Related papers: DeeBERT: Dynamic Early Exiting for Accelerating BE…

Deep neural networks (DNNs) have been successfully applied in various fields. In DNNs, a large number of multiply-accumulate (MAC) operations are required to be performed, posing critical challenges in applying them in resource-constrained…

Pretrained language models like BERT have achieved good results on NLP tasks, but are impractical on resource-limited devices due to memory footprint. A large fraction of this footprint comes from the input embeddings with large input…

The recently proposed BERT has shown great power on a variety of natural language understanding tasks, such as text classification, reading comprehension, etc. However, how to effectively apply BERT to neural machine translation (NMT) lacks…

With the yearning for deep learning democratization, there are increasing demands to implement Transformer-based natural language processing (NLP) models on resource-constrained devices for low-latency and high accuracy. Existing BERT…

Adaptive inference is a simple method for reducing inference costs. The method works by maintaining multiple classifiers of different capacities, and allocating resources to each test instance according to its difficulty. In this work, we…

Natural Language Processing (NLP) has witnessed a transformative leap with the advent of transformer-based architectures, which have significantly enhanced the ability of machines to understand and generate human-like text. This paper…

Diffusion models produce high quality images but inference is costly due to many denoising steps and heavy matrix operations. We present DiffPro, a post-training, hardware-faithful framework that works with the exact integer kernels used in…

Neural language representation models such as BERT, pre-trained on large-scale unstructured corpora lack explicit grounding to real-world commonsense knowledge and are often unable to remember facts required for reasoning and inference.…

Recent advances in natural language processing (NLP) have been driven bypretrained language models like BERT, RoBERTa, T5, and GPT. Thesemodels excel at understanding complex texts, but biomedical literature, withits domain-specific…

Transformer-based QA models use input-wide self-attention -- i.e. across both the question and the input passage -- at all layers, causing them to be slow and memory-intensive. It turns out that we can get by without input-wide…

Since their initial release, BERT models have demonstrated exceptional performance on a variety of tasks, despite their relatively small size (BERT-base has ~100M parameters). Nevertheless, the architectural choices used in these models are…

Recently, pre-trained Transformer based language models, such as BERT, have shown great superiority over the traditional methods in many Natural Language Processing (NLP) tasks. However, the computational cost for deploying these models is…

Diffusion-based large language models (dLLMs) have emerged as a promising alternative to autoregressive (AR) LLMs, leveraging denoising-based generation to enable inherent parallelism. Even more and more open-sourced dLLM models emerge, yet…

As a pre-trained Transformer model, BERT (Bidirectional Encoder Representations from Transformers) has achieved ground-breaking performance on multiple NLP tasks. On the other hand, Boosting is a popular ensemble learning technique which…

Biomedical text mining is becoming increasingly important as the number of biomedical documents rapidly grows. With the progress in natural language processing (NLP), extracting valuable information from biomedical literature has gained…

We introduce EELBERT, an approach for compression of transformer-based models (e.g., BERT), with minimal impact on the accuracy of downstream tasks. This is achieved by replacing the input embedding layer of the model with dynamic, i.e.…

This paper presents a performance study of transformer language models under different hardware configurations and accuracy requirements and derives empirical observations about these resource/accuracy trade-offs. In particular, we study…

Inference latency and trustworthiness of Deep Neural Networks (DNNs) are the bottlenecks in deploying them in critical applications like sensitive tasks. Early Exit (EE) DNNs overcome the latency issues by allowing samples to exit from…

As a simple technique to accelerate inference of large-scale pre-trained models, early exiting has gained much attention in the NLP community. It allows samples to exit early at internal classifiers without passing through the entire model.…

We explore advanced fine-tuning techniques to boost BERT's performance in sentiment analysis, paraphrase detection, and semantic textual similarity. Our approach leverages SMART regularization to combat overfitting, improves hyperparameter…