arxiv:2406.04412
dongyoung kim
vangard703
AI & ML interests
None yet
Recent Activity
submitted a paper 1 day ago
RoboAlign: Learning Test-Time Reasoning for Language-Action Alignment in Vision-Language-Action Models upvoted a paper 1 day ago
SpatialBoost: Enhancing Visual Representation through Language-Guided ReasoningOrganizations
models 55
vangard703/V8_traj_rl
Image-Text-to-Text • 8B • Updated
vangard703/oxe_1_ep_RL_50step
Image-Text-to-Text • 8B • Updated • 1
vangard703/oxe_1_ep_RL_25step
Image-Text-to-Text • 8B • Updated • 5
vangard703/v8_ecot_finetune
Image-Text-to-Text • 8B • Updated • 1
vangard703/v8_1_ecot_finetune
Image-Text-to-Text • 8B • Updated • 1
vangard703/V8_1_traj_rl
Image-Text-to-Text • 8B • Updated
vangard703/v8_1_movement_rl
Image-Text-to-Text • 8B • Updated
vangard703/v8_movement_rl
Image-Text-to-Text • 8B • Updated
vangard703/V8_1_full_Fast_100K_25ep
Image-Text-to-Text • 8B • Updated • 1
vangard703/v8_only_vlm
Image-Text-to-Text • 8B • Updated • 2
datasets 14
vangard703/two_arm_transport
Updated • 4
vangard703/two_arm_three_piece_assembly
Updated • 7
vangard703/two_arm_threading
Updated • 5
vangard703/two_arm_pouring
Updated • 5
vangard703/two_arm_lift_tray
Updated • 4
vangard703/two_arm_drawer_cleanup
Updated • 7
vangard703/two_arm_coffee
Updated • 6
vangard703/two_arm_can_sort_random
Updated • 8
vangard703/two_arm_box_cleanup
Updated • 4
vangard703/dexmimicgen_training_dataset
Updated • 19