Paper

1.GPT : Improving Language Understanding by Generative Pre-training

post-thumbnail

2.GPT2 - Language Models are Unsupervised Multitask Learners

post-thumbnail

3.ELECTRA : Pre-training Text Encoders As Discriminators Rather than Generators

post-thumbnail

4.FastText - Enriching Word Vectors with Subword Information

post-thumbnail

5.Transformer

post-thumbnail

6.Sequence to Sequence with Attention

post-thumbnail

7.ALBERT: A Lite BERT for Self-supervised Learning of Language Representations

post-thumbnail

8.Positional Encoding

post-thumbnail

9.Get To The Point : Summarization with Pointer-Generator Network's

post-thumbnail

10.BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding

post-thumbnail

11.ResNet - Deep Residual Learning for Image Recognition

post-thumbnail

12.GAN - Generative Adversarial Nets

post-thumbnail

13.SimCSE : Simple Contrastive Learning of Sentence Embeddings

post-thumbnail

14.Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks

post-thumbnail

15.Object Tracking + Simple Online and Realtime Tracking : SORT

post-thumbnail

16.DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRF

post-thumbnail

17.DiffCSE: Difference-based Contrastive Learning for Sentence Embeddings

post-thumbnail

18.TSDAE: Using Transformer-based Sequential Denoising Auto-Encoder for Unsupervised Sentence Embedding Learning

post-thumbnail

19.Vision Transformer & ViTPose

post-thumbnail

20.Transformer-XL : Attentive Language Models Beyond a Fixed-Length Context

post-thumbnail

21.MobileViT - Version 1, 2

post-thumbnail

22.Luna: Linear Unified Nested Attention

post-thumbnail

23.Multi-head or Single-head? An Empirical Comparison for Transformer Training

post-thumbnail

24.ClusterFormer: Neural Clustering Attention for Efficient and Effective Transformer

post-thumbnail

25.Generating Long Sequences with Sparse Transformers

post-thumbnail

26.DA-Transformer: Distance-aware Transformer

post-thumbnail

27.Linear Complexity Attention

post-thumbnail

28.EfficientViT: Multi-Scale Linear Attention for High-Resolution Dense Prediction

post-thumbnail