Related papers: ColBERT-Zero: To Pre-train Or Not To Pre-train Col…

Generative pre-trained models have demonstrated remarkable effectiveness in language and vision domains by learning useful representations. In this paper, we extend the scope of this effectiveness by showing that visual robot manipulation…

Pre-trained Language Models (PLMs) have been successful for a wide range of natural language processing (NLP) tasks. The state-of-the-art of PLMs, however, are extremely large to be used on edge devices. As a result, the topic of model…

He et al. (2018) have called into question the utility of pre-training by showing that training from scratch can often yield similar performance to pre-training. We show that although pre-training may not improve performance on traditional…

In this paper, we study how the intrinsic nature of pre-training data contributes to the fine-tuned downstream performance. To this end, we pre-train different transformer-based masked language models on several corpora with certain…

Experiments with pre-trained models such as BERT are often based on a single checkpoint. While the conclusions drawn apply to the artifact tested in the experiment (i.e., the particular instance of the model), it is not always clear whether…

Recent studies pointed out that knowledge distillation (KD) suffers from two degradation problems, the teacher-student gap and the incompatibility with strong data augmentations, making it not applicable to training state-of-the-art models,…

Pre-training has marked numerous state of the arts in high-level computer vision, while few attempts have ever been made to investigate how pre-training acts in image processing systems. In this paper, we tailor transformer-based…

Knowledge distillation (KD) is one of the prominent techniques for model compression. In this method, the knowledge of a large network (teacher) is distilled into a model (student) with usually significantly fewer parameters. KD tries to…

Recent developments in machine translation and multilingual text generation have led researchers to adopt trained metrics such as COMET or BLEURT, which treat evaluation as a regression problem and use representations from multilingual…

Pre-training has exhibited notable benefits to downstream tasks by boosting accuracy and speeding up convergence, but the exact reasons for these benefits still remain unclear. To this end, we propose to quantitatively and explicitly…

The pre-trained language model is trained on large-scale unlabeled text and can achieve state-of-the-art results in many different downstream tasks. However, the current pre-trained language model is mainly concentrated in the Chinese and…

Recent years have witnessed the promise of coupling machine learning methods and physical domain-specific insights for solving scientific problems based on partial differential equations (PDEs). However, being data-intensive, these methods…

In this paper, we explore the possibility of building a unified foundation model that can be adapted to both vision-only and text-only tasks. Starting from BERT and ViT, we design a unified transformer consisting of modality-specific…

Web-crawled pretraining datasets underlie the impressive "zero-shot" evaluation performance of multimodal models, such as CLIP for classification/retrieval and Stable-Diffusion for image generation. However, it is unclear how meaningful the…

Deep pre-training and fine-tuning models (like BERT, OpenAI GPT) have demonstrated excellent results in question answering areas. However, due to the sheer amount of model parameters, the inference speed of these models is very slow. How to…

Knowledge distillation~(KD) has been proved effective for compressing large-scale pre-trained language models. However, existing methods conduct KD statically, e.g., the student model aligns its output distribution to that of a selected…

Learning program representations has been the core prerequisite of code intelligent tasks such as code search and code clone detection. The state-of-the-art pre-trained models such as CodeBERT require the availability of large-scale code…

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…

Vulnerability analysis is crucial for software security. This work focuses on using pre-training techniques to enhance the understanding of vulnerable code and boost vulnerability analysis. The code understanding ability of a pre-trained…

Knowledge Distillation (KD) has emerged as an effective model compression technique in deep learning, enabling the transfer of knowledge from a large teacher model to a compact student model. While KD has demonstrated significant success,…