FailSense Datasets and Benchmarks ACIDE/AHA-Calvin-1p Viewer • Updated 29 days ago • 12.3k • 246 ACIDE/AHA-Calvin-2p Viewer • Updated 29 days ago • 12.3k • 171 ACIDE/AHA-Calvin Viewer • Updated 29 days ago • 12.3k • 90 ACIDE/DROID_1p_bench Viewer • Updated 19 days ago • 138 • 108
User-VLM 360° Datasets and Benchmarks ACIDE/user-vlm-pt Viewer • Updated Feb 14 • 132k • 54 ACIDE/user-vlm-instruct Viewer • Updated Feb 14 • 112k • 24 ACIDE/user-vlm-dpo Viewer • Updated Feb 14 • 17.2k • 22 ACIDE/user-vlm-face-bench Viewer • Updated Feb 14 • 1.2k • 8
FailSense 3B Failure Detection for Robotic Manipulation with VLMs ACIDE/FailSense-AHA-Calvin-1p-3b Updated 24 days ago ACIDE/FailSense-AHA-Calvin-2p-3b Updated 17 days ago • 64 ACIDE/FailSense-Video-Calvin-1p-3b Updated 17 days ago • 48 ACIDE/FailSense-Video-Calvin-2p-3b Updated 17 days ago • 102
User-VLM 360° Models A series of Personalized Vision Language Models for Social Human-Robot Interactions ACIDE/User-VLM-3B-base Image-Text-to-Text • 3B • Updated Feb 21 • 7 ACIDE/User-VLM-10B-base Image-Text-to-Text • 10B • Updated Feb 21 • 36 ACIDE/User-VLM-3B-Instruct Visual Question Answering • Updated Feb 15 ACIDE/User-VLM-10B-Instruct Visual Question Answering • Updated Feb 15
FailSense Datasets and Benchmarks ACIDE/AHA-Calvin-1p Viewer • Updated 29 days ago • 12.3k • 246 ACIDE/AHA-Calvin-2p Viewer • Updated 29 days ago • 12.3k • 171 ACIDE/AHA-Calvin Viewer • Updated 29 days ago • 12.3k • 90 ACIDE/DROID_1p_bench Viewer • Updated 19 days ago • 138 • 108
FailSense 3B Failure Detection for Robotic Manipulation with VLMs ACIDE/FailSense-AHA-Calvin-1p-3b Updated 24 days ago ACIDE/FailSense-AHA-Calvin-2p-3b Updated 17 days ago • 64 ACIDE/FailSense-Video-Calvin-1p-3b Updated 17 days ago • 48 ACIDE/FailSense-Video-Calvin-2p-3b Updated 17 days ago • 102
User-VLM 360° Datasets and Benchmarks ACIDE/user-vlm-pt Viewer • Updated Feb 14 • 132k • 54 ACIDE/user-vlm-instruct Viewer • Updated Feb 14 • 112k • 24 ACIDE/user-vlm-dpo Viewer • Updated Feb 14 • 17.2k • 22 ACIDE/user-vlm-face-bench Viewer • Updated Feb 14 • 1.2k • 8
User-VLM 360° Models A series of Personalized Vision Language Models for Social Human-Robot Interactions ACIDE/User-VLM-3B-base Image-Text-to-Text • 3B • Updated Feb 21 • 7 ACIDE/User-VLM-10B-base Image-Text-to-Text • 10B • Updated Feb 21 • 36 ACIDE/User-VLM-3B-Instruct Visual Question Answering • Updated Feb 15 ACIDE/User-VLM-10B-Instruct Visual Question Answering • Updated Feb 15
