By 2018 or so, on a dedicated GPU, I could get 10-20 fps https://
vimeo.com/382088640#t=58s Current SOTA are all diffusion models, which are multi-step, hence a bit slower again. I bet there will be real-time variants in a year or two.
RESEARCH
-
Real-time GPU rendering and diffusion models performance evolution
By
–
-
The AI Apocalypse: A Scorecard
By
–
The AI Apocalypse: A Scorecard https://
bit.ly/3rZiLua #AI #MachineLearning #DeepLearning #LLMs #DataScience -
AI Industry and Researchers Issue Extinction Risk Warning Statement
By
–
#AI industry and researchers sign statement warning of ‘extinction’ risk https://
cnn.it/3C0kqBB #ethics #FutureofWork -
Open Buildings: AI and Deep Learning for Data Science
By
–
Open Buildings https://
bit.ly/3s3xhRJ #AI #MachineLearning #DeepLearning #LLMs #DataScience -
Stanford CS324 LLM Course: Comprehensive Notes on Large Language Models
By
–
[Lecture notes] Stanford CS324 – Large Language Models Excellent notes on various topics related to large language models: fundamentals of language models, capabilities of LLMs, data behind LLMs, modeling, training, scaling laws, selective architectures, task adaptation, and
-
Geoffrey Hinton: AI Systems May Develop or Already Have Emotions
By
–
AI researcher Geoffrey Hinton thinks AI has or will have emotions https://
bit.ly/3KrAAIQ
#AI #MachineLearning #DeepLearning #LLMs #DataScience -
Are We Using AI to Solve the Wrong Problems?
By
–
I wonder if people use artificial intelligence on a large scale to solve the wrong problems.
-
Are We Using AI to Solve the Wrong Problems?
By
–
Most people have been solving the wrong problems. I wonder if people use artificial intelligence to do more of it.
-
Clarifying Terminology: Fine-tuning vs Training for Text Classification
By
–
This is so different from what we're seeing that I wonder whether we're talking about the same things. The terminology in the field is really confusing now. Let's say I want to do text classification. Would you call training a model for that 'fine-tuning'? One way to do it text
-
Cultural emotional expression data scaling across modalities
By
–
Can I join? Been thinking quite a bit about scaling our cultural emotional expression data, the tricky part has been that cultures use different weightings of face/gesture/voice/context for the same expr. https://
arxiv.org/abs/2103.04262 https://
arxiv.org/abs/2112.05267
v1
… https://
frontiersin.org/articles/10.33
89/fnint.2021.699667/full
…