MolmoAct Action Reasoning Models that can Reason in Space
This is experimental HTML to improve accessibility. We invite you to report rendering errors. Use Alt+Y to toggle on accessible reporting links and Alt+Shift+Y to toggle off. Learn more about this project and help improve conversions.
\authorOne [1,2*]Jason Lee ♥ \authorOne [1,2*]Jiafei Duan ♥ \authorOne [1,2*]Haoquan Fang ♥ \authorTwo [1]Yuquan Deng ♥ \authorTwo [1,2]Shuo Liu ♥ \authorTwo [2]Boyang Li ♥ \authorTwo [2]Bohan Fang ♥ \authorTwo [1,2]Jieyu Zhang ♥ \authorTwo [1,2]Yi Ru Wang ♥ \authorThree [1]Sangho Lee \authorThree [1]Winson Han \authorThree [1]Wilbert Pumacay \authorThree [2]Angelica Wu \authorThree [1]Rose Hendrix ♥ \authorThree [1]Karen Farley \authorThree [1]Eli VanderBilt \authorFour [1,2]Ali Farhadi \authorFour [1,2]Dieter Fox ♥ \authorFour [1,2]Ranjay Krishna ♥ 1]Allen Institute for AI 2]University of Wa
saved by
related reading
- Efficient World Models with Context-Aware Tokenizationarxiv.org
- VRPRM: Process Reward Modeling via Visual Reasoningarxiv.org
- A Steerable Model with Emergent Capabilitiespi.website
- Molmo and PixMo: Open Weights and Open Data for State-of-the-Art Vision-Language Modelsarxiv.org
- ACT-1: A Robot Foundation Model Trained on Zero Robot Data | Sunday Robotics | The helpful robotics companysunday.ai
- ERCEIVER-ACTOR: A Multi-Task Transformer for Robotic Manipulationarxiv.org
- RT-2: Vision-Language-Action Modelsrobotics-transformer2.github.io
- [2201.07207] Language Models as Zero-Shot Planners: Extracting Actionable Knowledge for Embodied Agentsarxiv.org
- 𝜋₀: A Vision-Language-Action Flow Model for General Robot Controlarxiv.org
- A Careful Examination of Large Behavior Models for Multitask Dexterous Manipulationtoyotaresearchinstitute.github.io
- [2602.10556] LAP: Language-Action Pre-Training Enables Zero-shot Cross-Embodiment Transferarxiv.org
- Sparse Autoencoders Reveal Interpretable and Steerable Features in VLA Modelsarxiv.org