# On Foundation Models for Temporal Point Processes to Accelerate Scientific Discovery

arXiv: https://arxiv.org/abs/2510.12640 · HTML: https://mlsanity.com/paper/2510.12640/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 15 of its 30 references that are in the map.
- First posted on arXiv 14 Oct 2025.

## Builds on (most cited first, 15 of 15)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [TabPFN: A Transformer That Solves Small Tabular Classification Problems in a Second](https://mlsanity.com/paper/2207.01848/) (2022)
- [Transformers Can Do Bayesian Inference](https://mlsanity.com/paper/2112.10510/) (2021)
- [Attentive Neural Processes](https://mlsanity.com/paper/1901.05761/) (2019)
- [Neural Temporal Point Processes For Modelling Electronic Health Records](https://mlsanity.com/paper/2007.13794/) (2020)
- [Position: The Future of Bayesian Prediction Is Prior-Fitted](https://mlsanity.com/paper/2505.23947/) (2025)
- [Zero-shot Imputation with Foundation Inference Models for Dynamical Systems](https://mlsanity.com/paper/2402.07594/) (2024)
- [Foundation Inference Models for Markov Jump Processes](https://mlsanity.com/paper/2406.06419/) (2024)
- [Neural Markov Jump Processes](https://mlsanity.com/paper/2305.19744/) (2023)
- [In-Context Learning of Temporal Point Processes with Foundation Inference Models](https://mlsanity.com/paper/2509.24762/) (2025)
- [Reasoning LLMs in the Medical Domain: A Literature Survey](https://mlsanity.com/paper/2508.19097/) (2025)
- [Recurrent Point Review Models](https://mlsanity.com/paper/2012.05684/) (2020)
- [Dynamic Review-based Recommenders](https://mlsanity.com/paper/2110.14747/) (2021)
- [Scalable Marked Point Processes for Exchangeable and Non-Exchangeable Event Sequences](https://mlsanity.com/paper/2105.14574/) (2021)
- [Towards Unified Multimodal Financial Forecasting: Integrating Sentiment Embeddings and Market Indicators via Cross-Modal Attention](https://mlsanity.com/paper/2508.13327/) (2025)

## Abstract (arXiv)

Many scientific fields, from medicine to seismology, rely on analyzing sequences of events over time to understand complex systems. Traditionally, machine learning models must be built and trained from scratch for each new dataset, which is a slow and costly process. We introduce a new approach: a single, powerful model that learns the underlying patterns of event data in context. We trained this "foundation model" on millions of simulated event sequences, teaching it a general-purpose understanding of how events can unfold. As a result, our model can analyze new scientific data instantly, without retraining, simply by looking at a few examples from the dataset. It can also be quickly fine-tuned for even higher accuracy. This approach makes sophisticated event analysis more accessible and accelerates the pace of scientific discovery.