Ismini Lourentzou

isminoula's activity

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

upvoted a paper 7 days ago

One Editor, Many Edits: A Unified Training-Free Framework for Diverse Video Editing

Paper • 2609.04190 • Published 12 days ago • 8

upvoted a paper 6 months ago

VTAM: Video-Tactile-Action Models for Complex Physical Interaction Beyond VLAs

Paper • 2603.23481 • Published Mar 24 • 7

upvoted a paper about 1 year ago

Fine-Grained Preference Optimization Improves Spatial Reasoning in VLMs

Paper • 2506.21656 • Published Jun 26, 2025 • 16