Gyubeum/AndroidFlux_Failure_Recovery_Eval_Agent
Updated • 280 • 1
AndroidFlux
[NeurIPS 2026 AgenticOS Workshop] Evaluating and Reward Modeling Failure Recovery Capabilities in Mobile-Use Multimodal Agents
-
-
Gyubeum/AndroidFlux_RL_Train
Viewer • Updated • 20k • 1.1k -
Gyubeum/AndroidFlux_Evaluation_Output
Updated • 377 -
Gyubeum/UI_Genie_128k
Viewer • Updated • 275k • 102 -
Gyubeum/UI_Genie_256k
Viewer • Updated • 479k • 69 -
Gyubeum/AndroidFlux_Failure_Recovery_Eval_RM
Viewer • Updated • 5.06k • 127 -
Gyubeum/Qwen3-VL-8B-Instruct-UI-Genie-BT-128K
Image-Text-to-Text • 8B • Updated • 56 -
Gyubeum/Qwen3-VL-8B-Instruct-UI-Genie-SFT-128K
Image-Text-to-Text • 9B • Updated • 52 -
Gyubeum/Qwen3-VL-8B-Instruct-UI-Genie-BT-256K
Image-Text-to-Text • 8B • Updated • 63