M2-Reasoning-7B reports state-of-the-art average scores across eight multimodal reasoning benchmarks using synthetic spatial data and dynamic multi-task RLVR.
– ObjectS (Object Score): Assess if the object(s) relevant to the question are clearly visible and identifiable in the image
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
M2-Reasoning: Empowering MLLMs with Unified General and Spatial Reasoning
M2-Reasoning-7B reports state-of-the-art average scores across eight multimodal reasoning benchmarks using synthetic spatial data and dynamic multi-task RLVR.