Sudong Wang PRO

xiao45791's activity

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

commented a paper about 21 hours ago

Beyond SFT-to-RL: Pre-alignment via Black-Box On-Policy Distillation for Multimodal RL

Paper • 2604.28123 • Published 8 days ago • 41 •

4

authored a paper 1 day ago

Beyond SFT-to-RL: Pre-alignment via Black-Box On-Policy Distillation for Multimodal RL

Paper • 2604.28123 • Published 8 days ago • 41

updated 3 datasets 2 days ago

prism-vlm/rl_dataset

Viewer • Updated 2 days ago • 20.3k • 48

prism-vlm/gemini_public_mmr1

Viewer • Updated 2 days ago • 1.27M • 408 • 2

prism-vlm/gemini_distill

Viewer • Updated 2 days ago • 108k • 210

upvoted a paper 2 days ago

Beyond SFT-to-RL: Pre-alignment via Black-Box On-Policy Distillation for Multimodal RL

Paper • 2604.28123 • Published 8 days ago • 41

submitted a paper to Daily Papers 3 days ago

Beyond SFT-to-RL: Pre-alignment via Black-Box On-Policy Distillation for Multimodal RL

Paper • 2604.28123 • Published 8 days ago • 41

upvoted a paper 7 days ago

Visual Generation in the New Era: An Evolution from Atomic Mapping to Agentic World Modeling

Paper • 2604.28185 • Published 9 days ago • 86

published 3 datasets 8 days ago

prism-vlm/gemini_distill

Viewer • Updated 2 days ago • 108k • 210

prism-vlm/gemini_public_mmr1

Viewer • Updated 2 days ago • 1.27M • 408 • 2

prism-vlm/rl_dataset

Viewer • Updated 2 days ago • 20.3k • 48

published 4 models 8 days ago

prism-vlm/Qwen3-VL-4B-Instruct-SFT

5B • Updated Feb 18 • 25

prism-vlm/Qwen3-VL-2B-4X-Moe-warmup-120k

5B • Updated Feb 28 • 24

prism-vlm/Qwen3-VL-4B-Instruct-SFT-PRISM

5B • Updated Mar 1 • 21

prism-vlm/Qwen3-VL-4B-Instruct-SFT-PRISM-GSPO

Image-Text-to-Text • 5B • Updated 2 days ago • 42

updated a model 12 days ago

prism-vlm/Qwen3-VL-8B-Instruct-SFT-PRISM-GRPO

Image-Text-to-Text • 9B • Updated 3 days ago • 42

published a model 12 days ago

prism-vlm/Qwen3-VL-8B-Instruct-SFT-PRISM-GRPO

Image-Text-to-Text • 9B • Updated 3 days ago • 42

updated a model 13 days ago

prism-vlm/Qwen3-VL-8B-Instruct-SFT-PRISM-DAPO

Image-Text-to-Text • 9B • Updated 2 days ago • 34

published a model 13 days ago

prism-vlm/Qwen3-VL-8B-Instruct-SFT-PRISM-DAPO

Image-Text-to-Text • 9B • Updated 2 days ago • 34

updated a model 16 days ago

prism-vlm/Qwen3-VL-8B-Instruct-SFT-PRISM-GSPO

Image-Text-to-Text • 9B • Updated 2 days ago • 35