首个统一基准框架，专攻时空事件建模评测，填补领域空白，值得关注。
arXiv:2607.01022v1 Announce Type: new Abstract: Spatiotemporal point processes (STPPs) model event data in continuous time and space, with application…
智能体时间机器为未来事件预测搭起基础设施，破解实时评测慢反馈难题，兼顾效率与保真。
arXiv:2606.21013v1 Announce Type: new Abstract: Forecasting future events is a critical challenge for large language model (LLM) agents, spanning doma…
用强化学习优化大模型事件预测，GRPO策略带来新突破
arXiv:2606.15917v1 Announce Type: new Abstract: We use Group Relative Policy Optimization (GRPO), a recently devised sample and memory efficient reinf…
先想象再预测：论文提出交错潜在视觉推理新方法，提升视频事件预测准确性与可解释性。
arXiv:2606.05769v1 Announce Type: new Abstract: Video event prediction (VEP) requires models to infer unobserved future states from partial video evid…