Training dataset and the warm-up checkpoint for paper Don’t Blind Your VLA: Aligning Visual Representations for OOD Generalization
Nikita
tttonyalpha
AI & ML interests
None yet
Recent Activity
authored a paper 11 days ago
$μ$VLA: On Recurrent Memory for Partially Observable Manipulation in VLA Models authored a paper 11 days ago
Does VLA Even Know the Basics? Measuring Commonsense and World Knowledge Retention in Vision-Language-Action ModelsOrganizations
None yet
models 23
tttonyalpha/pi05_vla_arena_cube_plate_3_try
Robotics • 4B • Updated • 22
tttonyalpha/act_vla_arena_pick_cube_1_try
Robotics • 51.7M • Updated • 2
tttonyalpha/pi05_vla_arena_pick_cube_2_try
Robotics • 4B • Updated • 9
tttonyalpha/pi05_vla_arena_2_test_pick_cube_norm_std
Updated
tttonyalpha/pi05_vla_arena_2_test_pick_cube_50k
4B • Updated • 6
tttonyalpha/pi05_vla_arena_3_test_pick_cube_100k
4B • Updated • 4
tttonyalpha/pi05_vla_arena_1_test_camera_normalized
Robotics • 4B • Updated • 2
tttonyalpha/pi05_vla_arena_test_ver3_30k
4B • Updated • 2
tttonyalpha/pi05_vla_arena_test_ver2_50k
4B • Updated • 1
tttonyalpha/pi05_vla_arena_1_test
Robotics • 4B • Updated • 3
datasets 26
tttonyalpha/vla_arena_pick_cube_test_0
Viewer • Updated • 4 • 16
tttonyalpha/mikasa-robo-vla-5-merged-new
Viewer • Updated • 10 • 19
tttonyalpha/mikasa-robo-vla-5-merged
Viewer • Updated • 10 • 4
tttonyalpha/mikasa-robo-vla-merged-5-tasks-vla-v0
Viewer • Updated • 10 • 23
tttonyalpha/mikasa-robo-vla-pi05-merged-5
Viewer • Updated • 10 • 15
tttonyalpha/mikasa-robo-vla-remember_shape_and_color_3x3_vla_v0
Viewer • Updated • 3.82k • 12
tttonyalpha/mikasa-robo-vla-remember_color_5_vla_v0
Viewer • Updated • 4.07k • 10
tttonyalpha/mikasa-robo-vla-intercept_grab_medium_vla_v0
Viewer • Updated • 8.93k • 17
tttonyalpha/mikasa-robo-vla-shell_game_push_vla_v0
Viewer • Updated • 3.99k • 17
tttonyalpha/mikasa-robo-vla-5-merged-fixed
Viewer • Updated • 10 • 17