Skip to content
RobotWorld
ZH

Demos

Every demo carries its vertical and capability domain. Pick a vertical to narrow the feed.

WaterfallPagination
All verticalsDevelopmentData & AnalyticsSecurityDocs & SlidesMediaDesign & FrontendGame MakingResearchKnowledgeEducationMarketing & GrowthCommerce & RetailLegal & FinanceHealthcareManufacturing
InternAI's Shusheng platform gives away 500M tokens: Intern-S2/Atria/Agents-A1 at zero cost, OpenAI & Anthropic compatible
2:16

InternAI's Shusheng platform gives away 500M tokens: Intern-S2/Atria/Agents-A1 at zero cost, OpenAI & Anthropic compatible

@xiangxiang103 · 1.6k views · 2026-10-04
ShanghaiAILabInternLM
NVIDIA PixelUMM: encoder-free unified understanding and generation in raw pixel space
0:30

NVIDIA PixelUMM: encoder-free unified understanding and generation in raw pixel space

@robotsdigest · 417 views · 2026-10-04
NVIDIAPixelUMM
Gemini Robotics-ER 2 scripts a two-FR3 grasp: shared circle, YZ then XY (Isaac Sim + ROS 2)
0:11

Gemini Robotics-ER 2 scripts a two-FR3 grasp: shared circle, YZ then XY (Isaac Sim + ROS 2)

@Official_m9g · 523 views · 2026-10-04
Gemini RoboticsFranka
MuscleMimic: one generalist policy drives 354 muscles zero-shot
0:33

MuscleMimic: one generalist policy drives 354 muscles zero-shot

@ckli85 · 573 views · 2026-10-03
MuscleMimicMusculoskeletal
All-Terrain Hopping Robot: Hopcopter Switches Between Jumping and Flying
0:55

All-Terrain Hopping Robot: Hopcopter Switches Between Jumping and Flying

@ZappyZappy7 · 545 views · 2026-10-03
LocomotionHoppingRobot
Caltech ROM-Nav: Decoupling Navigation from Embodiment Lets Humanoids Walk Better
0:39

Caltech ROM-Nav: Decoupling Navigation from Embodiment Lets Humanoids Walk Better

@LeoKharon · 643 views · 2026-10-03
HumanoidNavigation
Local 3D AI Now Generates 100% Watertight Meshes: Trellis2 + Pixal3D in ComfyUI
0:20

Local 3D AI Now Generates 100% Watertight Meshes: Trellis2 + Pixal3D in ComfyUI

@philippsieben · 562 views · 2026-10-03
3DGenerationMeshGeneration
DynaRetarget: Learning Humanoid Robot Motions from Human Demonstrations
0:25

DynaRetarget: Learning Humanoid Robot Motions from Human Demonstrations

@spaceandtech_ · 689 views · 2026-10-02
HumanoidMotion retargeting
Delta Intelligence unveils Delta-0, a humanoid foundation model trained on 10,000+ hours of human data — making beds, opening dishwashers, emptying trash with a brain-cerebellum force-position hybrid architecture
0:29

Delta Intelligence unveils Delta-0, a humanoid foundation model trained on 10,000+ hours of human data — making beds, opening dishwashers, emptying trash with a brain-cerebellum force-position hybrid architecture

@spaceandtech_ · 458 views · 2026-10-02
FreeVideo: MiniMax H3 video generation on a laptop with as little as 8GB VRAM — VDN-H3 linear attention plus hardware-adaptive execution planning, open source as a ComfyUI plugin
0:45

FreeVideo: MiniMax H3 video generation on a laptop with as little as 8GB VRAM — VDN-H3 linear attention plus hardware-adaptive execution planning, open source as a ComfyUI plugin

@HaochengXiUCB · 1.1k views · 2026-10-02
text-to-cad's Codex plugin is live: generate STEP/STL/3MF/GLB from a prompt, DFM-review it, then send straight to Bambu printing or SendCutSend — fully open source, free, and local
0:28

text-to-cad's Codex plugin is live: generate STEP/STL/3MF/GLB from a prompt, DFM-review it, then send straight to Bambu printing or SendCutSend — fully open source, free, and local

@earthtojake · 865 views · 2026-10-02
CLONE: whole-body humanoid teleoperation from a single MR headset — closed-loop correction plus MoE tracking keeps 5.1cm error over 8.9m, built for long-horizon data collection
3:28

CLONE: whole-body humanoid teleoperation from a single MR headset — closed-loop correction plus MoE tracking keeps 5.1cm error over 8.9m, built for long-horizon data collection

@robotsdigest · 611 views · 2026-10-01
HumanoidTeleoperation

As an Amazon Associate, we earn from qualifying purchases.