AI open source rankings.
[NeurIPS 2024] SimPO: Simple Preference Optimization with a Reference-Free Reward
AgentSims is an easy-to-use infrastructure for researchers from all disciplines to test the specific capacities they are interested in.
Work with local and cloud LLMs from Emacs.
An engine for high performance multi-agent environments with very large numbers of agents, along with a set of reference environments
Official implementation of HARL algorithms based on PyTorch.
Use Claude Code for free in the terminal, VSCode extension, or via Discord
A polyhedral compiler for expressing fast and portable data parallel algorithms
Personal cloud OS for a developer and their AI agents on a single server. One-command install on Ubuntu, then everything in the browser: a windowed desktop, isolated workspaces with VS Code, Claude Code and Codex, a store of 944 self-hosted apps, backups and updates. Access only via Tailscale, nothing exposed to the internet. Rust core, Svelte UI.
Source code for end-to-end dialogue model from the MultiWOZ paper (Budzianowski et al. 2018, EMNLP)
A must-read paper for speech separation based on neural networks
This node provides lip-sync capabilities in ComfyUI using ByteDance's LatentSync model. It allows you to synchronize video lips with audio input.
A tutorial for Kaggle's Titanic: Machine Learning from Disaster competition. Demonstrates basic data munging, analysis, and visualization techniques. Shows examples of supervised machine learning techniques.
A collection of implementations of deep domain adaptation algorithms
Cosmos-Reason1 models understand the physical common sense and generate appropriate embodied decisions in natural language through long chain-of-thought reasoning processes.
PINNs-Torch, Physics-informed Neural Networks (PINNs) implemented in PyTorch.
The complete post-training stack for LLMs, plus RL for any problem. SFT, DPO and multi-turn agentic RL, with evolutionary hyperparameter optimization built in.
The hub for audio AI research: papers, open models, benchmarks & datasets across audio LLMs, speech recognition, TTS, music & audio generation.
PyTorch implementation of normalizing flow models
Near-Realtime audio transcription using self-hosted Whisper and WebSocket in Python/JS
TensorFlow Lite Samples on Unity
Cayu is an open-source Python framework for building and running domain-specific long-horizon agents, with a durable runtime built in.
Sandboxed devcontainer for running Claude Code in bypass mode safely. Built for security audits and untrusted code review.
Официальный репозиторий курса Deep Learning (2018-2021) от Deep Learning School при ФПМИ МФТИ
An Efficient, Scalable and Optimized Python Framework for Deep Forest (2021.2.1)
An open protocol for secure data sharing
Official implementation of Half-Quadratic Quantization (HQQ)
Code for "HyperNeRF: A Higher-Dimensional Representation for Topologically Varying Neural Radiance Fields".
Code for 3D object detection for autonomous driving
Easy Linux virtual machine on MacOS to sandbox LLM agents.
Contains examples for the Movidius Neural Compute Stick.