Turning benchmark to data generation and post-training infrastructure in agentic AI
Kuma Kuma PRO
MitakaKuma
AI & ML interests
Towards AutoResearch Agentic AI
Recent Activity
published a model about 2 hours ago
MitakaKuma/BaT-Qwen3.5-9B-0815 updated a collection about 2 hours ago
Benchmark-as-Teacher updated a collection about 2 hours ago
Benchmark-as-TeacherOrganizations
models 6
MitakaKuma/BaT-Qwen3.5-9B-0815
Text Generation • 9B • Updated • 7
MitakaKuma/BaT-Qwen3.5-4B-0815
Image-Text-to-Text • 5B • Updated • 5
MitakaKuma/SUMI
Updated • 1
MitakaKuma/SMILE
Image-to-Image • Updated • 1
MitakaKuma/SMILE_baselines
Updated
MitakaKuma/PanTS_Segmenter
Image Segmentation • Updated • 1
datasets 13
MitakaKuma/public-agentic-cowork-benchmarks
Viewer • Updated • 143 • 1.93k
MitakaKuma/public-agentic-med-benchmarks
Preview • Updated • 208
MitakaKuma/AutoMedBench-Lite-release
Updated • 494
MitakaKuma/BaT-RL-data
Viewer • Updated • 126 • 28
MitakaKuma/BaT-SFT-data
Viewer • Updated • 9.96k • 29
MitakaKuma/AutoMedBench-Full-release
Updated • 344
MitakaKuma/SUMI-OpenCT
Updated • 80
MitakaKuma/kuma-nvda-demo-test
Viewer • Updated • 3 • 5
MitakaKuma/automedbench-report_gen-task-data
Updated • 10
MitakaKuma/automedbench-seg-task-data
Viewer • Updated • 5.04k • 33