The paper introduces the Foundation Event Predictor (FEP), a scalable in‑context architecture that performs next‑event prediction across diverse event logs using learned, event‑level nonparametric inference. FEP employs causal self‑attention to encode context and target histories, cross‑attention for relevance‑weighted aggregation, and permutation‑robust embedding learning to decouple event IDs from semantics. Trained on 696 real‑world datasets and evaluated on 50 unseen ones, FEP generalizes effectively to new systems without parameter adaptation, often matching or surpassing models trained separately on each target dataset.
arXiv:2609.24579v1 Announce Type: new Abstract: Event logs arise in a wide range of real-world processes, capturing not only event activities and timestamps but also multi-modal contextual informatio...
arXiv:2606. 09861v1 Announce Type: cross Abstract: While Next-Token Prediction (NTP) has unified LLM pretraining, its adaptation to unbounded, continuous time series (TS) remains open.
D-TAIA is a framework that adapts large language models for multi‑task predictive process monitoring, jointly predicting the next activity and remaining time of ongoing cases. It uses domain‑aware triplet loss pre‑training, FAISS‑based nearest‑neighbor retrieval for time estimation, and a TAIA inference strategy to preserve sequential reasoning while fine‑tuning a 10 M‑parameter backbone. Across four real‑world event logs, D‑TAIA achieves state‑of‑the‑art or competitive results compared to a fine‑tuned LLM and a recurrent neural network baseline, with ablation studies showing the effectiveness of NLP and computer‑vision techniques for this domain.
arXiv:2602. 00541v2 Announce Type: replace Abstract: Clinical events captured in Electronic Health Records (EHR) are irregularly sampled and may consist of a mixture of discrete events and numerical measurements, such as laboratory values or treatment dosages.
arXiv:2608. 10120v1 Announce Type: new Abstract: Modern sequence models, from Transformers to State Space Models, have enabled powerful generative modeling across diverse domains, yet they are typically trained to predict what happens while treating when it happens as a secondary concern.
KITE is a knowledge‑injected temporal encoder that augments self‑supervised event forecasting with semantic priors supplied by system engineers. It uses two switchable mechanisms—a covariate mechanism and an attention‑bias mechanism—so the same architecture can incorporate different prior types without per‑dataset tuning. Experiments show that informative priors improve performance in short contexts and enable out‑of‑domain transfer, while priors already present in the observed window have little effect.
The paper introduces a Unified Particle Filter LSTM (Unified PF‑LSTM) for data‑driven process simulation, which maintains a weighted set of recurrent‑state hypotheses to better capture latent process conditions from incomplete event logs. By summarizing this particle belief with a weighted mean and moment‑generating‑function features, the model predicts next‑activity probabilities and conditional sojourn‑time quantiles. Experiments on three real‑world emergency department datasets show that the framework consistently outperforms existing data‑driven baselines in reproducing routing, duration, and system‑level behavior, especially when process dynamics are only partially reflected in the logs.
FEAT is a foundation model designed for extremely large structured data that replaces quadratic self‑attention with a linear‑complexity dual‑axis encoding architecture. It combines an adaptive‑fusion bidirectional state‑space model with convolutional gated linear attention to achieve permutation‑invariant representation learning in O(N) time. Experiments on 12 real‑world database benchmarks show that FEAT outperforms existing structured data foundation models on zero‑shot tasks and can be up to 50× faster in inference latency.
arXiv:2607. 15447v1 Announce Type: new Abstract: Recent research in clinical machine learning, focusing on outcome predictions in intensive care unit (ICU), has shifted from bespoke supervised models to foundation models, utilising modern representation learning methods.
The paper introduces a unified multi-domain and multi-task generative framework for event extraction that incorporates explicit domain conditioning signals and task-specific prompts. This design allows a single model to adapt dynamically to different event schemas without needing full event label sets during inference, supporting both pipeline and end-to-end extraction. Experiments on various benchmarks show competitive performance, strong cross-domain generalization, and practical scalability while maintaining domain-specific precision.
arXiv:2602. 12147v4 Announce Type: replace Abstract: Time series foundation models (TSFMs) are revolutionizing the forecasting landscape from specific dataset modeling to generalizable task evaluation.
arXiv:2606. 08601v1 Announce Type: new Abstract: Large Language Models (LLMs) have recently demonstrated impressive potential for time series forecasting.