Dongxu Li's picture

5 9 8

Dongxu Li

dxli1

·

AI & ML interests

None yet

Recent Activity

upvoted a paper 27 days ago

MinerU2.5: A Decoupled Vision-Language Model for Efficient High-Resolution Document Parsing

authored a paper about 1 month ago

MANZANO: A Simple and Scalable Unified Multimodal Model with a Hybrid Vision Tokenizer

upvoted a paper about 1 month ago

AToken: A Unified Tokenizer for Vision

View all activity

Organizations

Papers 11

arxiv:2509.16197

arxiv:2503.06885

arxiv:2410.05993

arxiv:2401.01827

models 1

dxli1/LEOSAM

Updated Mar 1, 2024

datasets 0

None public yet