Paired 360 + first-person video of photoreal scenes, with per-frame depth, camera pose and actions.
AI & ML interests
None defined yet.
Recent Activity
Papers
Kaininja: Extending Native 3D Generators to the Part Level
AlayaVista: Streaming World Modeling from Panoramic States to Perspective Video
models 15
AlayaLab/AlayaWorld-stage1
Updated
AlayaLab/Evoke-Turbo
Text-to-Video • 14B • Updated • 254
AlayaLab/WorldSculpt
Updated • 18
AlayaLab/AlayaWorld-v1.1-stage3
Image-to-Video • Updated • 675 • 1
AlayaLab/AlayaWorld-v1.1-stage2b
Image-to-Video • Updated • 106
AlayaLab/AlayaWorld
Image-to-Video • Updated • 987 • 20
AlayaLab/Marionette
Video-to-Video • Updated • 24 • 9
AlayaLab/Evoke
Text-to-Video • Updated • 83 • 26
AlayaLab/AlayaInverseRenderer
Image-to-Image • Updated • 10 • 1
AlayaLab/AlayaRenderer
Text-to-Video • 1B • Updated • 17
datasets 11
AlayaLab/WorldRover-6scenes
Updated
AlayaLab/WorldRover-med_village
Preview • Updated • 572
AlayaLab/WorldRover
Preview • Updated • 935
AlayaLab/WorldRover-art_nouveau
Preview • Updated • 492
AlayaLab/WorldRover-venice
Preview • Updated • 467
AlayaLab/WorldRover-paris
Preview • Updated • 475
AlayaLab/Worldsculpt_data
Preview • Updated • 481 • 4
AlayaLab/AlayaWorld-v1.1-data
Preview • Updated • 52 • 1
AlayaLab/WildWorld
Preview • Updated • 48.3k • 7
AlayaLab/AgenticSTS-trajectories
Updated • 142 • 2