activity
20242026
most citedLeveraging Visual Tokens for Extended Text Contexts in Multi-Modal Learning

2 citations · 3 across the 5 of their papers we have counts for

collaborators
Showing 2026Show all

1 paper · 1 filter

cs.CV2026

Residual Decoder Adapter: ID-Preserving Tokenizer Adaption for Autoregressive Text Rendering

Dongxing Mao, Jinpeng Wang, Jiahao Tang +6

Visual Autoregressive (AR) models generate images by predicting discrete tokens that are decoded by a visual tokenizer. Despite demonstrating strong overall image generation abilit…