Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding
Chitwan Saharia, William Chan, Saurabh Saxena, Lala Li, Jay Whang, Emily Denton..
PDF
SearchScholar
Summary
Imagen builds on the power of large transformer language models in understanding text. It hinges on the strength of diffusion models in high-fidelity image generation. Imagen achieves a new state-of-the-art FID score of 7.27 on the COCO dataset.
Published on Tue May 24 2022
Large Language Models are Zero-Shot Reasoners
Takeshi Kojima, Shixiang Shane Gu, Machel Reid, Yutaka Matsuo, Yusuke Iwasawa
PDF
SearchScholar
Summary
Pretrained large language models (LLMs) are widely used in many sub-fields of natural language processing (NLP) These successes are often attributed to LLMs' ability for few-shot learning. We show that LLMs are decent zero-shot reasoners by simply adding Let's think step by step'' before each answer.
Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models
Aarohi Srivastava, Abhinav Rastogi, Abhishek Rao, Abu Awal Md Shoeb, Abubakar Abid, Adam Fisch ...
PDF
SearchScholar
Summary
Language models demonstrate both quantitative improvement and new qualitative capabilities with increasing scale. Despite their potentially transformative impact, these new capabilities are as yet poorly characterized. To address this challenge, we introduce the Beyond the Imitation Game benchmark (BIG-bench)
Toward a realistic model of speech processing in the brain with self-supervised learning
Juliette Millet, Charlotte Caucheteux, Pierre Orhan, Yves Boubenec, Alexandre Gramfort, Ewan Dunbar, See More ...
PDF
SearchScholar
Summary
Several deep neural networks have recently been shown to generate activations similar to those of the brain in response to the same input. These algorithms, however, remain largely implausible. We hypothesize that self-supervised algorithms trained on the raw waveform constitute a promising candidate.