SujieHu

SujieHu's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

upvoted a paper 12 days ago

Blame Errant Words, Not the Canvas: Defect-Aware Spatial Credit Assignment for Visual Text Generation

Paper • 2610.20794 • Published 26 days ago • 7

authored 3 papers 13 days ago

Blame Errant Words, Not the Canvas: Defect-Aware Spatial Credit Assignment for Visual Text Generation

Paper • 2610.20794 • Published 26 days ago • 7

TOD3Cap: Towards 3D Dense Captioning in Outdoor Scenes

Paper • 2403.19589 • Published Mar 28, 2024

Taming Preference Mode Collapse via Directional Decoupling Alignment in Diffusion Reinforcement Learning

Paper • 2512.24146 • Published Dec 30, 2025 • 14

updated a dataset 13 days ago

SujieHu/PolyText-Bench

Viewer • Updated 13 days ago • 600 • 179

updated a collection 13 days ago

TextDART-SCANNER

Collection

Project Page: https://sujiehu.github.io/textdart-scanner • 4 items • Updated 13 days ago

published a dataset 13 days ago

SujieHu/PolyText-Bench

Viewer • Updated 13 days ago • 600 • 179

updated a dataset 13 days ago

SujieHu/TextDART-123K

Viewer • Updated 13 days ago • 123k • 392

updated a collection 13 days ago

TextDART-SCANNER

Collection

Project Page: https://sujiehu.github.io/textdart-scanner • 4 items • Updated 13 days ago

updated a model 13 days ago

SujieHu/TextDART-8B-Qwen3VL

Image-Text-to-Text • 9B • Updated 13 days ago • 45

published a dataset 13 days ago

SujieHu/TextDART-123K

Viewer • Updated 13 days ago • 123k • 392

updated a collection 13 days ago

TextDART-SCANNER

Collection

Project Page: https://sujiehu.github.io/textdart-scanner • 4 items • Updated 13 days ago

published a model 13 days ago

SujieHu/TextDART-8B-Qwen3VL

Image-Text-to-Text • 9B • Updated 13 days ago • 45

upvoted a paper about 2 months ago

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

Paper • 2609.20423 • Published Sep 17 • 18

upvoted a collection about 2 months ago

WeVisDoc

Collection

3 items • Updated 12 days ago • 15

upvoted a paper 5 months ago

Where, What, Why, and Importance: Structured Defect Grounding for Text-to-Image Feedback

Paper • 2606.06113 • Published Jun 4 • 15

liked a model 7 months ago

baidu/ERNIE-Image

Text-to-Image • 8B • Updated Apr 17 • 1.98k • • 689

upvoted 2 papers 9 months ago

Everything in Its Place: Benchmarking Spatial Intelligence of Text-to-Image Models

Paper • 2601.20354 • Published Jan 28 • 103

Harder Is Better: Boosting Mathematical Reasoning via Difficulty-Aware GRPO and Multi-Aspect Question Reformulation

Paper • 2601.20614 • Published Jan 28 • 110