Skip to content
Agientry
← Back to Videos

DreamCan: Sparse Visual Planning for Long-Horizon Manipulation

Loading video
Loading video

DreamCan argues visual planning does not need to imagine every frame: sparse keyframe planning supports long-horizon tabletop manipulation, with paper and code released.

World ModelsVisual PlanningManipulationDreamCanLong-Range Operation
Category: arm
Author: @GChongkai
Date: 2026-10-23T00:00:00
Duration: 161.066s
Source: https://x.com/GChongkai/status/2113669984094449738
Reference: https://arxiv.org/abs/2610.24981

Related Videos

LeWAM: An End-to-End JEPA That Controls Real Robots
0:57

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

@Minghao__Fu · 244 views · 2026-10-09
World ModelsJEPA
3DPWM: Completed Point Clouds for Robot Planning
0:55

3DPWM: Completed Point Clouds for Robot Planning

@fuxinli2 · 113 views · 2026-10-20
3DPWMPoint Cloud Completion
DexTacWAM: Making Touch Part of the Robot World Model
0:31

DexTacWAM: Making Touch Part of the Robot World Model

@robotsdigest · 593 views · 2026-09-22
Tactile SensingWorld Models
FAR: Robot Arms Learn to Recover From Failure
0:24

FAR: Robot Arms Learn to Recover From Failure

@hrhao1 · 22 views · 2026-10-26
Robot LearningManipulation
OneWM: World and Action Models That Strengthen Each Other
2:52

OneWM: World and Action Models That Strengthen Each Other

@Selen7005717917 · 56 views · 2026-10-24
World ModelsRobot Manipulation
R2-WAM: data-free continual learning for world action models via rectified generative replay
1:14

R2-WAM: data-free continual learning for world action models via rectified generative replay

@Yunsong_Zhou · 108 views · 2026-10-21
ContinualLearningWorldActionModel

As an Amazon Associate, we earn from qualifying purchases.