An 8B MLLM reaches state-of-the-art efficiency and performance under 30B by combining a unified 3D resampler, joint document-text training, and hybrid RL for reasoning modes.
Capsfusion: Rethinking image-text data at scale
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
MiniCPM-V 4.5: Cooking Efficient MLLMs via Architecture, Data, and Training Recipe
An 8B MLLM reaches state-of-the-art efficiency and performance under 30B by combining a unified 3D resampler, joint document-text training, and hybrid RL for reasoning modes.