Foundation Model Approach Enables In-Context Learning for Temporal Point Process Inference
Researchers have developed FIM-PP, a foundation inference model that uses in-context learning to predict event sequences without requiring separate specialized models for each system. The model is pretrained on synthetic data from Hawkes processes and can be applied to real-world temporal point process data with minimal or no additional training. This approach could simplify the modeling of complex event sequences across diverse domains by enabling rapid adaptation to new systems.
A new machine learning approach published at ICLR 2026 demonstrates that foundation models can effectively learn to infer marked temporal point processes (MTPPs) through in-context learning rather than task-specific training. The Foundation Inference Model for Point Processes (FIM-PP) is pretrained on a large synthetic dataset of Hawkes processes, allowing it to estimate conditional intensity functions from event histories without domain-specific retraining. Experiments show the amortized approach matches the performance of specialized models on next-event prediction benchmarks. This represents a shift from the traditional paradigm of training separate neural networks for each target system, instead leveraging pretraining and rapid finetuning to adapt to new domains. The method draws on amortized inference techniques to enable efficient generalization across diverse temporal point process systems.
What's missing
The paper does not discuss computational costs or inference speed comparisons between FIM-PP and specialized models. Additionally, the specific real-world datasets used for evaluation and the magnitude of performance differences (if any) between the foundation model and specialized baselines are not detailed in the abstract.
What different sources said
- arXiv cs.LGCenter
In-Context Learning of Stochastic Differential Equations with Foundation Inference Models
Related
Gut Bacteria Enzyme Found to Break Down Heat-Processed Food Compounds, Producing Novel Biogenic Amines
Researchers have discovered that an enzyme in common gut bacteria can degrade N-epsilon-carboxymethyllysine (CML), a compound formed during thermal food processing, producing previously unknown biogenic amines. The enzyme, ornithine decarboxylase SpeC from enterobacteria, acts on CML and related modified lysine derivatives through a low-level 'underground' catalytic activity. This finding suggests a previously unrecognized communication axis between thermally processed dietary compounds and gut microbial physiology, with potential implications for host health.
Full-Length Gene Sequencing Reveals Two Distinct Bacterial Communities in Black-Legged Ticks Expanding Into Canada
Researchers used Oxford Nanopore full-length 16S rRNA gene sequencing to characterize the microbiome of Ixodes scapularis black-legged ticks collected in Nova Scotia, Canada, distinguishing between tick-adapted bacteria and environmentally acquired bacteria. The study comes as I. scapularis — the primary vector of Lyme disease — is rapidly expanding northward into Canada due to climate change. The findings suggest that environmentally derived bacteria in tick microbiomes are not mere contamination, which has implications for how tick microbiome data is collected and interpreted across surveillance studies.
Study Identifies Metabolic Link Between Cell Envelope Stress and Biofilm Formation in Bacteria
Researchers have discovered that the metabolite acetyl-CoA directly inhibits enzymes that degrade the bacterial signaling molecule c-di-GMP, connecting cell envelope biosynthesis stress to biofilm formation in Pseudomonas aeruginosa. The study found that sub-inhibitory concentrations of antibiotics targeting early peptidoglycan biosynthesis — but not other antibiotic classes — elevate c-di-GMP levels by reducing phosphodiesterase activity, with acetyl-CoA competing for the enzyme active site. Because the relevant enzyme domain is broadly conserved across bacterial species, this checkpoint mechanism may be widespread and could have implications for understanding antibiotic-induced biofilm responses.