…
Large Language Models (LLMs) have demonstrated impressive reasoning capabilities, but their substantial size often demands significant computational resources. To reduce resource consumption and accelerate inference, it is essential to…
Deep pre-trained Transformer models have achieved state-of-the-art results over a variety of natural language processing (NLP) tasks. By learning rich language knowledge with millions of parameters, these models are usually…
This paper addresses the challenges of high computational cost and slow inference in deploying large language models. It proposes a distillation strategy guided by multiple teacher models. The method constructs several teacher models and…
Since deep learning became a key player in natural language processing (NLP), many deep learning models have been showing remarkable performances in a variety of NLP tasks, and in some cases, they are even outperforming humans. Such high…
Deep neural networks (DNNs) have demonstrated remarkable success in various fields. However, the large number of floating-point operations (FLOPs) in DNNs poses challenges for their deployment in resource-constrained applications, e.g.,…
Pruning is a promising approach to compress deep learning models in order to deploy them on resource-constrained edge devices. However, many existing pruning solutions are based on unstructured pruning, which yields models that cannot…
With the increasing size of large language models, layer pruning has gained increased attention as a hardware-friendly approach for model compression. However, existing layer pruning methods struggle to simultaneously address key practical…
Data-centric distillation, including data augmentation, selection, and mixing, offers a promising path to creating smaller, more efficient student Large Language Models (LLMs) that retain strong reasoning abilities. However, there still…
The use of large transformer-based models such as BERT, GPT, and T5 has led to significant advancements in natural language processing. However, these models are computationally expensive, necessitating model compression techniques that…
Large Language Models (LLMs) have recently achieved remarkable progress by leveraging Reinforcement Learning and extended Chain-of-Thought (CoT) techniques. However, the challenge of performing efficient language reasoning--especially…
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…
Recent large language models have shown promising capabilities in long-form reasoning, following structured chains of thought before arriving at a final answer. However, we observe that these reasoning paths tend to include substantial…
Unstructured pruning remains a powerful strategy for compressing deep neural networks, yet it often demands iterative train-prune-retrain cycles, resulting in significant computational overhead. To address this challenge, we introduce a…
Advancements in Natural Language Processing are heavily reliant on the Transformer architecture, whose improvements come at substantial resource costs due to ever-growing model sizes. This study explores optimization techniques, including…
Knowledge Distillation is becoming one of the primary trends among neural network compression algorithms to improve the generalization performance of a smaller student model with guidance from a larger teacher model. This momentous rise in…