Physical AI

FPO: Flow-matching reinforcement learning for vision-language-action models

Original titletuotuoLyu/FPO

Outlet: GitHub
Published: Oct 29, 2026
Importance: 3/5
Trending: 9

Summary

FPO is the official implementation for reinforcement fine-tuning of flow-matching policies for vision-language-action models, presented at ICRA 2026. It enables flow policy optimization for pi0-style models in robot learning.

Also reported by 1 outlet

GitHubtuotuoLyu/ForesightSafety-VLA

Original excerpt

Official code for "Reinforcement Fine-Tuning of Flow-Matching Policies for Vision-Language-Action Models" (ICRA 2026): Flow Policy Optimization for pi0 · topics: aloha, flow-matching, icra2026, jax, libero, reinforcement-learning, robot-learning, vision-language-action

#robot-learning#flow-matching#vision-language-action

Read the original

See all →

Oct 31

Foundry Robotics raises $100 million Series A for autonomous assembly factories

Foundry Robotics announced an oversubscribed $100 million Series A funding round led by Marlinspike Partners. The round includes participation from early backers Khosla Ventures and Red Glass Ventures, alongside new investors SE Ventures, Wing VC, and Axiom Ventures.

Robotics & Automation News

Nov 2

Meta partners with Fourier on humanoid robot for household tasks

Meta and Chinese robotics startup Fourier jointly developed humanoid robot prototype Max, a 48-kilogram robot completed in three months. The companies are working on a successor model, targeting the household robotics market for housekeeping and daily tasks.

AI Times

Nov 4

NEO-VLA, an encoder-free vision-language-action framework for robotic manipulation

The authors propose NEO-VLA, an encoder-free vision-language-action framework where images are tokenized and evolve jointly with language throughout the backbone. They show that this approach outperforms encoder-based counterparts across diverse manipulation tasks and distribution shifts.

Hugging FaceTrending 27

Oct 27

PDRVLA integrates physical dynamics into robot vision-language-action models

PDRVLA, a vision-language-action model with a lightweight physical dynamics module, generates robot actions from visual input and language instructions. It learns from public data augmented with human-to-robot synthesis and embodied chain-of-thought annotation, achieving 99.3% success on LIBERO and up to 93.6% on RoboTwin 2.0.

Hugging Face +1 moreTrending 25