spark

spark-tom's activity

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

upvoted a paper 14 days ago

PixelRefer: A Unified Framework for Spatio-Temporal Object Referring with Arbitrary Granularity

Paper • 2510.23603 • Published 15 days ago • 21

upvoted a paper about 1 month ago

MM-HELIX: Boosting Multimodal Long-Chain Reflective Reasoning with Holistic Platform and Adaptive Hybrid Policy Optimization

Paper • 2510.08540 • Published Oct 9 • 108

upvoted 2 papers 5 months ago

Geometry-Editable and Appearance-Preserving Object Compositon

Paper • 2505.20914 • Published May 27 • 6

EOC-Bench: Can MLLMs Identify, Recall, and Forecast Objects in an Egocentric World?

Paper • 2506.05287 • Published Jun 5 • 15

upvoted a paper 10 months ago

VideoRefer Suite: Advancing Spatial-Temporal Object Understanding with Video LLM

Paper • 2501.00599 • Published Dec 31, 2024 • 47