Cite
Notes
Only stored in your browser.
Attribution
BitDance: Scaling Autoregressive Generative Models with Binary Tokens
arXiv 2026
Vision as a Dialect: Unifying Visual Understanding and Generation via Text-Aligned Representations
arXiv 2025
Improving Visual Grounding by Encouraging Consistent Gradient-based Explanations
CVPR 2023 1
from 3 papers
Hao Chen
Jiaming Han
Xiangyu Yue
Franck Dernoncourt
Hanyu Wang
Hao He
Huaibo Huang
Kushal Kafle
Lu Jiang
Qi Zhao