arxiv:2511.01093
Jarrod Barnes PRO
Jarrodbarnes
AI & ML interests
Continual Learning, Reinforcement Learning
Recent Activity
updated
a dataset
about 11 hours ago
Jarrodbarnes/osworld-train-v1
published
a dataset
about 11 hours ago
Jarrodbarnes/osworld-train-v1
updated
a dataset
about 11 hours ago
Jarrodbarnes/osworld-union-v1
Organizations
models
40
Jarrodbarnes/osworld-vlm-gspo-step25
4B
•
Updated
•
8
Jarrodbarnes/osworld-vlm-grpo-cookbook-v3
Updated
Jarrodbarnes/osworld-vlm-distill-iter49
2B
•
Updated
•
7
Jarrodbarnes/osworld-vlm-4b-sft
4B
•
Updated
•
6
Jarrodbarnes/osworld-vlm-sft-step25
4B
•
Updated
•
29
Jarrodbarnes/osworld-vlm-sft-qwen3-vl-4b-instruct
Updated
Jarrodbarnes/osworld-vlm-grpo-qwen3-vl-4b-instruct
Updated
Jarrodbarnes/osworld-vlm-grpo-v7
Updated
Jarrodbarnes/osworld-vlm-grpo-distill-v1
Updated
Jarrodbarnes/osworld-vlm-grpo-hightemp-v1
Updated
datasets
39
Jarrodbarnes/osworld-train-v1
Updated
Jarrodbarnes/osworld-union-v1
Viewer
•
Updated
•
149
•
27
•
2
Jarrodbarnes/osworld-merged-replay
Viewer
•
Updated
•
47
•
24
Jarrodbarnes/osworld-sft-hybrid
Updated
•
24
Jarrodbarnes/osworld-sft-curated-final
Viewer
•
Updated
•
1
•
23
Jarrodbarnes/osworld-sft-curated-v3
Updated
•
17
Jarrodbarnes/osworld-variance-subset
Viewer
•
Updated
•
28
•
18
Jarrodbarnes/osworld-exploratory-rollouts
Updated
•
22
Jarrodbarnes/osworld-vlm-distill-data
Viewer
•
Updated
•
93
•
26
Jarrodbarnes/osworld-sft-clean
Viewer
•
Updated
•
86
•
25