Gyubeum Lim

Gyubeum's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

updated a dataset 4 days ago

Gyubeum/AndroidFlux_RL_Train

Viewer • Updated 4 days ago • 20k • 581

updated 2 datasets 13 days ago

Gyubeum/AndroidFlux_RM_train

Preview • Updated 13 days ago • 51

Gyubeum/AndroidFlux_Evaluation_Output

Updated Sep 6 • 822

updated a dataset 14 days ago

Gyubeum/AndroidFlux_RM_Eval

Viewer • Updated 14 days ago • 5.06k • 147

updated a model 15 days ago

Gyubeum/Qwen3-VL-8B-Instruct-UI-Genie-scoring-128k-balanced-bt-naive

Image-Text-to-Text • 9B • Updated 15 days ago • 28

updated a model 17 days ago

Gyubeum/Qwen3-VL-8B-Instruct-UI-Genie-scoring-128k-balanced-pl-naive

Image-Text-to-Text • 9B • Updated 17 days ago • 25

published 2 models 17 days ago

Gyubeum/Qwen3-VL-8B-Instruct-UI-Genie-scoring-128k-balanced-bt-naive

Image-Text-to-Text • 9B • Updated 15 days ago • 28

Gyubeum/Qwen3-VL-8B-Instruct-UI-Genie-scoring-128k-balanced-pl-naive

Image-Text-to-Text • 9B • Updated 17 days ago • 25

updated a model 21 days ago

Gyubeum/Qwen3-VL-8B-Instruct-UI-Genie-scoring-64k-bt_with_highest

Image-Text-to-Text • 9B • Updated 21 days ago • 27

published a model 21 days ago

Gyubeum/Qwen3-VL-8B-Instruct-UI-Genie-scoring-64k-bt_with_highest

Image-Text-to-Text • 9B • Updated 21 days ago • 27

updated a dataset 22 days ago

Gyubeum/AndroidFlux_Failure_Recovery_Eval

Updated 22 days ago • 99

updated a dataset 26 days ago

Gyubeum/AndroidFlux_results

Viewer • Updated 26 days ago • 5.26k • 179

updated a model 27 days ago

Gyubeum/Qwen3-VL-8B-Instruct-UI-Genie-128k-balanced

9B • Updated 27 days ago • 25

published a model 27 days ago

Gyubeum/Qwen3-VL-8B-Instruct-UI-Genie-128k-balanced

9B • Updated 27 days ago • 25

updated a model 28 days ago

Gyubeum/Qwen3-VL-8B-Instruct-UI-Genie-scoring-128k-balanced

8B • Updated 28 days ago • 24

published a model 28 days ago

Gyubeum/Qwen3-VL-8B-Instruct-UI-Genie-scoring-128k-balanced

8B • Updated 28 days ago • 24

updated a collection 29 days ago

AndroidFlux

Collection

Evaluating and Reward Modeling Failure Recovery Capabilities in Mobile-Use Multimodal Agents • 8 items • Updated 29 days ago