G²TR reduces visual tokens and prefill compute by 1.94x in separate-encoder UMMs via generation-guided importance from VAE latent consistency, balanced selection, and merging, while preserving reasoning accuracy and editing quality.
Unimod: Efficient unified multimodal transformers with mixture-of-depths
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 2roles
background 1polarities
background 1representative citing papers
A literature survey that categorizes how Mixture-of-Experts architectures address multimodal learning challenges and identifies open research gaps.
citing papers explorer
-
G$^2$TR: Generation-Guided Visual Token Reduction for Separate-Encoder Unified Multimodal Models
G²TR reduces visual tokens and prefill compute by 1.94x in separate-encoder UMMs via generation-guided importance from VAE latent consistency, balanced selection, and merging, while preserving reasoning accuracy and editing quality.
-
Tackling Multimodal Learning Challenges with Mixture-of-Expert: A Survey
A literature survey that categorizes how Mixture-of-Experts architectures address multimodal learning challenges and identifies open research gaps.