Damiano Marsili

dmarsili's activity

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

upvoted a collection 13 days ago

TWIN

Collection

Datasets and models from the paper "Same or Not? Enhancing Visual Perception in Vision-Language Models" • 4 items • Updated about 1 hour ago • 1

upvoted a collection 18 days ago

VALOR

Collection

Models from the paper "No Labels, No Problem: Training Visual Reasoners with Multimodal Verifiers" • 2 items • Updated 13 days ago • 1

upvoted a paper 7 months ago

Aligning Text, Images, and 3D Structure Token-by-Token

Paper • 2506.08002 • Published Jun 9 • 21