探讨非交换面板数据的在线共形预测新方法，突破传统假设，提升实时预测可靠性
arXiv:2605.17705v1 Announce Type: cross Abstract: Panel data, in which multiple units are repeatedly observed over time, arise throughout science and …
探索上下文排队老虎机中的队列长度后悔界限，为在线队列调度提供理论保证。
arXiv:2601.19300v2 Announce Type: replace Abstract: We introduce contextual queueing bandits, a new context-aware framework for scheduling while simul…
探讨Chain-of-Thought验证器的在线可学习性，深入分析正确性与完备性间的权衡关系。
arXiv:2603.03538v3 Announce Type: replace Abstract: Large Language Models (LLMs) with chain-of-thought generation have demonstrated great potential fo…
首次系统研究结构化Stackelberg博弈，利用上下文信息预测对手类型，助力领导者在线学习最优策略。
arXiv:2504.09006v4 Announce Type: replace-cross Abstract: We initiate the study of structured Stackelberg games, a novel form of strategic interaction…