相关论文: TWEO: Transformers Without Extreme Outliers Enable…

Intelligent transportation systems (ITS) rely heavily on complete and high-quality spatiotemporal traffic data to achieve optimal performance. Nevertheless, in real-word traffic data collection processes, issues such as communication…

The rapid growth of large language models (LLMs) has heightened the importance of post-training quantization (PTQ) for reducing memory and computation costs. Among PTQ methods, GPTQ has gained significant attention for its efficiency,…

Low-Rank Adaptation (LoRA), as a representative Parameter-Efficient Fine-Tuning (PEFT)method, significantly enhances the training efficiency by updating only a small portion of the weights in Large Language Models (LLMs). Recently,…

Pushing forward the compute efficacy frontier in deep learning is critical for tasks that require frequent model re-training or workloads that entail training a large number of models. We introduce SliceOut -- a dropout-inspired scheme…

Understanding whether deep neural networks are effectively optimized remains challenging, as training occurs in highly nonconvex landscapes and standard metrics provide limited visibility into layer-wise learning quality. This challenge is…

Simulating physical systems using Partial Differential Equations (PDEs) has become an indispensible part of modern industrial process optimization. Traditionally, numerical solvers have been used to solve the associated PDEs, however…

The burgeoning computational demands for training large language models (LLMs) necessitate efficient methods, including quantized training, which leverages low-bit arithmetic operations to reduce costs. While FP8 precision has shown…

Training large language models using 4-bit arithmetic enhances throughput and memory efficiency. Yet, the limited dynamic range of FP4 increases sensitivity to outliers. While NVFP4 mitigates quantization error via hierarchical…

While 4-bit quantization is essential for high-throughput deployment of Large Language Models, activation outliers often lead to significant accuracy degradation due to the restricted dynamic range of low-bit formats. In this paper, we…

We propose a simplified, biologically inspired predictive local learning rule that eliminates the need for global backpropagation in conventional neural networks and membrane integration in event-based training. Weight updates are triggered…

In this paper, we assess the viability of transformer models in end-to-end InfoSec settings, in which no intermediate feature representations or processing steps occur outside the model. We implement transformer models for two distinct…

Pretraining transformers are generally time-consuming. Fully quantized training (FQT) is a promising approach to speed up pretraining. However, most FQT methods adopt a quantize-compute-dequantize procedure, which often leads to suboptimal…

Extreme compression, particularly ultra-low bit precision (binary/ternary) quantization, has been proposed to fit large NLP models on resource-constraint devices. However, to preserve the accuracy for such aggressive compression schemes,…

When neural networks are employed for high-stakes decision-making, it is desirable that they provide explanations for their prediction in order for us to understand the features that have contributed to the decision. At the same time, it is…

Modern machine learning-based recognition approaches require large-scale datasets with large number of labelled training images. However, such datasets are inherently difficult and costly to collect and annotate. Hence there is a great and…

Outlier detection is an important topic in machine learning and has been used in a wide range of applications. Outliers are objects that are few in number and deviate from the majority of objects. As a result of these two properties, we…

DeepFake face swapping enables highly realistic identity forgeries, posing serious privacy and security risks. A common defence embeds invisible perturbations into images, but these are fragile and often destroyed by basic transformations…

Machine learning models implemented in hardware on physical devices may be deployed for a long time. The computational abilities of the device may be limited and become outdated with respect to newer improvements. Because of the size of ML…

The deployment of AI models on low-power, real-time edge devices requires accelerators for which energy, latency, and area are all first-order concerns. There are many approaches to enabling deep neural networks (DNNs) in this domain,…

Out-of-distribution (OOD) detection is essential for deploying machine learning models in open-world and safety-critical scenarios, where test inputs may deviate from the training distribution and overconfident predictions on unknown…