Meta figured out how to make better videos by turning text into images first | allainews.com

Nov. 18, 2023, 12:44 a.m. | Mike Young

AIModels.fyi aimodels.substack.com

The new approach uses "explicit image conditioning" for higher quality video

image images meta quality text video videos

More from aimodels.substack.com / AIModels.fyi

How AlphaFold 3 predicts the structure of all of life’s molecules 3 days, 3 hours ago | aimodels.substack.com

alphafold life molecules

Twitter thinks they killed MLPs. But what are Kolmogorov-Arnold Networks? 1 week, 2 days ago | aimodels.substack.com

functions networks twitter

They taught AI to edit genes with CRISPR. It knocked out 4 skin cancer genes. 1 week, 4 days ago | aimodels.substack.com

cancer crispr designs edit +4

Microsoft's Phi-3 model is cool tech, but local LLMs are useless 2 weeks, 5 days ago | aimodels.substack.com

llm llms microsoft phi +3

How Microsoft's new model turns audio into a realistic talking head 3 weeks, 3 days ago | aimodels.substack.com

audio head microsoft researchers +2

LLMs are secretly good at regression calculations 4 weeks ago | aimodels.substack.com

good llms prompt regression +1

The death of creativity 1 month ago | aimodels.substack.com

creativity death

A change to make diffusion models 80% faster 1 month ago | aimodels.substack.com

change diffusion diffusion models discovery +1

Automatic Prompt Selection for Large Language Models 1 month ago | aimodels.substack.com

algorithm language language models large language +4

Data Engineer

@ Lemon.io | Remote: Europe, LATAM, Canada, UK, Asia, Oceania

View on ai-jobs.net

Artificial Intelligence – Bioinformatic Expert

@ University of Texas Medical Branch | Galveston, TX

View on ai-jobs.net

Lead Developer (AI)

@ Cere Network | San Francisco, US

View on ai-jobs.net

Research Engineer

@ Allora Labs | Remote

View on ai-jobs.net

Ecosystem Manager

@ Allora Labs | Remote

View on ai-jobs.net

Founding AI Engineer, Agents

@ Occam AI | New York

View on ai-jobs.net