3DTopia / LGM
LGM: Large Multi-View Gaussian Model for High-Resolution 3D Content Creation.
https://github.com/3DTopia/LGM
LGM: Large Multi-View Gaussian Model for High-Resolution 3D Content Creation.
https://github.com/3DTopia/LGM
GitHub
GitHub - 3DTopia/LGM: [ECCV 2024 Oral] LGM: Large Multi-View Gaussian Model for High-Resolution 3D Content Creation.
[ECCV 2024 Oral] LGM: Large Multi-View Gaussian Model for High-Resolution 3D Content Creation. - 3DTopia/LGM
facebookresearch / jepa
PyTorch code and models for V-JEPA self-supervised learning from video.
https://github.com/facebookresearch/jepa
PyTorch code and models for V-JEPA self-supervised learning from video.
https://github.com/facebookresearch/jepa
GitHub
GitHub - facebookresearch/jepa: PyTorch code and models for V-JEPA self-supervised learning from video.
PyTorch code and models for V-JEPA self-supervised learning from video. - facebookresearch/jepa
Relieving your Python packaging pain
An opinionated take for bootstrapping Python
https://www.bitecode.dev/p/relieving-your-python-packaging-pain
An opinionated take for bootstrapping Python
https://www.bitecode.dev/p/relieving-your-python-packaging-pain
www.bitecode.dev
Relieving your Python packaging pain
60% of the time, it works every time
👍1
LLM4Decompile
Reverse Engineering: Decompiling Binary Code with Large Language Models.
https://github.com/albertan017/LLM4Decompile
Reverse Engineering: Decompiling Binary Code with Large Language Models.
https://github.com/albertan017/LLM4Decompile
GitHub
GitHub - albertan017/LLM4Decompile: Reverse Engineering: Decompiling Binary Code with Large Language Models
Reverse Engineering: Decompiling Binary Code with Large Language Models - albertan017/LLM4Decompile
Diffusion models from scratch, from a new theoretical perspective
The article provides insights into interpreting and enhancing diffusion models using the Euclidean distance function, offering a detailed exploration of diffusion models and their applications. It focuses on improving diffusion models through gradient estimation, efficient sampling techniques, and visualizing the impact of momentum terms on text-to-image generation.
https://www.chenyang.co/diffusion.html
The article provides insights into interpreting and enhancing diffusion models using the Euclidean distance function, offering a detailed exploration of diffusion models and their applications. It focuses on improving diffusion models through gradient estimation, efficient sampling techniques, and visualizing the impact of momentum terms on text-to-image generation.
https://www.chenyang.co/diffusion.html
www.chenyang.co
Diffusion models from scratch
This tutorial aims to give a gentle introduction to diffusion models, with a running example to illustrate how to build, train and sample from a simple diffusion model from scratch.
Every dunder method in Python
An explanation of all of Pytho's 100+ dunder methods and 50+ dunder attributes, including a summary of each one.
https://www.pythonmorsels.com/every-dunder-method/
An explanation of all of Pytho's 100+ dunder methods and 50+ dunder attributes, including a summary of each one.
https://www.pythonmorsels.com/every-dunder-method/
Pythonmorsels
Every dunder method in Python
An explanation of all of Python's 100+ dunder methods and 50+ dunder attributes, including a summary of each one.
Vchitect / Latte
Latte: Latent Diffusion Transformer for Video Generation.
https://github.com/Vchitect/Latte
Latte: Latent Diffusion Transformer for Video Generation.
https://github.com/Vchitect/Latte
GitHub
GitHub - Vchitect/Latte: [TMLR 2025] Latte: Latent Diffusion Transformer for Video Generation.
[TMLR 2025] Latte: Latent Diffusion Transformer for Video Generation. - GitHub - Vchitect/Latte: [TMLR 2025] Latte: Latent Diffusion Transformer for Video Generation.
Python 3.10.14, 3.9.19, and 3.8.19 is now available
https://pythoninsider.blogspot.com/2024/03/python-31014-3919-and-3819-is-now.html
https://pythoninsider.blogspot.com/2024/03/python-31014-3919-and-3819-is-now.html
Blogspot
Python Insider: Python 3.10.14, 3.9.19, and 3.8.19 is now available
phospho
Text analytics for LLM apps. PostHog for prompts. Extract evaluations, intents and events from text messages. phospho leverages LLM (OpenAI, MistralAI, Ollama, etc.)
https://github.com/phospho-app/phospho
Text analytics for LLM apps. PostHog for prompts. Extract evaluations, intents and events from text messages. phospho leverages LLM (OpenAI, MistralAI, Ollama, etc.)
https://github.com/phospho-app/phospho
GitHub
GitHub - phospho-app/phospho: Text analytics for LLM apps. Cluster messages to detect use cases, outliers, power users. Detect…
Text analytics for LLM apps. Cluster messages to detect use cases, outliers, power users. Detect intents and run evals with LLM (OpenAI, MistralAI, Ollama, etc.) - phospho-app/phospho
Chronos
Pretrained (Language) Models for Probabilistic Time Series Forecasting.
https://github.com/amazon-science/chronos-forecasting
Pretrained (Language) Models for Probabilistic Time Series Forecasting.
https://github.com/amazon-science/chronos-forecasting
GitHub
GitHub - amazon-science/chronos-forecasting: Chronos: Pretrained Models for Probabilistic Time Series Forecasting
Chronos: Pretrained Models for Probabilistic Time Series Forecasting - amazon-science/chronos-forecasting
Lambda on hard mode: Inside Modal's web infrastructure
This post talks about how Modal handles real-time HTTP requests and WebSockets in serverless functions.
https://modal.com/blog/serverless-http
This post talks about how Modal handles real-time HTTP requests and WebSockets in serverless functions.
https://modal.com/blog/serverless-http
Modal
Lambda on hard mode: Inside Modal's web infrastructure
In this post, we'll talk about how Modal handles real-time HTTP requests and WebSockets in serverless functions.