ZD

Zheyuan Deng

cs.AIcs.LGcs.CLcs.CYcs.HC

On Valency

published · living versions

W_sp6hm735·v1 · currentpublished

PersonaChatBench: Evaluating Chat Assistants with Diverse Simulated Users

with Taoran Li, Jingwen Zhang, Yuante Li, Dachuan Zhao +26

1 version

Preprints & journals

6 papers in the corpus · 2026

PersonaCUABench: Benchmarking Computer-Use Agents Serving Diverse Personas2610.22990v1 · Haoming Li, Defu Cao, Xu Hu et al.2026 · 0 citationsarXiv

OmniStepBench: Deployment-Aware Agent Evaluation across Modalities and Task Complexity2609.06059v2 · Yu Liu, Zhilin Liu, Zhiwei Yang et al.2026 · 0 citationsarXiv

ClueWeaver: Reward-Guided Dual-Agent Evidence Reasoning for Compact LLMs on Literary Long Narratives2608.25531v2 · Jihao Zhu, Zhiwei Yang, Wenxiao Zhang et al.2026 · 0 citationsarXiv

CONTRAMEM: Learning Self-Evolving Procedural Memory from Contrasting Multi-Model Trajectories2608.22533v2 · Zheyuan Deng, Binghang Lu, Hanqi Feng et al.2026 · 0 citationsarXiv

Muon-OGD: Muon-based Spectral Orthogonal Gradient Projection for LLM Continual Learning2605.08949v2 · Binghang Lu, Zheyuan Deng, Runyu Zhang et al.2026 · 0 citationsarXiv

Chain of Risk: Safety Failures in Large Reasoning Models and Mitigation via Adaptive Multi-Principle Steering2605.05678v1 · Xiaomin Li, Jianheng Hou, Zheyuan Deng et al.2026 · 0 citationsarXiv

Career total: 6 works. 6 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.