Pith. sign in

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 1

years

2025 1

verdicts

CONDITIONAL 1

roles

background 1

polarities

background 1

representative citing papers

Training-Free Reasoning and Reflection in MLLMs

cs.CV · 2025-05-22 · conditional · novelty 5.0

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.

citing papers explorer

Showing 1 of 1 citing paper.

  • Training-Free Reasoning and Reflection in MLLMs cs.CV · 2025-05-22 · conditional · none · ref 29

    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.