TwinVLA: Data-Efficient Bimanual Manipulation with Twin Single-Arm Vision-Language-Action Models
Paper
• 2511.05275 • Published
Tabletop-Sim Datasets
Datasets of Tabletop-Sim (https://github.com/jellyho/Tabletop-Sim), from TwinVLA (ICLR 2026)
-
-
jellyho/tabletop-simulation-hdf5
Viewer • Updated • 45.1k • 39 -
jellyho/tabletop-simulation-rlds
Updated • 250 -
jellyho/aloha_dish_drainer
Viewer • Updated • 14.2k • 36 -
jellyho/aloha_handover_box
Viewer • Updated • 23.4k • 50 -
jellyho/aloha_lift_box
Viewer • Updated • 23k • 33 -
jellyho/aloha_shoes_table
Viewer • Updated • 25.5k • 35 -
jellyho/aloha_box_into_pot_easy
Viewer • Updated • 8.59k • 26