Search Results
Attention Is All You Need
huggingface/transformers
•
•
NeurIPS 2017
The dominant sequence transduction models are based on complex recurrent or convolutional neural networks in an encoder-decoder configuration.
Ranked #2 on
Multimodal Machine Translation
on Multi30K
(BLUE (DE-EN) metric)
ColBERT: Using BERT Sentence Embedding in Parallel Neural Networks for Computational Humor
The proposed technical method initiates by separating sentences of the given text and utilizing the BERT model to generate embeddings for each one.
Supervised Multimodal Bitransformers for Classifying Images and Text
Self-supervised bidirectional transformer models such as BERT have led to dramatic improvements in a wide variety of textual classification tasks.
Ranked #1 on
Natural Language Inference
on V-SNLI
(using extra training data)
DeeBERT: Dynamic Early Exiting for Accelerating BERT Inference
huggingface/transformers
•
•
ACL 2020
Large-scale pre-trained language models such as BERT have brought significant improvements to NLP applications.
Transformers: State-of-the-Art Natural Language Processing
huggingface/transformers
•
•
EMNLP 2020
Transformer architectures have facilitated building higher-capacity models and pretraining has made it possible to effectively utilize this capacity for a wide variety of tasks.
Visual Instruction Tuning
huggingface/transformers
•
•
NeurIPS 2023
Instruction tuning large language models (LLMs) using machine-generated instruction-following data has improved zero-shot capabilities on new tasks, but the idea is less explored in the multimodal field.
Ranked #4 on
Visual Question Answering
on BenchLMM
A Study on Knowledge Distillation from Weak Teacher for Scaling Up Pre-trained Language Models
Distillation from Weak Teacher (DWT) is a method of transferring knowledge from a smaller, weaker teacher model to a larger student model to improve its performance.
Multilingual Denoising Pre-training for Neural Machine Translation
This paper demonstrates that multilingual denoising pre-training produces significant performance gains across a wide variety of machine translation (MT) tasks.
Improving the Domain Adaptation of Retrieval Augmented Generation (RAG) Models for Open Domain Question Answering
We propose \textit{RAG-end2end}, an extension to RAG, that can adapt to a domain-specific knowledge base by updating all components of the external knowledge base during training.
wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations
huggingface/transformers
•
•
NeurIPS 2020
We show for the first time that learning powerful representations from speech audio alone followed by fine-tuning on transcribed speech can outperform the best semi-supervised methods while being conceptually simpler.
Ranked #1 on
Speech Recognition
on TIMIT
(using extra training data)
