--- title: "Hao Wang — papers, page 2 · Shanghai University" description: "Hao Wang, Shanghai University: 27 papers on Elamur Research (2015–2026), h-index 1 — affiliations, topics, co-authors and who cites them…" canonical: "https://research.elamur.ai/free/en/authors/hao-wang/page/2/" --- [Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/authors/hao-wang/page/2/) [home](https://md.research.elamur.ai/free/en/) / [authors](https://md.research.elamur.ai/free/en/authors/) / [Hao Wang](https://md.research.elamur.ai/free/en/authors/hao-wang/) / page 2 # Hao Wang · page 2 27 papers in our library · 2015–2026 · page 2 of 2 [The profile, affiliations and co-authors →](https://md.research.elamur.ai/free/en/authors/hao-wang/) ## Papers The most cited first (OpenAlex and our library). [← prev](https://md.research.elamur.ai/free/en/authors/hao-wang/) [1](https://md.research.elamur.ai/free/en/authors/hao-wang/) **2** 26. **[SafetyMem: Adaptive Jailbreak Defense via Dual-Component Safety Memory](https://md.research.elamur.ai/free/en/papers/wang-2026-safetymem-adaptive-jailbreak-defense-dual/)** *(2026)* LLM jailbreak defenses tend to fall into two camps. Methods that change model weights, such as fine-tuning or trained detectors, are costly and slow to adapt. Inference-time filters are flexible, but they start from scratch on every prompt. SafetyMem is a training-free framework that lets a model accumulate defense… 27. **[SOLAR-RL: Semi-Online Long-horizon Assignment Reinforcement Learning](https://md.research.elamur.ai/free/en/papers/wang-2026-solar-rl-semi-online-long/)** *(2026)* The paper targets long-horizon navigation for GUI agents built on MLLMs. Offline RL on step-level data ignores trajectory-wide outcomes, while online RL is costly and unstable on workflows of 30+ steps. Both suffer from the credit assignment problem. SOLAR-RL takes a semi-online route: it simulates online feedback… [← prev](https://md.research.elamur.ai/free/en/authors/hao-wang/) [1](https://md.research.elamur.ai/free/en/authors/hao-wang/) **2**