Introducing AI research blog, merely for distilling cutting-edge approaches and all things AI. What are some topics that you are particularly interested in and would like to see discussed? Let me know below! https://
deeprevision.github.io/posts/welcome/
@jeande_d
-
New AI Research Blog Launched for Cutting-Edge Approaches
By
–
-
Challenges and Applications of Large Language Models Overview
By
–
Challenges and Applications of Large Language Models A comprehensive review of the problems that remain unsolved in LLMs arena. The paper also provides a broad overview of application areas of LLMs and highlights some common application architectures across domains. This is
-
Comprehensive Literature Review of Transformer-Based Models and Techniques
By
–
Transformer Taxonomy A fantastic literature review of transformers. it covers 22 transformer-based models, 11 architectural changes, post pre-training techniques, training techniques, and other relevant techniques from recent papers. A quick example of models/techniques
-
Cool LLaMA developments: recipes, iOS, C++, finetuning
By
–
Cool things happening around LLaMA. From LLaMA recipes, running LLaMA on iOS, cpp, to finetuning it with replicate.
-
FlashAttention-2: 2x Faster Attention with Better Parallelism
By
–
FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning FlashAttention-2 is 2x faster than previous version. Release blog: https://
crfm.stanford.edu/2023/07/17/fla
sh2.html
… Paper: https://
tridao.me/publications/f
lash2/flash2.pdf
… -
LLaMA 2 from Meta AI: Major Improvements and New Features
By
–
Probably the biggest highlight of this week is LLaMA 2 from Meta AI. LLaMA 2 is improved version of LLaMA 1. It was trained on more data(40% more than LLaMa 1) and it has 4K context length(double the previous context). LLaMA 2 release package contains 3 model sizes(7B, 13B,
-
Weekly Thread on Latest AI and ML Developments
By
–
In the light of our short context window and lots of cool things that are coming out instantly, I am starting a weekly running thread of things that I find useful spanning a wide variety of topics from LLMs, vision, robotics, multimodals LLMs, etc… I have been jotting down
-
Generative AI Learning Path: Resources and Topics Overview
By
–
Generative AI learning path Generative AI is becoming a new field involving/attracting practitioners or builders, industries integrating generative models into their products, and academia. This is a great collection of contents on generative AI covering topics such as
-
Nice Response: Meta Open Sources LLaMA 2
By
–
This looks like a nice response. https://
open.substack.com/pub/mattrickar
d/p/why-did-meta-open-source-llama-2?r=j34du&utm_medium=ios&utm_campaign=post
…
