This collection hosts MRPO series introduced in paper, Breaking Failure Cascades: Step-Aware Reinforcement Learning for Medical Multimodal Reasoning
Data Mining and Information Systems Lab
dmis-lab
AI & ML interests
None yet
Recent Activity
View all activity
Organizations
models 56
dmis-lab/Qwen2.5-VL-7B-Instruct-MRPO
Image-Text-to-Text • 849k • Updated • 31
dmis-lab/Qwen3-VL-8B-Instruct-MRPO
Image-Text-to-Text • 770k • Updated • 20
dmis-lab/OSP-1.4B-100B-Shampoo-SSNorm-EmbProj
1B • Updated • 7 • 4
dmis-lab/OSP-1.4B-100B-Shampoo-SSNorm
1B • Updated • 4 • 3
dmis-lab/OSP-1.4B-100B-Muon-SSNorm-EmbProj
1B • Updated • 6 • 4
dmis-lab/OSP-1.4B-100B-Muon-EmbProj
1B • Updated • 10 • 3
dmis-lab/OSP-1.4B-100B-Muon-SSNorm
1B • Updated • 5 • 3
dmis-lab/OSP-1.4B-100B-Muon-Only
1B • Updated • 4 • 3
dmis-lab/OSP-1.4B-100B-Muon
1B • Updated • 4 • 3
dmis-lab/OSP-1.4B-100B-Adam
1B • Updated • 5 • 3
datasets 11
dmis-lab/ToxReason
Viewer • Updated • 35.6k • 82
dmis-lab/llama-3.1-medprm-reward-raw-test-set
Viewer • Updated • 5.47k • 6
dmis-lab/llama-3.1-medprm-reward-raw-training-set
Viewer • Updated • 11.7k • 14
dmis-lab/llama-3.1-medprm-reward-test-set
Updated • 25 • 2
dmis-lab/llama-3.1-medprm-reward-training-set
Viewer • Updated • 11.7k • 24 • 11
dmis-lab/TemporalHead
Viewer • Updated • 11 • 26 • 1
dmis-lab/meerkat-instructions
Viewer • Updated • 440k • 211 • 10
dmis-lab/RF-Collection
Preview • Updated • 57 • 1
dmis-lab/ChroKnowBench
Preview • Updated • 78 • 8
dmis-lab/ETHIC
Viewer • Updated • 1.99k • 31 • 7