1
Dynamic Jailbreaking Attack
打破静态优化桎梏，动态越狱攻击同时提升大模型攻击的有效性、效率与灵活性，安全研究者需警惕新范式。
arXiv:2510.02422v4 Announce Type: replace-cross Abstract: Existing gradient-based jailbreak attacks typically optimize a fixed-length adversarial suff…
2
Online LLM Selection via Constrained Bandits with Time-Varying Demand
挑战在线LLM选择中的时变需求？这篇论文提出约束赌博机框架，动态平衡性能与成本。
arXiv:2606.17489v1 Announce Type: cross Abstract: Large Language Models (LLMs) are increasingly deployed in edge-cloud inference systems to handle div…
3
Uni-DPO: A Unified Paradigm for Dynamic Preference Optimization of LLMs
DPO统一范式Uni-DPO，动态优化LLM偏好，解决数据质量差异问题。
arXiv:2506.10054v4 Announce Type: replace-cross Abstract: Direct Preference Optimization (DPO) has emerged as a cornerstone of reinforcement learning …