Modi Jin

ghost233lism's activity

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

upvoted 2 papers about 2 months ago

Towards Universal Video MLLMs with Attribute-Structured and Quality-Verified Instructions

Paper • 2602.13013 • Published Feb 13 • 54

GeoAgent: Learning to Geolocate Everywhere with Reinforced Geographic Characteristics

Paper • 2602.12617 • Published Feb 13 • 20

upvoted 2 papers 10 months ago

Depth Anything at Any Condition

Paper • 2507.01634 • Published Jul 2, 2025 • 49

LLaVA-Scissor: Token Compression with Semantic Connected Components for Video LLMs

Paper • 2506.21862 • Published Jun 27, 2025 • 36