Huaisong Zhang

P1n3's activity

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

upvoted a paper about 19 hours ago

Learning from the Self-future: On-policy Self-distillation for dLLMs

Paper • 2606.18195 • Published 2 days ago • 27

upvoted a paper 6 days ago

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

Paper • 2606.06113 • Published 14 days ago • 15

submitted a paper to Daily Papers 6 days ago

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

Paper • 2606.06113 • Published 14 days ago • 15

authored a paper 6 days ago

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

Paper • 2606.06113 • Published 14 days ago • 15

updated a collection 7 days ago

SDG

Collection

Resources for Where, What, Why, and Importance: Structured Defect Grounding for Text-to-Image Feedback. • 4 items • Updated 7 days ago

updated 3 models 7 days ago

P1n3/boxflow-grpo-flux-lora

Text-to-Image • Updated 7 days ago • 17 •

P1n3/sdg-detector-grpo

Image-Text-to-Text • 4B • Updated 7 days ago • 17

P1n3/sdg-detector-sft

Image-Text-to-Text • 4B • Updated 7 days ago • 28

updated a dataset 7 days ago

P1n3/SDG-30K

Viewer • Updated 7 days ago • 30.2k • 7.58k

updated a collection 7 days ago

SDG

Collection

Resources for Where, What, Why, and Importance: Structured Defect Grounding for Text-to-Image Feedback. • 4 items • Updated 7 days ago

published a model 7 days ago

P1n3/boxflow-grpo-flux-lora

Text-to-Image • Updated 7 days ago • 17 •

published a dataset 7 days ago

P1n3/SDG-30K

Viewer • Updated 7 days ago • 30.2k • 7.58k

published 2 models 7 days ago

P1n3/sdg-detector-grpo

Image-Text-to-Text • 4B • Updated 7 days ago • 17

P1n3/sdg-detector-sft

Image-Text-to-Text • 4B • Updated 7 days ago • 28

upvoted a paper 13 days ago

Watch Before You Answer: Learning from Visually Grounded Post-Training

Paper • 2604.05117 • Published Apr 6 • 36

upvoted a paper 3 months ago

FCL-COD: Weakly Supervised Camouflaged Object Detection with Frequency-aware and Contrastive Learning

Paper • 2603.22969 • Published Mar 24 • 10