zhijie deng's picture

2 20

zhijie deng PRO

zhijie3

·

https://thudzj.github.io/

thudzj

AI & ML interests

None yet

Recent Activity

upvoted a paper 9 days ago

Efficient Long-context Language Model Training by Core Attention Disaggregation

upvoted a paper 3 months ago

NextStep-1: Toward Autoregressive Image Generation with Continuous Tokens at Scale

updated a Space 3 months ago

zhijie3/D2F-LLaDA-Instruct-8B

View all activity

Organizations

Papers 20

arxiv:2504.00883

arxiv:2502.06155

arxiv:2502.05415

arxiv:2412.00127

spaces 1

Running on Zero

D2F LLaDA Instruct 8B

Diffusion LLMs Can Do Faster-Than-AR Inference via Discret

models 0

None public yet

datasets 0

None public yet