黑盒视觉语言模型无需微调，测试时通过提示提升性能，新方法突破传统限制
arXiv:2605.16410v1 Announce Type: new Abstract: Test-time scaling (TTS) methods have proven highly effective for LLMs, yet their application to vision…
面向大语言模型昂贵任务的黑盒优化基准BoLT，降低研究门槛，推动领域民主化。
arXiv:2605.17000v1 Announce Type: new Abstract: Optimization of LLM training and inference configurations, such as hyperparameters, data mixtures, and…
用大语言模型实现语义感知的在线OS调优，解决黑盒优化难题。
arXiv:2605.15026v1 Announce Type: cross Abstract: Online OS tuning can improve long-running services, but existing controllers are poorly matched to l…
用大语言模型突破传统黑盒优化瓶颈，语义引导高效探索昂贵实验空间。
arXiv:2510.25404v3 Announce Type: replace-cross Abstract: Optimizing an experimental system can be extremely challenging when each experiment is expen…