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 • 38 -
jellyho/tabletop-simulation-rlds
Updated • 16 -
jellyho/aloha_dish_drainer
Viewer • Updated • 14.2k • 30 -
jellyho/aloha_handover_box
Viewer • Updated • 23.4k • 40 -
jellyho/aloha_lift_box
Viewer • Updated • 23k • 27 -
jellyho/aloha_shoes_table
Viewer • Updated • 25.5k • 29 -
jellyho/aloha_box_into_pot_easy
Viewer • Updated • 8.59k • 10