MolmoAct2: Action Reasoning Models for Real-world Deployment research paper by Ai2, 2026

Ai2 · May 4, 2026 · Multimodal and robotics · 44 citations · 355 upvotes

A fully open robot action model, released with new datasets including 720 hours of two-arm teleoperation.

Summarised by hand from the abstract.

Date	Paper	Lab	Citations
Apr 5, 2023	Segment AnythingA promptable model and a dataset of over a billion masks that cut out any object in any image.Meta · Apr 2023Meta	Meta	15.7k
Jun 1, 2026	Cosmos 3: Omnimodal World Models for Physical AIOne model that reads and generates text, images, video, audio and robot actions for physical AI.NVIDIA · Jun 2026NVIDIA	NVIDIA	90
Aug 6, 2026	Towards Physics of Multimodal Pretraining: Knowledge Flow, Modality Synergy, Early Unification, and RecipesControlled experiments on when text, image understanding and image generation help or compete when trained together.Meta · Aug 2026Meta	Meta	2

About this paper

Authors: Haoquan Fang, Jiafei Duan, Donovan Clay and 26 more
arXiv: 2605.02881 · PDF
Venue: arXiv.org
Citations: 44, 1 influential · Semantic Scholar
Upvotes: 355 · Hugging Face
Code: github.com/allenai/molmoact2
Lab: Ai2

Changes

Date	What changed
Sep 24, 2026	New paperAdded to the listSep 24, 2026

Sources: each lab's own papers and arXiv, with citation and upvote counts from Semantic Scholar and Hugging Face. One-line summaries are for orientation, not a substitute for the paper. Logos via logo.dev; trademarks belong to their owners.

What it shows

Other multimodal and robotics papers

Changes

New papers by email