WeiQuan Huang

Quansir's activity

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

updated 6 models about 21 hours ago

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

Image-Text-to-Text • 5B • Updated about 21 hours ago • 30

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

Image-Text-to-Text • 5B • Updated about 21 hours ago • 11

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

Image-Text-to-Text • 5B • Updated about 21 hours ago • 33

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

Image-Text-to-Text • 9B • Updated about 21 hours ago • 11

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

Image-Text-to-Text • 9B • Updated about 21 hours ago • 11

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

Image-Text-to-Text • 9B • Updated about 21 hours ago • 19

New activity in prism-vlm/Qwen3-VL-8B-Instruct-SFT-PRISM-GRPO about 21 hours ago

Create README.md

#1 opened about 21 hours ago by

Quansir

upvoted a paper about 22 hours ago

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

Paper • 2604.28123 • Published 6 days ago • 35

updated a model 2 months ago

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

5B • Updated Mar 1 • 21

updated a dataset 3 months ago

prism-vlm/gemini_distill

Viewer • Updated about 16 hours ago • 108k • 5

updated a model 3 months ago

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

5B • Updated Feb 18 • 24

upvoted a paper 3 months ago

Modality Gap-Driven Subspace Alignment Training Paradigm For Multimodal Large Language Models

Paper • 2602.07026 • Published Feb 2 • 140

upvoted a paper 4 months ago

Watching, Reasoning, and Searching: A Video Deep Research Benchmark on Open Web for Agentic Video Reasoning

Paper • 2601.06943 • Published Jan 11 • 214

upvoted a paper 5 months ago

LongVT: Incentivizing "Thinking with Long Videos" via Native Tool Calling

Paper • 2511.20785 • Published Nov 25, 2025 • 188