Zhiding Yu

Zhiding's activity

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

authored a paper 3 days ago

Token-Efficient Long Video Understanding for Multimodal LLMs

Paper • 2503.04130 • Published 4 days ago • 66

upvoted a collection 19 days ago

Deepseek Papers

Collection

Deepseek papers collection • 18 items • Updated 20 days ago • 166

updated 2 models 27 days ago

Zhiding/eagle2-commercial_llama3-2_3b_data-v11-gl_16k

Updated 27 days ago • 7

Zhiding/eagle2-commercial_llama3-2_1b_data-v11-gl_16k

Updated 27 days ago • 8

published 2 models 27 days ago

Zhiding/eagle2-commercial_llama3-2_1b_data-v11-gl_16k

Updated 27 days ago • 8

Zhiding/eagle2-commercial_llama3-2_3b_data-v11-gl_16k

Updated 27 days ago • 7

updated 3 models 28 days ago

nvidia/QLIP-L-14-392

Updated 28 days ago • 298 • 9

nvidia/QLIP-B-16-256

Updated 28 days ago • 288 • 4

nvidia/QLIP-B-8-256

Updated 28 days ago • 136 • 5

published 3 models about 1 month ago

nvidia/QLIP-B-8-256

Updated 28 days ago • 136 • 5

nvidia/QLIP-B-16-256

Updated 28 days ago • 288 • 4

nvidia/QLIP-L-14-392

Updated 28 days ago • 298 • 9

upvoted a collection about 1 month ago

QLIP

Collection

QLIP is a family of image tokenizers with SOTA reconstruction quality and zero-shot image understanding. • 3 items • Updated Feb 6 • 7

updated a collection about 1 month ago

QLIP

Collection

QLIP is a family of image tokenizers with SOTA reconstruction quality and zero-shot image understanding. • 3 items • Updated Feb 6 • 7

upvoted a paper about 1 month ago

Eagle 2: Building Post-Training Data Strategies from Scratch for Frontier Vision-Language Models

Paper • 2501.14818 • Published Jan 20 • 4

updated 3 models about 1 month ago

nvidia/Eagle2-9B

Image-Text-to-Text • Updated Jan 28 • 1.21k • 45

nvidia/Eagle2-2B

Image-Text-to-Text • Updated Jan 28 • 390 • 13

nvidia/Eagle2-1B

Image-Text-to-Text • Updated Jan 28 • 979 • 18