Papers

2023

LongNet: Scaling Transformers to 1,000,000,000 Tokens

Pre-Trained Image Processing Transformer

Album Storytelling with Iterative Story-aware Captioning and Large Language Models

Using Natural Language and Program Abstractions to Instill Human Inductive Biases in Machines

Voyager: An Open-Ended Embodied Agent with Large Language Models

MEGABYTE: Predicting Million-byte Sequences with Multiscale Transformers

A Neural Corpus Indexer for Document Retrieval

GeneGPT: Augmenting Large Language Models with Domain Tools for Improved Access to Biomedical Information *

Giving BERT a Calculator *

Check Your Facts and Try Again: Improving Large Language Models with External Knowledge and Automated Feedback *

How well do Large Language Models perform in Arithmetic tasks? *

ToolCoder: Teach Code Generation Models to use API search tools *

TaskMatrix.AI: Completing Tasks by Connecting Foundation Models with Millions of APIs *

Small Models are Valuable Plug-ins for Large Language Models *

API-Bank: A Benchmark for Tool-Augmented LLMs *

GeneGPT: Augmenting Large Language Models with Domain Tools for Improved Access to Biomedical Information *

ART: Automatic multi-step reasoning and tool-use for large language models *

TALM: Tool Augmented Language Models *

Tool Learning with Foundation Models *

Toolformer: Language Models Can Teach Themselves to Use Tools *

LoRA: Low-Rank Adaptation of Large Language Models

Scaling Transformer to 1M tokens and beyond with RMT

HuggingGPT: Solving AI Tasks with ChatGPT and its Friends in Hugging Face

Sparks of Artificial General Intelligence: Early experiments with GPT-4

(Ada) Human-Timescale Adaptation in an Open-Ended Task Space

2022

(VPT) Video PreTraining: Learning to Act by Watching Unlabeled Online Videos

(OPT) Open Pre-trained Transformer Language Models

(LaMDA) Language Models for Dialog Applications

Attention Is All You Need

(Imagen) Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding

(DALLE2) Hierarchical Text-Conditional Image Generation with CLIP Latents

(GATO) A Generalist Agent

Thinking Fast and Slow in Ai

2021

(Attribute2Font) Creating Fonts You Want From Attributes

(DALLE) Zero-Shot Text-to-Image Generation

(GPT3) Language Models are Few-Shot Learners

(MNIST) Backpropagation Applied to Handwritten Zip Code Recognition