SixAILab

community

https://sihanxu.me/

AI & ML interests

None defined yet.

Recent Activity

Shoubin submitted a paper about 4 hours ago

Ego2Web: A Web Agent Benchmark Grounded in Egocentric Videos

Shoubin submitted a paper 8 days ago

VisionCoach: Reinforcing Grounded Video Reasoning via Visual-Perception Prompting

sihanxu updated a model 10 days ago

SixAILab/dit-2-b-400k

View all activity

Papers

Next-Embedding Prediction Makes Strong Vision Learners

View all Papers

SixAILab 's models 5

SixAILab/dit-2-b-400k

Updated 10 days ago • 32

SixAILab/nepa-large-patch14-224-sft

Image Classification • 0.3B • Updated Dec 21, 2025 • 55 • 1

SixAILab/nepa-base-patch14-224-sft

Image Classification • 86.3M • Updated Dec 21, 2025 • 56 • 4

SixAILab/nepa-large-patch14-224

Image Feature Extraction • 0.3B • Updated Dec 21, 2025 • 7 • 3

SixAILab/nepa-base-patch14-224

Image Feature Extraction • 85.5M • Updated Dec 21, 2025 • 72 • 1