Hoshipu/stageguard-qwen3.5-0.8b-b1k-task69-removed-fullparam-45k
Image-Text-to-Text • 0.9B • Updated • 17 • 2
Zhiyuan Li
Hoshipu
AI & ML interests
Embodied AI, robot learning, VLA and world action models, agentic robot learning. Robotics @ University of Toronto (RVL) and Huawei Noah's Ark Lab.
Recent Activity
updated a dataset 7 days ago
Hoshipu/reflex-b1k-task1-2f published a dataset 7 days ago
Hoshipu/reflex-b1k-task1-2f updated a dataset 9 days ago
Hoshipu/reflex-b1k-task1-2dOrganizations
models 105
Hoshipu/StageGuard-Qwen3.5-4B-LoRA-delay2-step-20000
Updated • 5
Hoshipu/behavior1k-task16-moving-boxes
Robotics • Updated
Hoshipu/pi05-b1kt4546-joint-ck2
Updated
Hoshipu/pi05-b1kt77-ft-nolang-50t20k
Updated
Hoshipu/pi05-b1kt77-ft-nolang-25k20k
Updated
Hoshipu/pi05-robodyna-baseline-bs256
Updated
Hoshipu/pi05-b1kt87-ft-nolang-25k30k
Updated
Hoshipu/pi05-b1kt73-ft-nolang-25k30k
Updated
Hoshipu/pi05-b1kt98-ft-nolang-25k30k
Updated
datasets 27
Hoshipu/reflex-b1k-task1-2f
Preview • Updated • 105
Hoshipu/reflex-b1k-task1-2d
Viewer • Updated • 738 • 227
Hoshipu/reflex-b1k-task1-2c
Viewer • Updated • 849 • 855
Hoshipu/reflex-b1k-task1-recoveries
Preview • Updated • 1.7k
Hoshipu/libero-logic
Updated • 1.17k
Hoshipu/robodyna-lerobot-suite
Updated • 116
Hoshipu/real_robot_data
Preview • Updated • 8.87k
Hoshipu/b1k_official_10tasks_combined
R1Pro • Updated • 1.96k episodes • 151
Hoshipu/b1k_perturb_recovery3_task0_curated
R1Pro • Updated • 836 episodes • 92
Hoshipu/b1k_mp_radio_task0_v2
R1Pro • Updated • 1.35k episodes • 151 • 1