Home›Papers
Papers
Papers
Papers that changed AI, with a plain-language explainer for each.
Total 52 · Clear filters
- 2022
Holistic Evaluation of Language Models (HELM)
arXiv
A 2022 paper by Percy Liang, Rishi Bommasani, Tony Lee and many co-authors that ran 30 language models through the same 42 scenarios and seven metrics, turning scattered benchmarks into one standardized evaluation.
- 2022
LAION-5B: An open large-scale dataset for training next generation image-text models
arXiv
LAION-5B is an openly available dataset of 5.85 billion CLIP-filtered image-text pairs, released so that researchers outside a handful of labs could study and reproduce large vision-language models.
- 2022
Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding (Imagen)
arXiv
Imagen is a text-to-image diffusion model that uses a large pretrained language model to encode prompts; it reached a zero-shot FID of 7.27 on COCO and introduced the DrawBench benchmark.
- 2022
Training Compute-Optimal Large Language Models (Chinchilla)
NeurIPS
A DeepMind study showing that, for a fixed computing budget, language models should be trained on far more data than was then standard; its 70-billion-parameter Chinchilla beat larger contemporaries.
- 2021
Program Synthesis with Large Language Models (MBPP)
arXiv
A 2021 arXiv paper by Austin, Odena, Nye and eight other authors that introduced MBPP, a benchmark of 974 short Python programming tasks, and measured how language models from 244M to 137B parameters turn natural-language descriptions into working code.
- 2021
Evaluating Large Language Models Trained on Code (Codex / HumanEval)
arXiv
A 2021 paper from OpenAI introduces Codex, a GPT model fine-tuned on public GitHub code, and HumanEval, an evaluation set that judges generated Python programs by whether they work rather than by how closely they match a reference.
- 2021
Zero-Shot Text-to-Image Generation (DALL·E)
arXiv
A 2021 OpenAI paper describing a single 12-billion-parameter autoregressive transformer trained on 250 million image-text pairs, which generates images from text and, evaluated zero-shot, is competitive with domain-specific models.
- 2021
Learning Transferable Visual Models From Natural Language Supervision (CLIP)
ICML
CLIP is an OpenAI model trained on 400 million image-text pairs to map pictures and sentences into one shared space, so it can classify images zero-shot from a written description.
- 2020
The Pile: An 800GB Dataset of Diverse Text for Language Modeling
arXiv
The Pile is an 825 GiB English text dataset of 22 combined sources, released by EleutherAI on 31 December 2020 with an arXiv paper. It became the training data for several of the group's open models.
- 2019
C4: Colossal Clean Crawled Corpus (T5 paper)
JMLR
A 2019 paper that casts every language task as text-to-text, systematically compares transfer-learning choices, releases the C4 corpus and models, and reports state-of-the-art results on summarization, question answering, and classification.
- 2019
Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer (T5)
JMLR
A 2019 Google paper that frames every language task as text in, text out, using one encoder-decoder Transformer and one training setup. It also introduced the C4 dataset, and the released T5 models became common research starting points.
- 2019
SuperGLUE: A Stickier Benchmark for General-Purpose Language Understanding Systems
arXiv
SuperGLUE is a benchmark for general-purpose language understanding, released in 2019 as a harder successor to GLUE. It bundles eight tasks, a single-number metric, an analysis toolkit and a public leaderboard.
- 2018
GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding
arXiv
GLUE is a benchmark and analysis platform that evaluates natural language understanding models across a diverse set of existing tasks, with an online comparison platform and a hand-crafted diagnostic suite for linguistic analysis.
- 2016
WaveNet: A Generative Model for Raw Audio
arXiv
WaveNet is a deep neural network that generates raw audio waveforms one sample at a time, predicting each sample from all the ones before it. Used for text-to-speech, it was rated by listeners as more natural than the systems it was compared with.
- 2016
SQuAD: 100,000+ Questions for Machine Comprehension of Text
arXiv
SQuAD is a reading-comprehension dataset of more than 100,000 crowdworker questions on Wikipedia articles, each answered by a span of its passage. Released in 2016, it gave machine comprehension a large, freely available benchmark with a measured human ceiling.
- 2014
Show and Tell: A Neural Image Caption Generator
arXiv
A 2014 paper by Vinyals and colleagues that trained a single deep network to turn a photograph into a sentence, reporting a BLEU-1 score of 59 on Pascal against 25 for the previous state of the art.
- 2014
GloVe: Global Vectors for Word Representation
EMNLP 2014
GloVe is a 2014 method that learns word vectors by factorising global word co-occurrence counts. Released together with pre-trained vectors, it became, alongside word2vec, one of the two standard ways of producing static word embeddings.
- 2014
Microsoft COCO: Common Objects in Context
arXiv
A 2014 paper introducing Microsoft COCO, a large dataset of everyday scenes in which common objects are labeled with per-instance segmentations, built to study object recognition as part of scene understanding.
- 2011
Deep Sparse Rectifier Neural Networks
A 2011 paper by Glorot, Bordes and Bengio reporting that deep networks built from rectifying neurons match or beat tanh networks and reach their best performance without unsupervised pre-training on large labelled supervised tasks.
- 2009
ImageNet: A Large-Scale Hierarchical Image Database
CVPR
The 2009 paper introduced ImageNet, a large, cleanly labelled image database organised by the WordNet hierarchy. It later became the basis of an annual benchmark, the ImageNet Large Scale Visual Recognition Challenge.