Paper, Data and Checkpoints for ''CronusVLA: Towards Efficient and Robust Manipulation
via Multi-Frame Vision-Language-Action Modeling''
LiHaoHN
JeasLee
AI & ML interests
VLA, VLM, Embodied AI, AIGC
Recent Activity
upvoted a paper about 21 hours ago
JoyAI-VL-Interaction: Real-Time Vision-Language Interaction Intelligence liked a dataset 17 days ago
YixiangChen/FlowWAM_WorldArena liked a model 29 days ago
bytedance-research/LanceOrganizations
models 12
JeasLee/cronusvla_7B_libero_10_w_wrist
Robotics • Updated • 4
JeasLee/cronusvla_7B_libero_spatial_w_wrist
Robotics • Updated • 7
JeasLee/openvla-0.5b-prismatic
Robotics • Updated • 8
JeasLee/cronusvla_7B_libero_spatial
Robotics • Updated • 23
JeasLee/cronusvla_7B_libero_object_w_wrist
Robotics • Updated • 4
JeasLee/cronusvla_7B_libero_goal_w_wrist
Robotics • Updated • 12
JeasLee/cronusvla_7B_libero_object
Robotics • Updated • 18
JeasLee/cronusvla_7B_libero_10
Robotics • Updated • 28 • 1
JeasLee/cronusvla_7B_libero_goal
Robotics • Updated • 19
JeasLee/cronusvla_0.5B_bridge_rt_1
Robotics • Updated • 12