Evaluating and Reward Modeling Failure Recovery Capabilities in Mobile-Use Multimodal Agents
Gyubeum Lim
Gyubeum
AI & ML interests
None yet
Recent Activity
updated a dataset 1 day ago
Gyubeum/AndroidFlux_RL_Train updated a dataset 2 days ago
Gyubeum/AndroidFlux_RM_train updated a dataset 2 days ago
Gyubeum/AndroidFlux_Evaluation_OutputOrganizations
None yet
models 7
Gyubeum/Qwen3-VL-8B-Instruct-UI-Genie-scoring-128k-balanced-bt-naive
Image-Text-to-Text • 9B • Updated • 24
Gyubeum/Qwen3-VL-8B-Instruct-UI-Genie-scoring-128k-balanced-pl-naive
Image-Text-to-Text • 9B • Updated • 20
Gyubeum/Qwen3-VL-8B-Instruct-UI-Genie-scoring-64k-bt_with_highest
Image-Text-to-Text • 9B • Updated • 20
Gyubeum/Qwen3-VL-8B-Instruct-UI-Genie-128k-balanced
9B • Updated • 24
Gyubeum/Qwen3-VL-8B-Instruct-UI-Genie-scoring-128k-balanced
8B • Updated • 19
Gyubeum/Qwen3-VL-8B-Instruct-UI-Genie-scoring-64k-balanced
Image-Text-to-Text • 8B • Updated • 34
Gyubeum/Qwen3-VL-8B-Instruct-UI-Genie-scoring
Image-Text-to-Text • 8B • Updated • 18
datasets 12
Gyubeum/AndroidFlux_RL_Train
Viewer • Updated • 20k • 410
Gyubeum/AndroidFlux_RM_train
Preview • Updated • 59
Gyubeum/AndroidFlux_RM_Eval
Viewer • Updated • 5.06k • 166
Gyubeum/AndroidFlux_Failure_Recovery_Eval
Updated • 460
Gyubeum/AndroidFlux_results
Viewer • Updated • 5.26k • 844
Gyubeum/AndroidFlux_RL_Train_Test
Viewer • Updated • 23.1k • 36
Gyubeum/AndroidFlux_Evaluation_Output
Updated • 837
Gyubeum/UI_Genie_256k
Viewer • Updated • 479k • 245
Gyubeum/UI_Genie_128k
Viewer • Updated • 275k • 330
Gyubeum/Android_Flux
Updated • 18