Pith. sign in

Llava-onevision: Easy visual task transfer

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

1 Pith paper citing it

fields

cs.CV 1

years

2025 1

verdicts

CONDITIONAL 1

representative citing papers

Token Sequence Compression for Efficient Multimodal Computing

cs.CV · 2025-04-24 · conditional · novelty 4.0

Simple cluster-based averaging of visual tokens is competitive with, and sometimes better than, attention-based token selection on LLaVA and VILA benchmarks, though the advantage over prior methods is mixed.

citing papers explorer

Showing 1 of 1 citing paper.

  • Token Sequence Compression for Efficient Multimodal Computing cs.CV · 2025-04-24 · conditional · none · ref 8

    Simple cluster-based averaging of visual tokens is competitive with, and sometimes better than, attention-based token selection on LLaVA and VILA benchmarks, though the advantage over prior methods is mixed.