Skip to content
Live
Trending storyPast story

dNaViT releases: Discrete code as a general visual representation

1 reports1 outlets8 days agoUpdate

The story so far

AI overview

Hugging Face has released dNaViT, a discrete native resolution visual Transformer, which matches or exceeds specific baselines in visual understanding, generation, and editing tasks through grouped product quantization and dual-branch objectives. It performs excellently on 12 visual understanding benchmarks, 4 generation benchmarks, and one image editing benchmark, proving that discrete vocabulary can serve as a universal visual representation.

AI-written from the reports · Updated 8 days ago

Coverage timeline

Follow the coverage to see every side of the story.

11 Nov
  1. Hugging Face Daily Papers
    dNaViT: Discrete Codes are General-Purpose Visual Representations

    dNaViT is a discrete native resolution vision Transformer that matches or exceeds specific baselines in visual understanding, generation, and editing tasks through grouped product quantization and dual-branch targets. It performs excellently on 12 visual understanding benchmarks, 4 generation benchmarks, and one image editing benchmark, proving that discrete vocabulary can be a universal visual representation

Heat over time

Now
3
Peak
512 Nov, 06:00
24h change
-49%

Hover or tap the chart to see each hour; use the arrow keys on a keyboard.