shijie xia

seven-cat

·

https://shijie-xia.github.io/

AI & ML interests

LLMs

Recent Activity

upvoted a paper 1 day ago

VidaForge: Open Research Infrastructure for Video Pretraining Data Recipes

upvoted a paper 6 months ago

Speed by Simplicity: A Single-Stream Architecture for Fast Audio-Video Generative Foundation Model

upvoted a paper 7 months ago

Data Darwinism Part I: Unlocking the Value of Scientific Data for Pre-training

View all activity

Organizations

Papers 10

arxiv:2510.11661

arxiv:2509.17567

arxiv:2504.13828

arxiv:2502.03387

models 0

None public yet

datasets 0

None public yet