Submitted “The Transformer Blueprint” article to HN out of curiosity and it got 90 points and great feedback! Way beyond what I expected!!
@jeande_d
-
Kaiming He’s Influential Role in Computer Vision Research
By
–
Kaiming He is the core author of most influential papers in Computer Vision. His future students will be very luck to learn directly from him.
-
LLaMA Training and PEFT for Neural Networks Zero to Hero
By
–
LLaMA training & PEFT would be a very appreciated entry in NN Zero to Hero :-). And plays well with recent entries(nanoGPT, State of GPT).
-
Pathways Models and PaLM-E Are Not Open-Source
By
–
All Pathways models including PaLM-E are not open-source as far as I know.
-
The Transformer Blueprint: A Holistic Guide to Neural Networks
By
–
A NEW ARTICLE The first article of Deep Learning Revision Research Blog(introduced recently) is out: "The Transformer Blueprint: A Holistic Guide to the Transformer Neural Network Architecture". In the article, we discuss the core mechanics of transformer neural
-
RT-2 Robotics Transformer: Vision and Language to Action Model
By
–
RT-2 relevant links: Project page: https://
robotics-transformer2.github.io
Paper: https://
robotics-transformer2.github.io/assets/rt2.pdf
Blog: https://
deepmind.com/blog/rt-2-new-
model-translates-vision-and-language-into-action
… Other links:
RT-1: https://
robotics-transformer1.github.io
PaLI-X(direct scale up of PaLI): https://
arxiv.org/abs/2305.18565
PaLM-E: https://
arxiv.org/abs/2303.03378 Work from Google -
RT-2: Vision-Language-Action Models for Robotic Control
By
–
RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control RT-2(Robotic Transformer 2) is a new model in family of vision-language action models(VLAs). RT-2 builds up on RT-1 and vision-language models(VLMs). RT-2 makes use of pre-trained VLMs and is
-
Visual Foundation Models: Architectures, Training, and Prompting Survey
By
–
Foundational Models Defining a New Era in Vision: A Survey and Outlook A comprehensive survey of visual foundation models. Covers emerging architectures(for vision+other modalities), training objectives, pre-training datasets, fine-tuning mechanisms, and the common prompting
-
Stanford MLSys Seminars: Essential Talks on Machine Learning Systems
By
–
Really like this series of talks by Stanford MLSys Seminars on wide range of topics. All talks are great. A few examples: – FlashAttention: https://
youtube.com/watch?v=gMOAud
7hZg4
…
– PaLM: https://
youtube.com/watch?v=CV_eBV
wzOaw
…
– Building ML models like open-source software: https://
youtube.com/watch?v=0oGxT_
i7nk8
… All talk -
Transformers in Reinforcement Learning: A Comprehensive Survey
By
–
Transformers in Reinforcement Learning: A Survey A survey that explores the applications of transformers in reinforcement learning. The survey provides a brief overview of RL and challenges of classical RL approaches, traits of transformers that make them suitable for