Skip to content
AI News HubLIVE
Original source2 min read

FLORA: An Open Model Suite for Scaling Robotics Data Engines

Summary

NVIDIA researchers introduce Flora, an industrial-quality robotics data engine that covers outcome reward, process reward, and timestamped caption labeling in one system, reaches SOTA on WGO-Bench, RoboReward, and Robometer, costs roughly 125x less than GPT-6 Astra, and has been battle tested labeling 200,000 hours of data per day across 512 GB300s.

SourcearXiv RoboticsAuthor: Sicong Leng, Yunze Man, Zhiqi Li, Jing Wang, Yuhe Zhang, Ryan Punamiya, Siddharth Patki, Kaiyuan Zheng, Zi-ang Cao, Zhiding Yu, Sifei Liu, Danfei Xu, Ben Levin, Jan Kautz, Yuke Zhu, Johan Bjorck, Linxi "Jim" Fan
FLORA: An Open Model Suite for Scaling Robotics Data Engines
Report an error

The correction channel is not available yet. You can copy the article reference below for later.

Correction instructions
Read article

[Submitted on 22 Oct 2026]

Title:FLORA: An Open Model Suite for Scaling Robotics Data Engines

View a PDF of the paper titled FLORA: An Open Model Suite for Scaling Robotics Data Engines, by Sicong Leng and 16 other authors

View PDF HTML (experimental)

Abstract:The life-cycle of robotics foundation models crucially depends on data labels. Outcome reward labels are needed for monitoring real-world deployments. Process reward labels are needed during RL post-training. Timestamped captions are needed for filtering and balancing pretraining data. We present Flora, an industrial-quality data engine used for training GR00T models, that simultaneously covers these capabilities. Flora achieves SOTA scores on the captioning benchmark WGO-Bench and reward benchmarks RoboReward and Robometer. On internal benchmarks it is competitive with GPT-6 Astra while beating other frontier models. The model is substantially cheaper than API-based alternatives, roughly 125 times cheaper than GPT-6 Astra. Florais battle tested at scale, labeling 200,000 hours of data per day across 512 GB300s. By open-sourcing our data engine, we enable researchers to scale custom robotics datasets and explore emerging applications such as physical auto-research and human-to-robot transfer.

Subjects:

Robotics (cs.RO)

Cite as: arXiv:2610.31779 [cs.RO]

(or arXiv:2610.31779v1 [cs.RO] for this version)

https://doi.org/10.48550/arXiv.2610.31779

arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Johan Bjorck [view email] [v1] Thu, 22 Oct 2026 18:16:17 UTC (8,889 KB)

Full-text links:

Access Paper:

View a PDF of the paper titled FLORA: An Open Model Suite for Scaling Robotics Data Engines, by Sicong Leng and 16 other authors

View PDF

HTML (experimental)

TeX Source

view license

Additional Features

Audio Summary

Current browse context:

cs.RO

new | recent | 2026-10

Change to browse by:

cs

References & Citations

SciX

Google Scholar

Semantic Scholar

Loading...

Data provided by:

Bibliographic Tools

Bibliographic and Citation Tools

Bibliographic Explorer Toggle

Bibliographic Explorer (What is the Explorer?)

Connected Papers Toggle

Connected Papers (What is Connected Papers?)

Litmaps Toggle

Litmaps (What is Litmaps?)

scite.ai Toggle

scite Smart Citations (What are Smart Citations?)

Code, Data, Media

Code, Data and Media Associated with this Article

alphaXiv Toggle

alphaXiv (What is alphaXiv?)

Links to Code Toggle

CatalyzeX Code Finder for Papers (What is CatalyzeX?)

DagsHub Toggle

DagsHub (What is DagsHub?)

GotitPub Toggle

Gotit.pub (What is GotitPub?)

Huggingface Toggle

Hugging Face (What is Huggingface?)

ScienceCast Toggle

ScienceCast (What is ScienceCast?)

Demos

Demos

Replicate Toggle

Replicate (What is Replicate?)

Spaces Toggle

Hugging Face Spaces (What is Spaces?)

Spaces Toggle

TXYZ.AI (What is TXYZ.AI?)

Related Papers

Recommenders and Search Tools

Link to Influence Flower

Influence Flower (What are Influence Flowers?)

Core recommender toggle

CORE Recommender (What is CORE?)

Author

Venue

Institution

Topic

About arXivLabs

arXivLabs: experimental projects with community collaborators

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.

Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)

Key points and analysis

Article intelligence

EngineersAdvanced

Key points

  • Flora covers outcome reward labels, process reward labels, and timestamped captions, spanning the full robotics foundation model life cycle.
  • It achieves SOTA on the WGO-Bench captioning benchmark and the RoboReward and Robometer reward benchmarks, and is competitive with GPT-6 Astra on internal benchmarks.
  • It is roughly 125 times cheaper than GPT-6 Astra and has labeled 200,000 hours of data per day across 512 GB300s.
  • Already used to train GR00T models, the open-sourced engine aims to help researchers scale custom robotics datasets and explore physical auto-research and human-to-robot transfer.

Highlights and analysis are generated automatically and may contain errors. Check the original source.

More recent stories on this topic · Robotics