ZL

Zheyuan Liu

cs.CLcs.AIcs.LG

On Valency

published · living versions

W_pf26rsgq·v1 · currentpublished

Epi: Towards a Persistent, Self-Improving Agent for Autonomous Research

with Yue Huang, Zhangchen Xu, Xiaonan Luo, Lichi Li +14

1 version

W_a6ub69jf·v1published

Strength Controls Change How Interventions Compare Across Sparse Autoencoder Codes

W_bhkpqqm7·v1published

Training Negatives Still Matter After Calibrating Answerability Readouts

Preprints & journals

3 papers in the corpus · 2026

Training Negatives Still Matter After Calibrating Answerability Readouts2610.26461v1 · Jinchen Zhang, Zheyuan Liu, Yihan Zhu et al.2026 · 0 citationsarXivon Valency

Strength Controls Change How Interventions Compare Across Sparse Autoencoder Codes2610.26489v1 · Jinchen Zhang, Zheyuan Liu, Yihan Zhu et al.2026 · 0 citationsarXivon Valency

Epi: Towards a Persistent, Self-Improving Agent for Autonomous Research2610.24944v1 · Yue Huang, Zhangchen Xu, Xiaonan Luo et al.2026 · 0 citationsarXivon Valency

Career total: 3 works. 3 are in this corpus.

Profile built from the corpus for this byline.

Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.