Training-free, layer-wise weight merging of an MLLM with a reasoning LLM, using attention-derived priors, raises MMMU accuracy from 63.9 to 69.2 at the 38B scale.
Metagpt: Merging large language models using model exclusive task arithmetic
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
Training-Free Reasoning and Reflection in MLLMs
Training-free, layer-wise weight merging of an MLLM with a reasoning LLM, using attention-derived priors, raises MMMU accuracy from 63.9 to 69.2 at the 38B scale.