MACHINE LEARNING - AI Dynamics

Long Context with RoPE Embeddings

By

@replicate

–

21 July 2023 3h52

Long context with RoPE embeddings

→ View original post on X — @replicate

21 July 2023

Numeric representation for efficient fused multiply-add hardware

By

@id_aa_carmack

–

21 July 2023 3h52

Conventional numbers are easy to add/subtract and logs are easy to multiply/divide — I wonder if there is a numeric representation that could support more efficient hardware fused multiply-adds for matrix multiplies.

→ View original post on X — @id_aa_carmack

21 July 2023

TokenFlow: Consistent Diffusion Features for Video Editing

By

@_akhaliq

–

21 July 2023 3h49

TokenFlow: Consistent Diffusion Features for Consistent Video Editing

paper page: https://t.co/t094Un4uNm

The generative AI revolution has recently expanded to videos. Nevertheless, current state-of-the-art video models are still lagging behind image models in terms of visual… pic.twitter.com/PVtfrLyLma
— AK (@_akhaliq) 21 juillet 2023

TokenFlow: Consistent Diffusion Features for Consistent Editing paper page: https://
huggingface.co/papers/2307.10
373
… The generative AI revolution has recently expanded to videos. Nevertheless, current state-of-the-art video models are still lagging behind image models in terms of visual

→ View original post on X — @_akhaliq

21 July 2023

Meta-Transformer: Unified Framework for Multimodal Learning

By

@ceobillionaire

–

21 July 2023 3h48

Meta-Transformer: A Unified Framework for Multimodal Learning Zhang et al.: https://
arxiv.org/abs/2307.10802 #ArtificialIntelligence #Transformer #MultimodalLearning

→ View original post on X — @ceobillionaire

21 July 2023

Evaluating Instruction-Following in Language Models via Verbalizer Manipulation

By

@_akhaliq

–

21 July 2023 3h44

Instruction-following Evaluation through Verbalizer Manipulation paper page: https://
huggingface.co/papers/2307.10
558
… While instruction-tuned models have shown remarkable success in various natural language processing tasks, accurately evaluating their ability to follow instructions remains

→ View original post on X — @_akhaliq

21 July 2023

Challenges and Applications of Large Language Models

By

@ceobillionaire

–

21 July 2023 3h32

Challenges and Applications of Large Language Models Kaddour et al.: https://
arxiv.org/abs/2307.10169 #ArtificialIntelligence #DeepLearning #LargeLanguageModels

→ View original post on X — @ceobillionaire

21 July 2023

Top AIOps Platforms According to Gartner Infographic

By

@ingliguori

–

20 July 2023 21h17

Check out this #infographic on the top AIOps platforms according to Gartner! Via @ingliguori #Architecture #AIOps #Application #APM #Infrastructure #Technology #Performance #Website #Innovation #MachineLearning #AI #Gartner

→ View original post on X — @ingliguori

20 July 2023

Genome-Scale Language Model Predicts Viral Variants

By

@animaanandkumar

–

20 July 2023 20h38

Please include our genome-scale language model with @arvindr_ @argonne which is open access. Trained on 110 million genomes of viruses and bacteria and able to predict new variants of concern for #SARSCoV2 and other viruses and bacteria. https://
github.com/ramanathanlab/
genslm
…

→ View original post on X — @animaanandkumar

20 July 2023

Deep Learning AI Analyzes DXA Scans Genomics 30000 People

By

@erictopol

–

20 July 2023 20h26

What you can get when you combine deep learning #AI of DXA scans and genomics in >30,000 people! @ScienceMagazine @uk_biobank @ScienceVisuals https://
doi.org/10.1126/scienc
e.adf8009
… https://
science.org/toc/science/cu
rrent
…

→ View original post on X — @erictopol

20 July 2023