Here are some links I found interesting this week.
copilot-explorer | Hacky repo to see what the Copilot extension sends to the server
openai/point-e: Point cloud diffusion for 3D model synthesis
What The Heck Is Happening In Japan?
Understanding Zero-Knowledge Proofs in 15 Mins through SNARK and STARK | by Intel Chen | Medium
Staring into the abyss as a core life skill | benkuhn.net
Unity - Developing Your First Game with Unity and C# | Microsoft Learn
Here are some links I found interesting this week.
Before the flood - by Samuel Hammond - Second Best
metaseq/README.md at main · facebookresearch/metaseq
Data2vec 2.0: Highly efficient self-supervised learning for vision, speech and text
How does GPT Obtain its Ability? Tracing Emergent Abilities of Language Models to their Sources
Why S4 is Good at Long Sequence: Remembering a Sequence with Online Function Approximation
A Closer Look at Large Language Models Emergent Abilities
[ECCV 2020] NeRF: Neural Radiance Fields (10 min talk) - YouTube
Fishmans - Long Season (Nightcore Mix) - YouTube
[2102.07350] Prompt Programming for Large Language Models: Beyond the Few-Shot Paradigm
Here are some links I found interesting this week.
The shit guide to training with optimized dreambooth stable diffusion
[2212.01349] Nonparametric Masked Language Modeling
The Chinese Civil Examinations | Hilde De Weerdt | Inference
[2209.11142] A Generalist Neural Algorithmic Learner
Illustrating Reinforcement Learning from Human Feedback (RLHF)
Here are some links I found interesting this week.
Another data science student's blog – Pointer cache for Language Model
An empirical analysis of compute-optimal large language model training
Training Compute-Optimal Large Language Models
[2211.13319] Make-A-Story: Visual Memory Conditioned Consistent Story Generation
Symmetric derivative - Wikipedia
DALL-E-Explained/README.md at main · simonsanvil/DALL-E-Explained
PyTorch internals : ezyang’s blog
Tales of the M1 GPU - Asahi Linux
Relaxing music from Gran Turismo #1 (GT2 - 6) - YouTube
Here are some links I found interesting this week.
Language Models are Few-Shot Learners
mosaicml/composer: Train neural networks up to 7x faster
alantess/transformer: Implementation of a modified vision transformer on the crypto market space
Zero-Shot Text-to-Image Generation
Training language models to follow instructions with human feedback
Common Problems | Machine Learning | Google Developers
Introduction - The Encointer Book
Why I think strong general AI is coming soon - LessWrong
A Census of the Factor Zoo by Campbell R. Harvey, Yan Liu :: SSRN
Magic3D: High-Resolution Text-to-3D Content Creation
[1910.02054] ZeRO: Memory Optimizations Toward Training Trillion Parameter Models
How to fine tune stable diffusion: how we made the text-to-pokemon model at Lambda
diffusers/convert_original_stable_diffusion_to_diffusers.py at main · huggingface/diffusers
Joji Instrumentals to relax to │Rain ambience - YouTube
Stable Diffusion | Qiang Zhang
CLIP: Connecting Text and Images