相关论文: Scale Efficient Training for Large Datasets

Learning robust models under adversarial settings is widely recognized as requiring a considerably large number of training samples. Recent work proposes semi-supervised adversarial training (SSAT), which utilizes external unlabeled or…

Large language models (LLMs) have shown strong reasoning capabilities when fine-tuned with reinforcement learning (RL). However, such methods require extensive data and compute, making them impractical under many realistic training budgets.…

Data augmentation has been widely employed to improve the generalization of deep neural networks. Most existing methods apply fixed or random transformations. However, we find that sample difficulty evolves along with the model's…

Researchers have long tried to minimize training costs in deep learning while maintaining strong generalization across diverse datasets. Emerging research on dataset distillation aims to reduce training costs by creating a small synthetic…

Data Augmentation (DA) is known to improve the generalizability of deep neural networks. Most existing DA techniques naively add a certain number of augmented samples without considering the quality and the added computational cost of these…

Recent DNN pruning algorithms have succeeded in reducing the number of parameters in fully connected layers, often with little or no drop in classification accuracy. However, most of the existing pruning schemes either have to be applied…

Speech Enhancement (SE) is essential for improving productivity in remote collaborative environments. Although deep learning models are highly effective at SE, their computational demands make them impractical for embedded systems.…

Training semantic segmenter with synthetic data has been attracting great attention due to its easy accessibility and huge quantities. Most previous methods focused on producing large-scale synthetic image-annotation samples and then…

The emergence of deep and large-scale spiking neural networks (SNNs) exhibiting high performance across diverse complex datasets has led to a need for compressing network models due to the presence of a significant number of redundant…

This paper presents SANA-1.5, a linear Diffusion Transformer for efficient scaling in text-to-image generation. Building upon SANA-1.0, we introduce three key innovations: (1) Efficient Training Scaling: A depth-growth paradigm that enables…

Meta-learning methods typically learn tasks under the assumption that all tasks are equally important. However, this assumption is often not valid. In real-world applications, tasks can vary both in their importance during different…

Recent advances on deep learning models come at the price of formidable training cost. The increasing model size is one of the root causes, but another less-emphasized fact is that data scale is actually increasing at a similar speed as…

The popularity of LLaMA (Touvron et al., 2023a;b) and other recently emerged moderate-sized large language models (LLMs) highlights the potential of building smaller yet powerful LLMs. Regardless, the cost of training such models from…

Dataset distillation extracts a small set of synthetic training samples from a large dataset with the goal of achieving competitive performance on test data when trained on this sample. In this work, we tackle dataset distillation at its…

Instruction tuning has emerged as a critical paradigm for improving the capabilities and alignment of large language models (LLMs). However, existing iterative model-aware data selection methods incur significant computational overhead, as…

Despite the growing integration of deep models into mobile terminals, the accuracy of these models declines significantly due to various deployment interferences. Test-time adaptation (TTA) has emerged to improve the performance of deep…

Pre-trained models have become indispensable for efficiently building models across a broad spectrum of downstream tasks. The advantages of pre-trained models have been highlighted by empirical studies on scaling laws, which demonstrate…

Deep neural networks (DNNs) offer a means of addressing the challenging task of clustering high-dimensional data. DNNs can extract useful features, and so produce a lower dimensional representation, which is more amenable to clustering…

Nowadays, the major challenge in machine learning is the Big Data challenge. The big data problems due to large number of data points or large number of features in each data point, or both, the training of models have become very slow. The…

Low-Rank Adaptation (LoRA) has emerged as one of the most widely used parameter-efficient fine-tuning (PEFT) methods for adapting large language models (LLMs) to downstream tasks. While highly effective in single-task settings, it struggles…