This work introduces LaT-PFN, a novel time series model that combines PFN and JEPA frameworks to generate zero-shot forecasts efficiently, using a versatile latent space that enables adaptable time granularity and superior predictive performance.
☆22Aug 1, 2024Updated 2 years ago
Alternatives and similar repositories for Lat-PFN
Users that are interested in Lat-PFN are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Implementation of "TS-JEPA"☆45Nov 17, 2024Updated last year
- Fine-grained attention in hierarchical transformers for tabular time-series.☆12Dec 24, 2024Updated last year
- SSCP: Improving Adaptive Conformal Prediction Using Self-supervised Learning (AISTATS 2023)☆17Mar 8, 2023Updated 3 years ago
- ☆25Nov 23, 2021Updated 4 years ago
- Welcome to the SOLETE platform. These scripts are meant to help you using the homonymous dataset [1] and to replicate the results from th…☆13Sep 14, 2023Updated 2 years ago
- Proton VPN Special Offer - Get 70% off • AdSpecial partner offer. Trusted by over 100 million users worldwide. Tested, Approved and Recommended by Experts.
- An extension of Py-Boost to probabilistic modelling☆24Jan 19, 2023Updated 3 years ago
- [JBHI 2024] Self-supervised pre-training on ECG collected in the wild☆15Nov 14, 2023Updated 2 years ago
- ☆20Mar 10, 2025Updated last year
- TuneTables is a tabular classifier that implements prompt tuning for frozen prior-fitted networks.☆25Mar 31, 2025Updated last year
- A PyTorch implementation of the Attention Diffusion Network from "Structured Time Series Prediction without Structural Prior"☆14Jul 10, 2022Updated 4 years ago
- ☆46Jul 25, 2024Updated 2 years ago
- ☆14Updated this week
- A Python library for anti-clustering algorithms☆10Sep 4, 2025Updated 11 months ago
- A mixture density network, by PyTorch, for scikit-learn☆26Feb 27, 2026Updated 6 months ago
- Proton VPN Special Offer - Get 70% off • AdSpecial partner offer. Trusted by over 100 million users worldwide. Tested, Approved and Recommended by Experts.
- GraphLand: Evaluating Graph Machine Learning Models on Diverse Industrial Data