Benchmark proposed (and used) in FedMosaic (ICLR 2026)
SNUMPR
SNUMPR
AI & ML interests
CV, Multimodal
Organizations
None yet
models 22
SNUMPR/llava-onevision-qwen2-7b-ov-multi-event
8B • Updated
SNUMPR/Terran-c
Text Generation • 2B • Updated • 3
SNUMPR/Terran-b
Text Generation • 2B • Updated • 4
SNUMPR/Zerg-c
Text Generation • 2B • Updated • 3
SNUMPR/Zerg-b
Text Generation • 2B • Updated • 2
SNUMPR/Terran-a
Text Generation • 2B • Updated • 3
SNUMPR/Zerg-a
Text Generation • 2B • Updated • 2
SNUMPR/Protoss-b
Text Generation • 2B • Updated • 11
SNUMPR/Protoss-a
Text Generation • 2B • Updated • 8
SNUMPR/Protoss-c
Text Generation • 2B • Updated • 5
datasets 8
SNUMPR/DRAKE
Updated • 207 • 5
SNUMPR/HFLB
Updated • 135 • 1
SNUMPR/VCG-bench
Preview • Updated • 9
SNUMPR/realfred_feat
Updated • 125 • 1
SNUMPR/realfred_json
Preview • Updated • 133 • 1
SNUMPR/vlm_rlaif_datasets
Preview • Updated • 13 • 2
SNUMPR/vlm_rlaif_eval_datasets
Updated • 5
SNUMPR/vlm_rlaif_train_anet_frames
Updated • 9