Pith. sign in

Vision transformers need registers,

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

2026 1

verdicts

CONDITIONAL 1

roles

background 1

polarities

unclear 1

representative citing papers

Visual Token Codec: Unleashing Spatial Redundancy for ViT Feature Coding

cs.CV · 2026-08-09 · conditional · novelty 6.0

The Visual Token Codec compresses ViT intermediate features by entropy-coding patch tokens on their native grid instead of a flattened sequence, reducing bitrate by 15.7x to 37.4x at 90% of uncompressed performance over a VTM-based baseline.

citing papers explorer

Showing 1 of 1 citing paper.

  • Visual Token Codec: Unleashing Spatial Redundancy for ViT Feature Coding cs.CV · 2026-08-09 · conditional · none · ref 8

    The Visual Token Codec compresses ViT intermediate features by entropy-coding patch tokens on their native grid instead of a flattened sequence, reducing bitrate by 15.7x to 37.4x at 90% of uncompressed performance over a VTM-based baseline.