Related papers: InterBERT: Vision-and-Language Interaction for Mul…

Language model pretraining has led to significant performance gains but careful comparison between different approaches is challenging. Training is computationally expensive, often done on private datasets of different sizes, and, as we…

Multilingual Language Models (\MLLMs) such as mBERT, XLM, XLM-R, \textit{etc.} have emerged as a viable option for bringing the power of pretraining to a large number of languages. Given their success in zero-shot transfer learning, there…

In recent years, self-supervised pre-training methods have gained significant traction in learning high-level information from raw speech. Among these methods, HuBERT has demonstrated SOTA performance in automatic speech recognition (ASR).…

BERT-type structure has led to the revolution of vision-language pre-training and the achievement of state-of-the-art results on numerous vision-language downstream tasks. Existing solutions dominantly capitalize on the multi-modal inputs…

In recent years, multimodal learning has become essential in robotic vision and information fusion, especially for understanding human behavior in complex environments. However, current methods struggle to fully leverage the textual…

Motivated by the success of masked language modeling~(MLM) in pre-training natural language processing models, we propose w2v-BERT that explores MLM for self-supervised speech representation learning. w2v-BERT is a framework that combines…

We present a unified perspective on tackling various human-centric video tasks by learning human motion representations from large-scale and heterogeneous data resources. Specifically, we propose a pretraining stage in which a motion…

Despite the development of pre-trained language models (PLMs) significantly raise the performances of various Chinese natural language processing (NLP) tasks, the vocabulary for these Chinese PLMs remain to be the one provided by Google…

In this demonstration, we present an efficient BERT-based multi-task (MT) framework that is particularly suitable for iterative and incremental development of the tasks. The proposed framework is based on the idea of partial fine-tuning,…

Images in the medical domain are fundamentally different from the general domain images. Consequently, it is infeasible to directly employ general domain Visual Question Answering (VQA) models for the medical domain. Additionally, medical…

Recently, self-supervised pre-training has shown significant improvements in many areas of machine learning, including speech and NLP. We propose using large self-supervised pre-trained models for both audio and text modality with…

Pre-trained models are widely used in the tasks of natural language processing nowadays. However, in the specific field of text simplification, the research on improving pre-trained models is still blank. In this work, we propose a…

Automatic emotion recognition plays a key role in computer-human interaction as it has the potential to enrich the next-generation artificial intelligence with emotional intelligence. It finds applications in customer and/or representative…

Although deep pre-trained language models have shown promising benefit in a large set of industrial scenarios, including Click-Through-Rate (CTR) prediction, how to integrate pre-trained language models that handle only textual signals into…

We introduce a self-supervised vision representation model BEiT, which stands for Bidirectional Encoder representation from Image Transformers. Following BERT developed in the natural language processing area, we propose a masked image…

A rising interest in the modality extension of foundation language models warrants discussion on the most effective, and efficient, multimodal training approach. This work focuses on neural machine translation (NMT) and proposes a joint…

This paper presents UniBERT, a compact multilingual language model that uses an innovative training framework that integrates three components: masked language modeling, adversarial training, and knowledge distillation. Pre-trained on a…

As multimodal large models (MLLMs) continue to advance across challenging tasks, a key question emerges: What essential capabilities are still missing? A critical aspect of human learning is continuous interaction with the environment --…

BERT-based models are currently used for solving nearly all Natural Language Processing (NLP) tasks and most often achieve state-of-the-art results. Therefore, the NLP community conducts extensive research on understanding these models, but…

Embedding models are pivotal in industrial information retrieval systems like search and advertising. However, existing pretrained models often exhibit fixed architectures and embedding dimensionalities, posing significant challenges when…