الباحثون

Jinyuan Jia

المنشورات 2

نسخة أولية وصول مفتوح

Complementary Supervised and Self-Supervised Representations for Out-of-Distribution Graph Learning

Qingying Hao, Zikang Chen, Chuxuan Hu وآخرون · 2026

Out-of-distribution (OOD) generalization remains challenging for graph neural networks (GNNs), as graph distributions can vary substantially across time and domains. Supervised and self-supervised graph representation learning are guided by distinct objectives and offer different perspectives on graph representations. …

نسخة أولية وصول مفتوح

Climbing the Hill: Prompt Injection Red-Teaming Against Frontier Models with Curriculum Reinforcement Learning

Chenlong Yin, Xiaolong Jin, Wei Zou وآخرون · 2026

Prompt injection is a leading security risk for LLMs and LLM-based applications such as agents. State-of-the-art red-teaming methods for prompt injection leverage reinforcement learning (RL) to train an attacker LLM to generate effective injected prompts. However, when targeting frontier LLMs such as GPT-6-Luna, a majo …

المؤلفون المشاركون

Qingying Hao Zikang Chen Chuxuan Hu Bo Li Gang Wang Carl Gunter Chenlong Yin Xiaolong Jin Wei Zou Yanting Wang