arxiv:2605.09269
Rui Liu
lr10260
·
AI & ML interests
None yet
Recent Activity
updated a dataset about 9 hours ago
lr10260/rlaif_v_filtered published a dataset about 12 hours ago
lr10260/rlaif_v_filtered upvoted a paper 1 day ago
Reinforcing Multimodal Reasoning Against Visual DegradationOrganizations
models 19
lr10260/DUPL-4B
5B • Updated • 16
lr10260/DUPL-8B
9B • Updated • 12
lr10260/GRPO-8B
9B • Updated • 24
lr10260/GRPO-4B
5B • Updated • 26
lr10260/DUPL-D-7B
8B • Updated • 15
lr10260/DUPL-G-7B
8B • Updated • 25
lr10260/StaticRubric-8B
9B • Updated • 18
lr10260/NoRubric-8B
9B • Updated • 19
lr10260/DeltaRubric-Curriculum-8B
9B • Updated • 18
lr10260/DeltaRubric
Updated