Counterfactual Video Generation Enables Scalable Humanoid Loco-Manipulation

arXiv:2609.38172 · cs.RO, cs.CV, cs.GR · Submitted 2026-09-29 · Read on arXiv

cs.RO, cs.CV, cs.GR

Submitted: 2026-09-29

Updated: 2026-09-29

Terminology

• Distillation — 8× in this paper · explained in 2 episodes
• Actor — 7× in this paper · explained in 3 episodes
• Ablation — 4× in this paper · explained in 1 episode
• Generalization — 4× in this paper · explained in 13 episodes
• Ablation study — 3× in this paper · explained in 1 episode
• Affordance — 3× in this paper · explained in 1 episode
• Sim-to-Real Gap — 3× in this paper · explained in 6 episodes
• Adaptation — 2× in this paper · explained in 1 episode
• Reconstruction Error — 2× in this paper · explained in 2 episodes
• Calibration — 1× in this paper · explained in 7 episodes
• Core — 1× in this paper · explained in 2 episodes
• Failure Modes — 1× in this paper · explained in 3 episodes
• Fine-Tuning — 1× in this paper · explained in 5 episodes
• Generative Model — 1× in this paper · explained in 2 episodes
• Generative Models — 1× in this paper · explained in 2 episodes
• Regret — 1× in this paper · explained in 3 episodes
• Reinforcement Learning — 1× in this paper · explained in 4 episodes
• Robustness — 1× in this paper · explained in 5 episodes
• Transferability — 1× in this paper · explained in 4 episodes
• Two-stage training — 1× in this paper · explained in 2 episodes
• World Model — 1× in this paper · explained in 7 episodes
• Zero-Shot Generalization — 1× in this paper · explained in 5 episodes

Sources

• Visual Imitation Enables Contextual Humanoid Control
• World Action Models are Zero-shot Policies
• HDMI: Learning Interactive Humanoid Whole-Body Control from Human Videos
• OmniRetarget: Interaction-Preserving Data Generation for Humanoid Whole-Body Loco-Manipulation and Scene Interaction
• VLK: Learning Humanoid Loco-Manipulation from Synthetic Interactions in Reconstructed Scenes
• LessMimic: Long-Horizon Humanoid Interaction with Unified Distance Field Representations
• ULTRA: Unified Multimodal Control for Autonomous Humanoid Whole-Body Loco-Manipulation
• Generalizing from References using a Multi-Task Reference and Goal-Driven RL Framework
• Learning from Massive Human Videos for Universal Humanoid Pose Control
• HumanX: Toward Agile and Generalizable Humanoid Interaction Skills from Human Videos
• Large Video Planner Enables Generalizable Robot Control
• Gen2Act: Human Video Generation in Novel Scenarios enables Generalizable Robot Manipulation
• Robotic Manipulation by Imitating Generated Videos Without Physical Demonstrations
• DreamGen: Unlocking Generalization in Robot Learning through Video World Models
• Seedance 2.0: Advancing Video Generation for World Complexity
• CRISP: Contact-Guided Real2Sim from Monocular Video with Planar Scene Primitives
• SAM 2: Segment Anything in Images and Videos
• SAM 3D: 3Dfy Anything in Images
• FoundationPose: Unified 6D Pose Estimation and Tracking of Novel Objects
• Perceptive Humanoid Parkour: Chaining Dynamic Human Skills via Motion Matching

Related papers

• FMT x: An Efficient and Asymptotically Optimal Extension of the Fast Marching Tree for Dynamic Replanning
• MPCFormer: A physics-informed data-driven approach for explainable socially-aware autonomous driving
• RoboLab: A High-Fidelity Simulation Benchmark for Analysis of Task Generalist Policies
• HRDexDB: A 4D Dexterous Grasping Dataset Across Human and Multiple Robot Embodiments
• APT: Action Expert Pretraining Improves Instruction Generalization of Vision-Language-Action Policies
• Fine-tuning is Not Enough: A Parallel Framework for Collaborative Imitation and Reinforcement Learning in End-to-end Autonomous Driving