DreamVLA: From Generated Human Motions to Humanoid Vision-Language-Action Policies
cs.RO
Submitted: 2026-11-07
Updated: 2026-11-07
Code: https://github.com/NVIDIA/Isaac-GR00T
Project page: https://genrobo.github.io/DreamControl/static/paper/DreamControl_arxiv.pdf
Terminology
Sources
- OpenVLA: An Open-Source Vision-Language-Action Model
- GR00T N1: An Open Foundation Model for Generalist Humanoid Robots
- DreamControl: Human-Inspired Whole-Body Humanoid Control for Scene Interaction via Guided Diffusion
- OmniControl: Control Any Joint at Any Time for Human Motion Generation
- OmniRetarget: Interaction-Preserving Data Generation for Humanoid Whole-Body Loco-Manipulation and Scene Interaction
- HumanoidMimicGen: Data Generation for Loco-Manipulation via Whole-Body Planning
- SONIC: Supersizing Motion Tracking for Natural Humanoid Whole-Body Control
- VIRAL: Visual Sim-to-Real at Scale for Humanoid Loco-Manipulation
- Opening the Sim-to-Real Door for Humanoid Pixel-to-Action Policy Transfer
- DeepMimic: Example-Guided Deep Reinforcement Learning of Physics-Based Character Skills
- AMP: Adversarial Motion Priors for Stylized Physics-Based Character Control
- Perpetual Humanoid Control for Real-time Simulated Avatars
- ExBody2: Advanced Expressive Humanoid Whole-Body Control
- BeyondMimic: From Motion Tracking to Versatile Humanoid Control via Guided Diffusion
- ASAP: Aligning Simulation and Real-World Physics for Learning Agile Humanoid Whole-Body Skills
- Learning Human-to-Humanoid Real-Time Whole-Body Teleoperation
- OmniH2O: Universal and Dexterous Human-to-Humanoid Whole-Body Teleoperation and Learning
- HumanPlus: Humanoid Shadowing and Imitation from Humans
- TWIST: Teleoperated Whole-Body Imitation System
Related papers
- Rethinking Actions: Continuity-Aware Priors for World-Model Planning
- MOSAIC: Modular Obstacle and Spatial-Aware Framework for Manipulation In Cluttered Scenes
- SAGAS: Semantic-Aware Graph-Assisted Stitching for Offline Temporal Logic Planning
- DexSeed: Expanding Human Hand-Object Interactions into Robot Demonstrations for Dexterous Policy Learning
- LaST0.5: A Generalist World Action Model with Interaction-Centric Latent Reasoning
- CIALLO: Learning Shared Intent Representations for Cross-Embodiment Manipulation