XZ
Xuandong Zhao
cs.LGcs.CLcs.CRcs.AIcs.CYcs.SI
On Valency
published · living versionsW_bqucpr6z·v1 · currentpublished
Can Test-Time Memory Evolution Outperform Test-Time Training for Scientific Discovery?
with Yepeng Liu, Shengmai Chen, Chengzhi Liu, Dawn Song +2
1 version
Preprints & journals
9 papers in the corpus · 2024–2026VIMPO: Value-Implicit Policy Optimization for LLMs2606.20008v1 · Zhewei Kang, Aosong Feng, Sergey Levine et al.2026 · 0 citationsarXiv
When Do Intrinsic Rewards Work for Code Reasoning? A Comprehensive Study2606.20881v1 · Xiaolong Jin, Xuandong Zhao, Wenbo Guo et al.2026 · 0 citationsarXiv
Auditing Agent Harness Safety2605.14271v2 · Chengzhi Liu, Yichen Guo, Yepeng Liu et al.2026 · 0 citationsarXiv
Self-Sovereign Agent2604.08551v1 · Wenjie Qu, Xuandong Zhao, Jiaheng Zhang et al.2026 · 0 citationsarXiv
Making Bias Non-Predictive: Training Robust LLM Reasoning via Reinforcement Learning2602.01528v2 · Qian Wang, Xuandong Zhao, Zirui Zhang et al.2026 · 0 citationsarXiv
Invisible Tokens, Visible Bills: The Urgent Need to Audit Hidden Operations in Opaque LLM Services2505.18471v1 · Guoheng Sun, Ziyao Wang, Xuandong Zhao et al.2025 · 0 citationsarXiv
Are You Getting What You Pay For? Auditing Model Substitution in LLM APIs2504.04715v2 · Will Cai, Tianneng Shi, Xuandong Zhao et al.2025 · 0 citationsarXiv
Bileve: Securing Text Provenance in Large Language Models Against Spoofing with Bi-level Signature2406.01946v3 · Tong Zhou, Xuandong Zhao, Xiaolin Xu et al.2024 · 3 citationsarXiv
Monitoring AI-Modified Content at Scale: A Case Study on the Impact of ChatGPT on AI Conference Peer Reviews2403.07183v4 · Weixin Liang, Zachary Izzo, Yaohui Zhang et al.2024 · 73 citationsarXiv
Career total: 9 works. 9 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.