Johannes Welbl and colleagues, 2017
We propose a novel task to encourage the development of models for text understanding across multiple documents.
Don't Just Read it – Explore It
We propose a novel task to encourage the development of models for text understanding across multiple documents.
We present MiniGPT-4, which aligns a frozen visual encoder with a frozen advanced language model using one projection layer.
We conduct a systematic and comprehensive study on vision-language instruction tuning based on the pretrained BLIP-2 models.
We introduce Voyager, the first LLM-powered embodied lifelong learning agent in Minecraft.
We build a system called Visual ChatGPT, incorporating different Visual Foundation Models.
We explore a new class of diffusion models based on the transformer architecture.
We introduce Graph of Thoughts: a framework that advances prompting capabilities in large language models.
To accelerate sampling, we present denoising diffusion implicit models.
We present Tacotron, an end-to-end generative text-to-speech model that synthesizes speech directly from characters.
We introduce the Differentiable Digital Signal Processing library, which enables direct integration of classic signal processing elements with deep learning methods.
We present an efficient gradient estimator that replaces the non-differentiable sample from a categorical distribution with a differentiable sample.
We describe a scalable end-to-end tree boosting system called XGBoost.