official code for "Large Language Models as Optimizers"

Awesome-LLM: a curated list of Large Language Model

Solve puzzles. Improve your pytorch.

TextGrad: Automatic ''Differentiation'' via Text -- using large language models to backpropagate textual gradients.

automatic differentiation made easier for C++

SuperPrompt is an attempt to engineer prompts that might help us understand AI agents.

DSPy: The framework for programming—not prompting—language models

This repo is meant to serve as a guide for Machine Learning/AI technical interviews.

Machine Learning Interviews from FAANG, Snapchat, LinkedIn. I have offers from Snapchat, Coupang, Stitchfix etc. Blog: mlengineer.io.

commaVQ is a dataset of compressed driving video

Re-thinking Federated Active Learning based on Inter-class Diversity (CVPR 2023)

FedML - The Research and Production Integrated Federated Learning Library: https://fedml.ai

SONAR - Self-Organizing Network of Aggregated Representations

AI residency programs information

🤖 Machine Learning Summer School deadlines

Master programming by recreating your favorite technologies from scratch.

Papers from the computer science community to read and discuss.

AR webapp to pick and place a selection of furniture models into your surroundings in real-time using your mobile's live video footage of your current surroundings: leverages ThreeJS and WebXR to e…

A crowdsourced list of shared tasks

[ICML'21 Oral] I-BERT: Integer-only BERT Quantization

[NeurIPS'22] Squeezeformer: An Efficient Transformer for Automatic Speech Recognition

[ICML 2024] SqueezeLLM: Dense-and-Sparse Quantization

Federated Optimization in Heterogeneous Networks (MLSys '20)

DISCO is a code-free and installation-free browser platform that allows any non-technical user to collaboratively train machine learning models without sharing any private data.

FEDML - The unified and scalable ML library for large-scale distributed training, model serving, and federated learning. FEDML Launch, a cross-cloud scheduler, further enables running any AI jobs o…

Pytorch implementation for Domain Adaptive Remaining Useful Life Prediction with Transformer

DoWhy is a Python library for causal inference that supports explicit modeling and testing of causal assumptions. DoWhy is based on a unified language for causal inference, combining causal graphic…