相关论文: HEAT: Hardware-Efficient Automatic Tensor Decompos…

Transformer-based models, such as BERT, have been widely applied in a wide range of natural language processing tasks. However, one inevitable side effect is that they require massive memory storage and inference cost when deployed in…

Bidirectional Encoder Representations from Transformers (BERT) reach state-of-the-art results in a variety of Natural Language Processing tasks. However, understanding of their internal functioning is still insufficient and unsatisfactory.…

Most currently used tensor regression models for high-dimensional data are based on Tucker decomposition, which has good properties but loses its efficiency in compressing tensors very quickly as the order of tensors increases, say greater…

Transformer-based detectors have advanced small-object detection, but they often remain inefficient and vulnerable to background-induced query noise, which motivates deep decoders to refine low-quality queries. We present HELP…

Advancements in monaural speech enhancement (SE) techniques have greatly improved the perceptual quality of speech. However, integrating these techniques into automatic speech recognition (ASR) systems has not yielded the expected…

Increasing model size when pretraining natural language representations often results in improved performance on downstream tasks. However, at some point further model increases become harder due to GPU/TPU memory limitations and longer…

Nonconvex sparse learning plays an essential role in many areas, such as signal processing and deep network compression. Iterative hard thresholding (IHT) methods are the state-of-the-art for nonconvex sparse learning due to their…

Conjugate heat transfer (CHT) analyses are vital for the design of many energy systems. However, high-fidelity CHT numerical simulations are computationally intensive, which limits their applications such as design optimization, where…

Pre-trained Transformer models such as BERT have shown great success in a wide range of applications, but at the cost of substantial increases in model complexity. Quantization-aware training (QAT) is a promising method to lower the…

Transformer models have achieved state-of-the-art performance across a wide range of machine learning tasks. There is growing interest in training transformers on resource-constrained edge devices due to considerations such as privacy,…

We propose a scalable tensorization framework for neural network compression based on slice-wise feature distillation. Unlike conventional tensor decomposition methods that rely on costly global finetuning, our approach decomposes the…

This paper presents a novel methodology for fast simulation and analysis of transient heat transfer. The proposed methodology is suitable for real-time applications owing to (i) establishing the solution method from the viewpoint of…

The highly popular Transformer architecture, based on self-attention, is the foundation of large pretrained models such as BERT, that have become an enduring paradigm in NLP. While powerful, the computational resources and time required to…

End-to-end automatic speech recognition (ASR), unlike conventional ASR, does not have modules to learn the semantic representation from speech encoder. Moreover, the higher frame-rate of speech representation prevents the model to learn the…

This work considers a computationally and statistically efficient parameter estimation method for a wide class of latent variable models---including Gaussian mixture models, hidden Markov models, and latent Dirichlet allocation---which…

With the increasing implementation of machine learning models on edge or Internet-of-Things (IoT) devices, deploying advanced models on resource-constrained IoT devices remains challenging. Transformer models, a currently dominant neural…

We introduce the CUDA Tensor Transpose (cuTT) library that implements high-performance tensor transposes for NVIDIA GPUs with Kepler and above architectures. cuTT achieves high performance by (a) utilizing two GPU-optimized transpose…

Decomposing tensors into orthogonal factors is a well-known task in statistics, machine learning, and signal processing. We study orthogonal outer product decompositions where the factors in the summands in the decomposition are required to…

Fine-tuning pre-trained transformers is a powerful technique for enhancing the performance of base models on specific tasks. From early applications in models like BERT to fine-tuning Large Language Models (LLMs), this approach has been…

Transfer learning in natural language processing (NLP), as realized using models like BERT (Bi-directional Encoder Representation from Transformer), has significantly improved language representation with models that can tackle challenging…