Jaehyun Kang

jaehyunkang's activity

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

upvoted a paper 7 months ago

Multi-Granular Spatio-Temporal Token Merging for Training-Free Acceleration of Video LLMs

Paper • 2507.07990 • Published Jul 10, 2025 • 46

upvoted a paper 9 months ago

UniSkill: Imitating Human Videos via Cross-Embodiment Skill Representations

Paper • 2505.08787 • Published May 13, 2025 • 14

upvoted a paper about 1 year ago

Omni-RGPT: Unifying Image and Video Region-level Understanding via Token Marks

Paper • 2501.08326 • Published Jan 14, 2025 • 33