Skip to content
RobotWorld
← Back to Videos

ThinkWorld Learns Robot Actions From Human Video

Loading video
Loading video

ThinkWorld represents actions as chains of dynamics and reinforces reasoning when imagined futures match what actually happens in unlabeled human video.

Vision-language-action (VLA)World ModelsHuman Video LearningChain-of-DynamicsRobotic Manipulation
Category: arm
Author: @HuggingPapers
Date: 2026-11-01T00:00:00
Duration: 115.1s
Source: https://x.com/HuggingPapers/status/2116687319562350904
Reference: https://arxiv.org/abs/2610.37666

Related Videos

OneWM: World and Action Models That Strengthen Each Other
2:52

OneWM: World and Action Models That Strengthen Each Other

@Selen7005717917 · 118 views · 2026-10-24
World ModelsRobot Manipulation
Real-Time EXPO-FT: Reliable VLA Fine-Tuning
1:00

Real-Time EXPO-FT: Reliable VLA Fine-Tuning

@robotsdigest · 735 views · 2026-09-24
VLARobotic Manipulation
RoboAPI Brings Zero-Shot Language Control to Compatible Robots
2:48

RoboAPI Brings Zero-Shot Language Control to Compatible Robots

@PokeBot_Global · 55 views · 2026-10-29
RoboAPIPoke-Aurora
DreamCan: Sparse Visual Planning for Long-Horizon Manipulation
2:41

DreamCan: Sparse Visual Planning for Long-Horizon Manipulation

@GChongkai · 120 views · 2026-10-23
World ModelsVisual Planning
3DPWM: Completed Point Clouds for Robot Planning
0:55

3DPWM: Completed Point Clouds for Robot Planning

@fuxinli2 · 153 views · 2026-10-20
3DPWMPoint Cloud Completion
LeWAM: An End-to-End JEPA That Controls Real Robots
0:57

LeWAM: An End-to-End JEPA That Controls Real Robots

@Minghao__Fu · 271 views · 2026-10-09
World ModelsJEPA

As an Amazon Associate, we earn from qualifying purchases.