ZD
Zhihao Dou
cs.AIcs.CRcs.LGcs.CLcs.CVcs.DCcs.IRcs.RO
On Valency
published · living versionsW_y8kw6zsh·v1 · currentpublished
Shuffled OPSD: When Semantic Consistency Hurts On-Policy Self-Distillation?
with Qingyuan Zheng
1 version
Preprints & journals
18 papers in the corpus · 2024–2026GAVEL: Graph World Models for Verified and Efficient Long-Horizon LLM Task Planning2609.19315v1 · Ruiyang Wang, Hao-Lun Hsu, Swarajh Mehta et al.2026 · 0 citationsarXiv
AMRM-Pure: Semantic-Preserving Adversarial Purification2607.04474v1 · Zhihao Dou, Zhiqiang Gao, Dongfei Cui et al.2026 · 0 citationsarXiv
ReShift: Aha-Moment-Driven Reasoning-Level Backdoor Attacks on Vision-Language Models2607.00361v1 · Zhihao Dou, Qinjian Zhao, Zhiqiang Gao et al.2026 · 0 citationsarXiv
ELDiff: When Evidential Learning Meets Text-to-Image Diffusion2606.20924v1 · Qingtao Pan, Kai Ye, Zhihao Dou et al.2026 · 0 citationsarXiv
STRIDE: Strategic Trajectory Reasoning via Discriminative Estimation for Verifiable Reinforcement Learning2606.15866v1 · Qinjian Zhao, Zhihao Dou, Dinggen Zhang et al.2026 · 0 citationsarXiv
CoRe-Code: Collaborative Reinforcement Learning for Code Generation2605.24812v1 · Zhihao Dou, Qinjian Zhao, Zhongwei Wan et al.2026 · 0 citationsarXiv
SkillEvolBench: Benchmarking the Evolution from Episodic Experience to Procedural Skills2605.24117v1 · Yingtie Lei, Zhongwei Wan, Jiankun Zhang et al.2026 · 0 citationsarXiv
AgentCE-Bench: Agent Configurable Evaluation with Scalable Horizons and Controllable Difficulty under Lightweight Environments2604.06111v2 · Wang Yang, Chaoda Song, Xinpeng Li et al.2026 · 0 citationsarXiv
ProtoGuard-SL: Prototype Consistency Based Backdoor Defense for Vertical Split Learning2604.03595v1 · Yuhan Shui, Ruobin Jin, Zhihao Dou et al.2026 · 0 citationsarXiv
Frequency-Modulated Visual Restoration for Matryoshka Large Multimodal Models2603.11220v1 · Qingtao Pan, Zhihao Dou, Shuo Li2026 · 0 citationsarXiv
DSDR: Dual-Scale Diversity Regularization for Exploration in LLM Reasoning2602.19895v1 · Zhongwei Wan, Yun Shen, Zhihao Dou et al.2026 · 0 citationsarXiv
SecureSplit: Mitigating Backdoor Attacks in Split Learning2601.14054v2 · Zhihao Dou, Dongfei Cui, Weida Wang et al.2026 · 1 citationarXiv
MMDeepResearch-Bench: A Benchmark for Multimodal Deep Research Agents2601.12346v1 · Peizhou Huang, Zixuan Zhong, Zhongwei Wan et al.2026 · 0 citationsarXiv
SafeBehavior: Simulating Human-Like Multistage Reasoning to Mitigate Jailbreak Attacks in Large Language Models2509.26345v1 · Qinjian Zhao, Jiaqi Wang, Zhiqiang Gao et al.2025 · 1 citationarXiv
Toward Malicious Clients Detection in Federated Learning2505.09110v2 · Zhihao Dou, Jiaqi Wang, Wei Sun et al.2025 · 4 citationsarXiv
DSADF: Thinking Fast and Slow for Decision Making2505.08189v2 · Zhihao Dou, Dongfei Cui, Jun Yan et al.2025 · 2 citationsarXiv
Adversarial Attacks to Multi-Modal Models2409.06793v2 · Zhihao Dou, Xin Hu, Haibo Yang et al.2024 · 8 citationsarXiv
Defending against Jailbreak through Early Exit Generation of Large Language Models2408.11308v2 · Chongwen Zhao, Zhihao Dou, Kaizhu Huang2024 · 1 citationarXiv
Career total: 19 works. 18 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.