Donghao Zhou

donghao-zhou

·

https://correr-zhou.github.io

AI & ML interests

Generative AI

Recent Activity

upvoted a paper 1 day ago

G-STAR: Group-Scaled Token Capacity for Deeply Compressed Autoregressive Generation

authored a paper 9 days ago

Qwen-Image-PE: Learning Visual Design for Text-to-Image Prompt Enhancement

upvoted a paper 9 days ago

EmoReward: Self-Evolving Reward Calibration for Emotional Video Generation RL

View all activity

Organizations

Collections 5

View 5 collections

Papers 20

arxiv:2610.33472

arxiv:2609.38541

arxiv:2609.23784

arxiv:2609.07398

models 3

donghao-zhou/PackLab-VLM-9B

Image-Text-to-Text • 9B • Updated Sep 17 • 15

donghao-zhou/ThinkV2V-5B

Video-to-Video • Updated Aug 10 • 1

donghao-zhou/HiFi-Inpaint

Image-to-Image • Updated Jun 5 • 105 • 2

datasets 8

donghao-zhou/PackData-20K

Viewer • Updated Sep 17 • 20k • 211

donghao-zhou/PackLab-Bench

Viewer • Updated Sep 17 • 60 • 78

donghao-zhou/ThinkV2V-150K

Updated Aug 11 • 38 • 1

donghao-zhou/OpenVE-HQ-1M

Updated Aug 11 • 64

donghao-zhou/ThinkV2V-Bench

Viewer • Updated Aug 6 • 308 • 72 • 1

donghao-zhou/HP-Image-40K

Updated Jun 5 • 386 • 7

donghao-zhou/OmniShow_example_dataset

Viewer • Updated Apr 25 • 2 • 42

donghao-zhou/HOIVG-Bench

Viewer • Updated Apr 14 • 270 • 577 • 2