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
OneCanvas: reproject video frames onto a single panoramic canvas so a stock 2D VLM reasons in 3D — SOTA on SQA3D, VSI-Bench and SPBench at an order of magnitude less compute

OneCanvas: reproject video frames onto a single panoramic canvas so a stock 2D VLM reasons in 3D — SOTA on SQA3D, VSI-Bench and SPBench at an order of magnitude less compute

@unknown · 572 views · 2026-06-19
VLMSpatial reasoning
Seamless 30-second Kung Fu Panda from two MiniMax H3 clips: ComfyUI-H3-Motion-Context chains clips via latent slicing and audio continuation
0:29

Seamless 30-second Kung Fu Panda from two MiniMax H3 clips: ComfyUI-H3-Motion-Context chains clips via latent slicing and audio continuation

@eternityspring · 944 views · 2026-10-02
MiniMax H3ComfyUI
NavVerse (CoRL 2026): a 200-scene, 10K-episode indoor-to-outdoor navigation benchmark — best zero-shot VLA reaches 11.6%, then halves across the door
2:51

NavVerse (CoRL 2026): a 200-scene, 10K-episode indoor-to-outdoor navigation benchmark — best zero-shot VLA reaches 11.6%, then halves across the door

@GhaffariMaani · 588 views · 2026-10-02
Embodied NavigationNavVerse
UBTECH opens its Liuzhou Super Smart Factory: 14,000 sqm, one humanoid every 10 minutes, 10,000-unit annual capacity — Walker S robots helping build Walker S
1:42

UBTECH opens its Liuzhou Super Smart Factory: 14,000 sqm, one humanoid every 10 minutes, 10,000-unit annual capacity — Walker S robots helping build Walker S

@roboindexio · 588 views · 2026-10-02
HumanoidUBTECH
Noetix Robotics unveils Boomy: full-body motion, real-time vision and practical control in a humanoid you can actually build and experiment with
0:49

Noetix Robotics unveils Boomy: full-body motion, real-time vision and practical control in a humanoid you can actually build and experiment with

@TheRealNoetix · 505 views · 2026-10-02
HumanoidNoetix
Boston Dynamics equips Atlas with a new 4-finger, 13-DoF hand: official blog explains robot hands built for modern AI and real work
1:03

Boston Dynamics equips Atlas with a new 4-finger, 13-DoF hand: official blog explains robot hands built for modern AI and real work

@ZappyZappy7 · 504 views · 2026-10-02
HumanoidBoston Dynamics
Stanford Real-Time EXPO-FT makes slow-but-smart VLAs real-time on robots: 42% to 97% with just 10 minutes of online data
0:22

Stanford Real-Time EXPO-FT makes slow-but-smart VLAs real-time on robots: 42% to 97% with just 10 minutes of online data

@LeoKharon · 593 views · 2026-10-02
VLAReinforcement Learning
AGIBOT A3 Ultra patrols Jinan Metro: WAIC 2026 "Best of Show" humanoid moves into public transit service
2:34

AGIBOT A3 Ultra patrols Jinan Metro: WAIC 2026 "Best of Show" humanoid moves into public transit service

@AGIBOTofficial · 504 views · 2026-10-02
HumanoidAgiBot Robotics
Clone shows VR teleoperation of Torso 3''s hand — open/close, point and pinch tracked in real time; after six months rebuilding everything, Torso 4 lands in early November with zero gears anywhere
0:14

Clone shows VR teleoperation of Torso 3''s hand — open/close, point and pinch tracked in real time; after six months rebuilding everything, Torso 4 lands in early November with zero gears anywhere

@CyberRobooo · 512 views · 2026-10-02
HumanoidMusculoskeletal
Microsoft MAI-Transcribe-2-Streaming tops Artificial Analysis: 2.5% WER with first partials ~100ms after speech — Japanese streamer demos it live: "the meeting-notes app era is over"
0:35

Microsoft MAI-Transcribe-2-Streaming tops Artificial Analysis: 2.5% WER with first partials ~100ms after speech — Japanese streamer demos it live: "the meeting-notes app era is over"

@studio_yebisu · 608 views · 2026-10-01
Speech-To-TextStreaming
MiniMax M3.1-Flash-Preview lands in MiniMax Code: 428B MoE (23B active), 1M context, native vision encoder — free to try in the desktop app
0:27

MiniMax M3.1-Flash-Preview lands in MiniMax Code: 428B MoE (23B active), 1M context, native vision encoder — free to try in the desktop app

@exploraX_ · 1.1k views · 2026-09-28
AI CodingLLM
Taiga-S1: a 1.2M-param model builds complete CAD parts in FreeCAD — ~1ms per decision on CPU, no LLM, no screenshots. Your agent plans, Taiga executes
0:08

Taiga-S1: a 1.2M-param model builds complete CAD parts in FreeCAD — ~1ms per decision on CPU, no LLM, no screenshots. Your agent plans, Taiga executes

@RoundtableSpace · 1k views · 2026-10-01
DesignCAD

As an Amazon Associate, we earn from qualifying purchases.