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

Zhaoxin Yu

1 indexed paper

Recent (6 mo)
1
With code
0
Influential cites
0
Benchmarked
0

Publications per year

1
26

Top categories

ML×1NLP×1

Frequent co-authors

Qi Shen1×
Hengli Li1×
Zhaowei Zhang1×
Song-Chun Zhu1×
Chi Zhang1×
Zilong Zheng1×

Research Timeline

2026
GradCuit: Credit-Assigned Gradient Flow Enables Robust and Interpretable Test-Time Latent Reasoning

The paper introduces GradCuit, a method for optimizing internal reasoning in large language models at test time by inserting optimizable latent states between hidden representations and enabling direct gradient assignment.

Highlighted terms show continued research focus across papers

Papers

cs.LGcs.CLEmpiricalRecentAug 3, 2026

GradCuit: Credit-Assigned Gradient Flow Enables Robust and Interpretable Test-Time Latent Reasoning

Zhaoxin Yu, Qi Shen, Hengli Li, Zhaowei Zhang +3 more

The paper introduces GradCuit, a method for optimizing internal reasoning in large language models at test time by inserting optimizable latent states between hidden representations and enabling direc…

View →