Jiazhe Wei

void-2024

8 3

·

https://jiazhewei.github.io/

AI & ML interests

Generative models World models World action models Multimodal learning

Recent Activity

upvoted a paper about 1 month ago

WeVisDoc: From Coverage to Capability for Robust End-to-End Document Parsing

upvoted a collection about 1 month ago

liked a model about 1 month ago

void-2024/PosterCopilot

View all activity

Organizations

None yet

upvoted a paper about 1 month ago

WeVisDoc: From Coverage to Capability for Robust End-to-End Document Parsing

Paper • 2609.20423 • Published Sep 17 • 48

upvoted a collection about 1 month ago

WeVisDoc

3 items • Updated about 22 hours ago • 15

upvoted a paper about 2 months ago

WeMM-Embedding: WeChat Multi-Modal Embedding Technical Report

Paper • 2608.24053 • Published Aug 25 • 71

upvoted a paper 3 months ago

AURORA-LM: Autoencoding Unified Representation for Continuous-Latent Diffusion Language Modeling

Paper • 2608.02602 • Published Aug 3 • 85

upvoted a collection 4 months ago

DINOv3

DINOv3: foundation models producing excellent dense features, outperforming SotA w/o fine-tuning - https://arxiv.org/abs/2508.10104 • 15 items • Updated Mar 10 • 836

upvoted a paper 8 months ago

PosterCopilot: Toward Layout Reasoning and Controllable Editing for Professional Graphic Design

Paper • 2512.04082 • Published Dec 3, 2025 • 14

upvoted a paper 10 months ago

LongVie 2: Multimodal Controllable Ultra-Long Video World Model

Paper • 2512.13604 • Published Dec 15, 2025 • 76

upvoted a paper about 1 year ago

Visual Jigsaw Post-Training Improves MLLMs

Paper • 2509.25190 • Published Sep 29, 2025 • 37