Official code for "Reinforcement Fine-Tuning of Flow-Matching Policies for Vision-Language-Action Models" (ICRA 2026): Flow Policy Optimization for pi0
- aloha
- flow-matching
- icra2026
- jax
108,094 visible repositories in the index
3,025–3,048 of 3,210 · Most stars
Official code for "Reinforcement Fine-Tuning of Flow-Matching Policies for Vision-Language-Action Models" (ICRA 2026): Flow Policy Optimization for pi0
Configure Python functions explicitly and safely
Axon/Myelin segmentation using Deep Learning
ro.py is a modern, asynchronous Python 3 wrapper for the Roblox API.
A sklearn-compatible Python implementation of Multifactor Dimensionality Reduction (MDR) for feature construction.
TranslatedMultimodal retrieval in practice: intent recognition, prompt engineering, Qwen LoRA, EmbeddingGemma 2, and InfoNCE contrastive learning. Includes real demos, integration of your own data, training and evaluation, and a learning guide to RAG retrieval components.
ReAlign models instantly, on demand. Per-request alignment for verified users and channels, or Always On. Use directly or with Hermes, OpenClaw and custom harnesses.
Introduction to Deep Learning
DeepSeek Harness Desktop 插件,让 AI Agent 用自然语言构建、检查和维护可编辑的 SideFX Houdini 工程,支持程序化建模、HDA、场景诊断与渲染。 | A DeepSeek Harness Desktop plugin that lets AI agents build, inspect, and maintain editable SideFX Houdini projects with natural language, including procedural modeling, HDAs, scene diagnostics, and rendering.
Turn intent into work. Open-source Desktop/Web agent harness with long-horizon memory, live evaluation and recoverable batches.
A Codex skill that turns local STEM course materials into a personal Obsidian learning vault, with source-grounded explanations, derivations and practice.
Python typing koans to learn type-hints in Python3 using Mypy
Learning cell communication from spatial graphs of cells
Open-source event management, ticketing and membership platform for communities, clubs, independent venues and independent artists.
Library for machine learning stacking generalization.
Full async Micropython web server with small memory footprint.
Benchmark harness and data: QEMU emulation vs native Buildx nodes for multi-arch container builds.
Public code release for the paper "The Surprising Effectiveness of Deleting Weights in LLM Post-Training"
Callisto is an open-source Kubernetes-native implementation of Selenium Grid.
Poco will help you to organise and manage Docker, Docker-Compose, Kubernetes, Openshift projects of any complexity using simple YAML config files to shorten the route from finding your project to initialising it in your local environment.
Inferred Model-based Fuzzer
CASSIA: A Multi-Agent LLM-Based Single-Cell Cell Type Annotation Framework
Build and deploy a serverless data pipeline on AWS with no effort.
📚 Control Functions For Single-Board Computers