pith. sign in

How far are we to GPT-4V? closing the gap to commercial multimodal models with open-source suites.Science China Information Sciences, 67(12):220101,

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it

fields

cs.CV 1

years

2026 1

verdicts

UNVERDICTED 1

representative citing papers

A More Word-like Image Tokenization for MLLMs

cs.CV · 2026-05-18 · unverdicted · novelty 6.0

DiVT clusters patch embeddings into coherent semantic units and adapts token count to image complexity, matching or exceeding baselines with fewer visual tokens on multimodal benchmarks.

citing papers explorer

Showing 1 of 1 citing paper.

  • A More Word-like Image Tokenization for MLLMs cs.CV · 2026-05-18 · unverdicted · none · ref 10

    DiVT clusters patch embeddings into coherent semantic units and adapts token count to image complexity, matching or exceeding baselines with fewer visual tokens on multimodal benchmarks.