Xiaoran Fan

cnxup's activity

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

upvoted a paper 28 days ago

How Far Are We from Removing the Visual Encoder? Scaling Laws for Encoder-Free Multimodal Pretraining

Paper • 2609.35457 • Published Sep 28 • 60

liked a dataset 7 months ago

sysuyy/ImgEdit

Updated Jun 16, 2025 • 33.7k • 46

liked 4 models 8 months ago

cnxup/LLaVA-NeXT-8B-MLA-stage2-rope32-d_kv_128

9B • Updated Mar 18 • 5 • 1

cnxup/LLaVA-NeXT-8B-MLA-stage2-rope32-d_kv_32

8B • Updated Mar 18 • 6 • 1

cnxup/LLaVA-NeXT-8B-MLA-stage1-rope32

8B • Updated Mar 18 • 5 • 1

cnxup/LLaVA-NeXT-8B-MLA-stage2-rope32-d_kv_64

8B • Updated Mar 18 • 5 • 1

published 4 models 8 months ago

cnxup/LLaVA-NeXT-8B-MLA-stage2-rope32-d_kv_32

8B • Updated Mar 18 • 6 • 1

cnxup/LLaVA-NeXT-8B-MLA-stage1-rope32

8B • Updated Mar 18 • 5 • 1

cnxup/LLaVA-NeXT-8B-MLA-stage2-rope32-d_kv_64

8B • Updated Mar 18 • 5 • 1

cnxup/LLaVA-NeXT-8B-MLA-stage2-rope32-d_kv_128

9B • Updated Mar 18 • 5 • 1

updated 4 models 8 months ago

cnxup/LLaVA-NeXT-8B-MLA-stage1-rope32

8B • Updated Mar 18 • 5 • 1

cnxup/LLaVA-NeXT-8B-MLA-stage2-rope32-d_kv_32

8B • Updated Mar 18 • 6 • 1

cnxup/LLaVA-NeXT-8B-MLA-stage2-rope32-d_kv_64

8B • Updated Mar 18 • 5 • 1

cnxup/LLaVA-NeXT-8B-MLA-stage2-rope32-d_kv_128

9B • Updated Mar 18 • 5 • 1

upvoted a paper 8 months ago

AgentVista: Evaluating Multimodal Agents in Ultra-Challenging Realistic Visual Scenarios

Paper • 2602.23166 • Published Feb 26 • 47

updated a dataset 9 months ago

cnxup/LLaVA-NeXT-Data

Preview • Updated Feb 12 • 24

published a dataset 9 months ago

cnxup/LLaVA-NeXT-Data

Preview • Updated Feb 12 • 24

updated 3 models 9 months ago

cnxup/SVD-Init

Updated Jan 31 • 1

cnxup/Qwen2.5-VL-7B-MLA-stage2-rope32-d_kv_128

8B • Updated Jan 27 • 6 • 1

cnxup/Qwen2.5-VL-7B-MLA-stage2-rope32-d_kv_64

8B • Updated Jan 27 • 5 • 1