Skip to content
Agientry
ZH

Demos

AIGC demos filed by vertical — agents and LLMs doing real work, world models, AI-made games and design. Each clip carries its vertical and capability domain; pick a chip to narrow the feed.

WaterfallPagination
All verticalsDevelopmentData & AnalyticsSecurityDocs & SlidesMediaDesign & FrontendGame MakingResearchKnowledgeEducationMarketing & GrowthCommerce & RetailLegal & FinanceHealthcareManufacturing
RoboJEPA: The First Scaling Law for Multi-Embodiment World Models
1:06

RoboJEPA: The First Scaling Law for Multi-Embodiment World Models

@artemZholus · 335 views · 2026-10-10
World ModelsJEPA
LeWAM: An End-to-End JEPA That Controls Real Robots
0:57

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

@Minghao__Fu · 307 views · 2026-10-09
World ModelsJEPA
MobileVISTA: Pose Generalization from Single-Pose Demos
0:15

MobileVISTA: Pose Generalization from Single-Pose Demos

@s_wistreich · 242 views · 2026-10-07
Mobile ManipulationData Augmentation
JEV-27B-VL: Calibrated Visual Decisions for Long-Context Workflows
0:25

JEV-27B-VL: Calibrated Visual Decisions for Long-Context Workflows

@ModelScope2022 · 379 views · 2026-10-10
Vision-language modelsCalibrated Confidence
Whole-Body UMI: Humanoid Whole-Body Manipulation from UMI Data
2:28

Whole-Body UMI: Humanoid Whole-Body Manipulation from UMI Data

@ZhongyuLi4 · 419 views · 2026-10-10
HumanoidWhole-Body Control
UVTA: Unified Visual-Tactile-Action Modeling for Dexterous Manipulation
0:28

UVTA: Unified Visual-Tactile-Action Modeling for Dexterous Manipulation

@CyberRobooo · 345 views · 2026-10-10
Dexterous ManipulationTactile Sensing
SpatialLM: Labeled 3D Room Layouts from Monocular Phone Video
0:51

SpatialLM: Labeled 3D Room Layouts from Monocular Phone Video

@0x0SojalSec · 675 views · 2026-10-09
Spatial Intelligence3D Scene Understanding
Qwen-Image-2.1-Turbo lands on HuggingFace: 8 steps, same quality, 4x faster
0:21

Qwen-Image-2.1-Turbo lands on HuggingFace: 8 steps, same quality, 4x faster

@HuggingApps · 468 views · 2026-10-09
Qwen-ImageText-to-Image
Perceptive Humanoid Parkour Open-Sourced With Browser Demo
0:23

Perceptive Humanoid Parkour Open-Sourced With Browser Demo

@zhenkirito123 · 363 views · 2026-10-09
HumanoidParkour
EgoLAP: Language Actions and Motion Reasoning From Egocentric Human Data
0:28

EgoLAP: Language Actions and Motion Reasoning From Egocentric Human Data

@LihanZha · 273 views · 2026-10-09
Robot foundation modelsEgocentric Learning
Odyssey 3: World Models Let Robots Rehearse Physics
0:29

Odyssey 3: World Models Let Robots Rehearse Physics

@joaquintenest · 361 views · 2026-10-09
World ModelsSim-to-Real
VioLA: Learning Generalist Humanoid Control From Human Data
0:43

VioLA: Learning Generalist Humanoid Control From Human Data

@annamanasyan4 · 326 views · 2026-10-09
HumanoidWhole-Body Control

As an Amazon Associate, we earn from qualifying purchases.