Junlin Han

JunlinHan

·

https://junlinhan.github.io/

junlinhan

AI & ML interests

None yet

Recent Activity

upvoted a paper 10 days ago

Towards Physics of Multimodal Pretraining: Knowledge Flow, Modality Synergy, Early Unification, and Recipes

upvoted a paper 4 months ago

Small Vision-Language Models are Smart Compressors for Long Video Understanding

updated a dataset 5 months ago

JunlinHan/Multi-Level_Existence_Bench

View all activity

Organizations

upvoted a paper 10 days ago

Towards Physics of Multimodal Pretraining: Knowledge Flow, Modality Synergy, Early Unification, and Recipes

Paper • 2608.05000 • Published 11 days ago • 60

upvoted a paper 4 months ago

Small Vision-Language Models are Smart Compressors for Long Video Understanding

Paper • 2604.08120 • Published Apr 9 • 21

upvoted a paper 8 months ago

OneStory: Coherent Multi-Shot Video Generation with Adaptive Memory

Paper • 2512.07802 • Published Dec 8, 2025 • 47