Built with and by Teycir Ben Soltane•
How to Use•FAQ•GitHub•arXiv.org•
Share:
ArXivCSExplorer
☆☆Bookmarks🏆RSSHow to UseFAQ
Home/Authors/Fang Xie

Fang Xie

2 indexed papers

Recent (6 mo)
2
With code
0
Influential cites
0
Benchmarked
0

Publications per year

2
26

Top categories

ML×2Crypto×1Stats ML×1AI×1Vision×1

Frequent co-authors

Xiaobo Huang1×
Divyansh Jha1×
Yuanfang Xie1×
Varan Mehra1×
Brennen Yu1×

Research Timeline

2026
BRo-JEPA: Learning Modular Arithmetic in Latent Space

The paper introduces BRo-JEPA, a latent world model that successfully learns modular arithmetic (like addition modulo 10) by explicitly imposing the circular structure of the problem into the latent space, enabling strong zero-shot generalization.

Revisiting Privacy Amplification by Subsampling in Selective Release DPSGD

The paper proposes DPSR-CG, a novel differentially private selective release mechanism that rigorously maintains strict privacy guarantees while significantly improving model utility compared to existing methods.

Highlighted terms show continued research focus across papers

Papers

cs.LGcs.CRstat.MLRecentJun 3, 2026

Revisiting Privacy Amplification by Subsampling in Selective Release DPSGD

Xiaobo Huang, Fang Xie

The paper proposes DPSR-CG, a novel differentially private selective release mechanism that rigorously maintains strict privacy guarantees while significantly improving model utility compared to exist…

View →
cs.LGcs.AIcs.CVRecentMay 31, 2026

BRo-JEPA: Learning Modular Arithmetic in Latent Space

Divyansh Jha, Yuanfang Xie, Varan Mehra, Brennen Yu

The paper introduces BRo-JEPA, a latent world model that successfully learns modular arithmetic (like addition modulo 10) by explicitly imposing the circular structure of the problem into the latent s…

View →