Papers

Important Papers

Name	Submission Date	Source	Type	Organization	Note
ImageNet Classification with Deep Convolutional Neural Networks (AlexNet)	2012	AlexNet Paper	Computer Vision		AlexNet
Efficient Estimation of Word Representations in Vector Space (Word2Vec)	2013/01/16	arxiv:1301.3781	Natural Language Processing		Word2Vec
Playing Atari with Deep Reinforcement Learning (DQN)	2013/12/19	arxiv:1312.5602			DQN
Generative Adversarial Networks (GAN)	2014/06/10	arxiv:1406.2661			GAN
Very Deep Convolutional Networks for Large-Scale Image Recognition (VGGNet)	2014/09/04	arxiv:1409.1556	Computer Vision		VGGNet
Sequence to Sequence Learning with Neural Networks (Seq2Seq)	2014/09/10	arxiv:1409.3215	Natural Language Processing		Seq2Seq
Adam: A Method for Stochastic Optimization)	2014/12/22	arxiv:1412.6980			Adam
Deep Residual Learning for Image Recognition (ResNet)	2015/12/10	arxiv:1512.03385	Computer Vision		ResNet
Going Deeper with Convolutions (GoogleNet)	2015/12/10	arxiv:1409.4842	Computer Vision	Google	GoogleNet
Asynchronous Methods for Deep Reinforcement Learning (A3C)	2016/02/04	arxiv:1602.01783			A3C
WaveNet: A Generative Model for Raw Audio	2016/09/12	arxiv:1609.03499	Audio		WaveNet
Attention Is All You Need (Transformer)	2017/06/12	arxiv:1706.03762	Natural Language Processing	Google	Influential paper that introduced Transformer
Proximal Policy Optimization Algorithms (PPO)	2017/07/20	arxiv:1707.06347			PPO
Improving Language Understanding by Generative Pre-Training (GPT)	2018	paper source	Natural Language Processing	OpenAI	GPT
Deep contextualized word representations (ELMo)	2018/02/15	arxiv:1802.05365	Natural Language Processing		ELMo
GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding	2018/04/20	arxiv:1804.07461 website	Natural Language Processing		GLUE
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding	2018/10/11	arxiv:1810.04805	Natural Language Processing	Google	BERT
Transformer-XL: Attentive Language Models Beyond a Fixed-Length Context	2019/01/09	arxiv:1901.02860 github			Transformer-XL
Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model (MuZero)	2019/11/19	arxiv:1911.08265			MuZero
Language Models are Few-Shot Learners (GPT-3)	2020/05/28	arxiv:2005.14165	Natural Language Processing	OpenAI	GPT-3
An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale (ViT)	2020/10/22	arxiv:2010.11929 GitHub	Computer Vision	Google	Vision Transformer (ViT)
Learning Transferable Visual Models From Natural Language Supervision (CLIP)	2021/02/26	arxiv:2103.00020 Blog Post	Computer Vision	OpenAI	CLIP (Contrastive Language-Image Pre-Training)
MobileViT: Light-weight, General-purpose, and Mobile-friendly Vision Transformer	2021/10/05	arxiv:2110.02178 GitHub	Computer Vision	Apple	MobileViT
LaMDA: Language Models for Dialog Applications	2022/01/20	arxiv:2201.08239	Natural Language Processing	Google	LaMDA
Block-Recurrent Transformers	2022/03/11	arxiv:2203.07852
Memorizing Transformers	2022/03/16	arxiv:2203.08913
STaR: Bootstrapping Reasoning With Reasoning	2022/03/28	arxiv:2203.14465			STaR

Other Papers

Name	Submission Date	Source	Type	Organization	Note
Dreamix: Video Diffusion Models are General Video Editors	2023/02/03	arxiv:2302.01329 blog post		Google	Dreamix
FLAME: A small language model for spreadsheet formulas	2023/01/31	arxiv:2301.13779		Microsoft	FLAME
SingSong: Generating musical accompaniments from singing	2023/01/30	arxiv:2301.12662 blog post	Audio		SingSong
MusicLM: Generating Music From Text	2023/01/26	arxiv:2301.11325 blog post	Audio	Google	MusicLM
Mastering Diverse Domains through World Models (DreamerV3)	2023/01/10	arxiv:2301.04104v1 blogpost		DeepMind	DreamerV3
Muse: Text-To-Image Generation via Masked Generative Transformers	2023/01/02	arxiv:2301.00704 blog post	Computer Vision	Google	Muse
Constitutional AI: Harmlessness from AI Feedback	2021/12/12	arxiv:2212.08073	Natural Language Processing	Anthropic	Constitutional AI, Claude
Improving language models by retrieving from trillions of tokens (RETRO)	2021/12/08	arxiv:2112.04426 Blog post	Natural Language Processing	OpenAI	RETRO (Retrieval Enhanced Transformer)
InstructPix2Pix: Learning to Follow Image Editing Instructions	2021/11/17	arxiv:2211.09800 Blog Post	Computer Vision	UC Berkley	InstructPix2Pix
REALM: Retrieval-Augmented Language Model Pre-Training	2020/02/10	arxiv:2002.08909 Blog Post	Natural Language Processing	Google	REALM