Parsa Madinei

pmadinei's activity

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

updated a Space about 3 hours ago

Running

Agents

Caption Preference Study

🖼

An image caption preference study (v2).

liked a dataset 13 days ago

starsky77/counterfactual-semantic-saliency

Viewer • Updated 5 days ago • 1.61k • 509 • 1

updated a dataset 4 months ago

pmadinei/caption-preference-results

Updated Jun 25 • 6 • 2

updated 8 models 5 months ago

pmadinei/Interlace-Qwen3-VL-4B-25pc

Image-Text-to-Text • 521k • Updated Jun 5 • 10

pmadinei/Interlace-Qwen3-VL-4B-20pc

Image-Text-to-Text • 532k • Updated Jun 5 • 11

pmadinei/Interlace-Qwen3-VL-4B-15pc

Image-Text-to-Text • 543k • Updated Jun 5 • 7

pmadinei/Interlace-Qwen3-VL-4B-10pc

Image-Text-to-Text • 554k • Updated Jun 5 • 8 • 1

pmadinei/Interlace-Qwen3-VL-8B-25pc

Image-Text-to-Text • 694k • Updated Jun 5 • 5

pmadinei/Interlace-Qwen3-VL-8B-20pc

Image-Text-to-Text • 711k • Updated Jun 5 • 10

pmadinei/Interlace-Qwen3-VL-8B-15pc

Image-Text-to-Text • 728k • Updated Jun 5 • 10

pmadinei/Interlace-Qwen3-VL-8B-10pc

Image-Text-to-Text • 745k • Updated Jun 5 • 6

published a Space 6 months ago

Running

Agents

Caption Preference Study

🖼

An image caption preference study (v2).

published a dataset 6 months ago

pmadinei/caption-preference-results

Updated Jun 25 • 6 • 2

updated a collection 7 months ago

Interlace

Collection

INTERLACE: Interleaved Layer Pruning in VLMs (CVPR 2025). Pruned Qwen3-VL models retaining up to 94% performance. • 8 items • Updated Apr 14