[NeurIPS 2025] Flow x RL. "ReinFlow: Fine-tuning Flow Policy with Online Reinforcement Learning". Support VLAs e.g., Pi0, Pi0.5, GR00TN1.5. Fully open-sourced.
-
Updated
Apr 24, 2026 - Python
[NeurIPS 2025] Flow x RL. "ReinFlow: Fine-tuning Flow Policy with Online Reinforcement Learning". Support VLAs e.g., Pi0, Pi0.5, GR00TN1.5. Fully open-sourced.
[ECCV 2026] Official repository of FlowInOne: Unifying Multimodal Generation as Image-In Image-Out Flow Matching
Official repository for FlowSE (Interspeech 2025)
(ICASSP 2025, official code)FlowSE: Flow Matching-based Speech Enhancement
unofficial Split Mean Flow Implementation from bytedance
《高级机器学习》:面向生成式人工智能时代的机器学习教材,涵盖强化学习、大模型训练与对齐、生成建模和多模态学习等内容。
Multi-stage Riemannian flow matching for physically valid molecular docking, with GNINA scoring, PoseBusters filtering, CLI inference, and benchmarks.
Diffusion-SDPO: Safeguarded Direct Preference Optimization for Diffusion Models
(Interspeech 2025, official code) Speech enhancement based on cascaded two flows
Conditional Flow matching for Image and video
Longitudinal Flow Matching for Trajectory Modeling (AISTAT 2026 Spotlight)
A toy implementation of a diffusion transformer based "world model" trained on the game of pong or doom.
Official Code for ICLR'26 Work LapFlow
A flow matching framework for EMG generation
[ECCV 2026] FlowCIR: Semantic Transport via Flow Matching for Zero-Shot Composed Image Retrieval
[IROS 2025] PainDiffusion: Learning to Express Pain - IROS Best Entertainment and Amusement Paper Award
Very minimal Implementation of Pi-Zero (https://www.pi.website/download/pi0.pdf). Vision Action Flow matching model
Python library designed to make model experimentation seamless and fast. The goal was simple: treat every component (attention heads, MLPs, MoE layers) as a plug-and-play block so you can focus on the architecture, not the boilerplate.
A basic implementation of Flow Matching for unconditional 3D point clouds generation.
Offical repo for "Helping Music Co-Creation Agents ‘Listen’ Well: Hierarchical Self-Supervised World Models for Understanding and Generation"
To associate your repository with the flowmatching topic, visit your repo's landing page and select "manage topics."