{"id":36525,"date":"2026-06-08T13:16:27","date_gmt":"2026-06-08T13:16:27","guid":{"rendered":"https:\/\/lamarr-institute.org\/publication\/in-context-learning-of-temporal-point-processes-with-foundation-inference-models\/"},"modified":"2026-06-08T13:16:27","modified_gmt":"2026-06-08T13:16:27","slug":"in-context-learning-of-temporal-point-processes-with-foundation-inference-models","status":"publish","type":"publication","link":"https:\/\/lamarr-institute.org\/de\/publication\/in-context-learning-of-temporal-point-processes-with-foundation-inference-models\/","title":{"rendered":"In-Context Learning of Temporal Point Processes with Foundation Inference Models"},"content":{"rendered":"<p>Modeling multi-type event sequences with marked temporal point processes (MTPPs) provides a principled framework for uncovering governing dynamical rules and predicting future events. Current neural approaches to MTPP inference typically require training separate, specialized models for each target system. We pursue a fundamentally different strategy: leveraging amortized inference and in-context learning, we pretrain a deep neural network to infer, in-context, the conditional intensity functions of event histories from a context consisting of sets of event sequences. Pretraining is performed on a large synthetic dataset of MTPPs sampled from a broad distribution over point processes. Once pretrained, our Foundation Inference Model for Point Processes (FIM-PP) can estimate MTPPs from real-world data without additional training, or be rapidly finetuned to specific target systems. Across common benchmark datasets, FIM-PP matches the performance of specialized models in zero-shot mode. After only a few finetuning iterations, FIM-PP further improves its predictions and outperforms competing methods on the majority of evaluated tasks.<\/p>\n","protected":false},"excerpt":{"rendered":"<p>Modeling multi-type event sequences with marked temporal point processes (MTPPs) provides a principled framework for uncovering governing dynamical rules and predicting future events. Current neural approaches to MTPP inference typically require training separate, specialized models for each target system. We pursue a fundamentally different strategy: leveraging amortized inference and in-context learning, we pretrain a deep neural network to infer, in-context, the conditional intensity functions of event histories from a context [&hellip;]<\/p>\n","protected":false},"author":12,"featured_media":0,"template":"","meta":{"_acf_changed":false,"footnotes":""},"publication-type":[32],"class_list":["post-36525","publication","type-publication","status-publish","hentry","publication-type-inproceedings"],"acf":[],"publishpress_future_workflow_manual_trigger":{"enabledWorkflows":[]},"_links":{"self":[{"href":"https:\/\/lamarr-institute.org\/de\/wp-json\/wp\/v2\/publication\/36525","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/lamarr-institute.org\/de\/wp-json\/wp\/v2\/publication"}],"about":[{"href":"https:\/\/lamarr-institute.org\/de\/wp-json\/wp\/v2\/types\/publication"}],"author":[{"embeddable":true,"href":"https:\/\/lamarr-institute.org\/de\/wp-json\/wp\/v2\/users\/12"}],"version-history":[{"count":0,"href":"https:\/\/lamarr-institute.org\/de\/wp-json\/wp\/v2\/publication\/36525\/revisions"}],"wp:attachment":[{"href":"https:\/\/lamarr-institute.org\/de\/wp-json\/wp\/v2\/media?parent=36525"}],"wp:term":[{"taxonomy":"publication-type","embeddable":true,"href":"https:\/\/lamarr-institute.org\/de\/wp-json\/wp\/v2\/publication-type?post=36525"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}