Jinsong Li

Jinsong-Li's activity

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

authored 4 papers 3 months ago

Light-A-Video: Training-free Video Relighting via Progressive Light Fusion

Paper • 2502.08590 • Published Feb 12 • 43

Towards Storage-Efficient Visual Document Retrieval: An Empirical Study on Reducing Patch-Level Embeddings

Paper • 2506.04997 • Published Jun 5

ScaleCap: Inference-Time Scalable Image Captioning via Dual-Modality Debiasing

Paper • 2506.19848 • Published Jun 24 • 26

Beyond Fixed: Variable-Length Denoising for Diffusion Large Language Models

Paper • 2508.00819 • Published Aug 1 • 62

authored 2 papers over 1 year ago

ShareGPT4Video: Improving Video Understanding and Generation with Better Captions

Paper • 2406.04325 • Published Jun 6, 2024 • 75

Are We on the Right Way for Evaluating Large Vision-Language Models?

Paper • 2403.20330 • Published Mar 29, 2024 • 6

authored a paper almost 2 years ago

ShareGPT4V: Improving Large Multi-Modal Models with Better Captions

Paper • 2311.12793 • Published Nov 21, 2023 • 18