This is the collection of FineVLA, including the RoboFine-Bench RoboFine-VLM and FineVLA-policyLA
AI & ML interests
None defined yet.
Recent Activity
models 12
xlangai/RoboFine-VLM-397B-A17B
Video-Text-to-Text • 403B • Updated • 61 • 8
xlangai/OpenCUA-7B
Image-Text-to-Text • 8B • Updated • 6.93k • 33
xlangai/OpenCUA-32B
Image-Text-to-Text • 33B • Updated • 321 • 29
xlangai/OpenCUA-72B
Image-Text-to-Text • 73B • Updated • 1.22k • 7
xlangai/VideoAgentTrek-ScreenFilter
Updated • 1
xlangai/VideoAgentTrek-CUA-7B
8B • Updated • 1
xlangai/VideoAgentTrek-IDM-s2-7B
8B • Updated • 5 • 2
xlangai/VideoAgentTrek-IDM-s1-7B
8B • Updated • 17 • 1
xlangai/Jedi-3B-1080p
Image-Text-to-Text • 4B • Updated • 97 • 19
xlangai/Jedi-7B-1080p
Image-Text-to-Text • 8B • Updated • 224 • 31
datasets 38
xlangai/ubuntu_osworld_verified_trajs
Updated • 3.5k • 19
xlangai/osworld_v2_assets
Viewer • Updated • 343 • 376k • 1
xlangai/osworld_v2_assets_gated
Updated • 5.65k • 1
xlangai/osworld_v2_tasks
Viewer • Updated • 1 • 1.89k • 17
xlangai/osworld2.0-trajectory
Updated • 18.8k • 7
xlangai/v2-image
Updated • 1.04k
xlangai/RoboFine-bench
Viewer • Updated • 1k • 1.6k • 5
xlangai/osworld2.0_human_crosscheck
Updated • 61
xlangai/ubuntu_osworld2_trajs
Viewer • Updated • 180k • 27
xlangai/CUA-Gym
Viewer • Updated • 10.9k • 675 • 24