Next Token Is Enough: Realistic Image Quality and Aesthetic Scoring with Multimodal Large Language Model
AI & ML interests
AI ML AIGC
Recent Activity
View all activity
Papers

ImagerySearch: Adaptive Test-Time Search for Video Generation Beyond Semantic Dependency Constraints

Advancing End-to-End Pixel Space Generative Modeling via Self-supervised Pre-training
models
8

GD-ML/Omni-Effects
Updated
•
6

GD-ML/FLUX-Text
Image-to-Image
•
Updated
•
30

GD-ML/UniVG-R1-stage1
Image-to-Text
•
8B
•
Updated
•
2

GD-ML/UniVG-R1
8B
•
Updated
•
342
•
6

GD-ML/Open-RS1
2B
•
Updated
•
14

GD-ML/Qwen2.5-Math-7B-GPG
8B
•
Updated
•
13

GD-ML/USP-Image_Generation
Updated
•
1

GD-ML/VMBench
Updated
•
1