MM-Eureka models trained via rule-based RL on the new MMK12 dataset achieve competitive or superior multimodal mathematical reasoning performance compared to models like InternVL2.5-78B while trailing slightly behind o1.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
MM-Eureka: Exploring the Frontiers of Multimodal Reasoning with Rule-based Reinforcement Learning
MM-Eureka models trained via rule-based RL on the new MMK12 dataset achieve competitive or superior multimodal mathematical reasoning performance compared to models like InternVL2.5-78B while trailing slightly behind o1.