ScaleBot @ CVPR 2026

Overview

The First Workshop on Scalable Robot Learning Systems (ScaleBot) aims to bring together researchers and engineers from computer vision, natural language processing, robotics, and related fields to discuss how to build scalable learning systems for general-purpose robots. Inspired by the success of large-scale foundation models in vision and language, this workshop focuses on scaling the entire robot learning pipeline—covering topics including data collection, training recipes, model architectures, system integration, and evaluation. By fostering interdisciplinary dialogue and collaboration, ScaleBot seeks to identify key challenges, share recent advances, and outline future directions toward scalable, robust, and generalizable robot systems that can effectively operate in the real world.

Call for Papers

Topics of Interest

We welcome topics related but not limited to:

Data Acquisition: Scalable data collection devices and strategies for scalable robot learning.
Training: Data pyramids and scalable training recipes.
Models: VLMs, VLAs, World Models for spatial intelligence and robotics.
System: Dual-system architectures for robots.
Evaluation: Scalable and fair robot evaluations.

Submission Guidelines

All papers must be submitted through our OpenReview portal.
Submissions must strictly adhere to the CVPR 2026 Author Guidelines in terms of potential ethics issues and potential risks of negative social impacts. Please find the details of paper formatting and submission below for either of our two submission tracks. To facilitate double-blind review, all manuscripts must be fully anonymized.
All accepted papers are expected to be presented in person at the workshop.
Exceptional submissions will be considered for Best Paper Award and Spotlight Presentations.
Notes from OpenReview: New profiles created without an institutional email will go through a moderation process that can take up to two weeks. New profiles created with an institutional email will be activated automatically.

Submission Track 1: Proceedings Track

Submissions to the Proceedings Track must present original, unpublished research. Manuscripts should be between 4 and 8 pages in length (excluding references) using the CVPR 2026 submission template. Accepted papers will be formally published in the CVPR 2026 Workshop Proceedings.

Submission Portal: Proceedings

March 1, 2026 (AoE)

Submission Deadline

March 20, 2026

Notification to Authors

April 10, 2026

Camera-ready Deadline

Submission Track 2: Non-Proceedings Track

The Non-Proceedings Track offers a flexible, non-archival venue for sharing a broad range of contributions. This track allows authors to present and promote their work without restrictive publishing constraints, formatting requirements or page limits.

We warmly welcome: