# Jua

> Jua is training a foundation model of how reality behaves (EPT-2) and the agent that acts inside it (Athena). The current focus is the atmosphere — state of the art on atmospheric prediction, in production across utilities and trading desks worldwide. Next is the rest of physical reality.

Jua.ai AG is an AI lab headquartered in Zürich, Switzerland (founded 2023). Research is peer-reviewed at NeurIPS and ICLR, with a Series A led by Ananda Impact Ventures and Future Energy Ventures. Team and collaborators span ETH Zurich, KIT, Google Research, the ETH AI Center, DeepMind, and Meta.

## Products

- [EPT-2 (Earth Physics Transformer)](https://jua.ai/company): foundation model for atmospheric physics. Global, hourly-updating, outperforms ECMWF HRES, IFS ENS, GEFS, NVIDIA FourCastNet 3, and Google GraphCast on RMSE, ACC, and CRPS. Family includes EPT-2 HRRR (high-resolution Europe), EPT-2 RR (hourly global), and EPT-2e (extended range to 60 days, roadmap to 180).
- [Athena](https://athena.jua.ai): AI agent for energy traders. Pairs the world model with a controller and a toolset. In production across utilities and trading desks worldwide. Sign in at athena.jua.ai.

## Pages

- [Home](https://jua.ai/): the Jua thesis — why physical AI needs its own foundation model.
- [Company](https://jua.ai/company): vision, benchmarks, transfer results (weather → CFD → airfoils), team, and papers.
- [Customers](https://jua.ai/customers): utilities and trading desks running Jua in production (Axpo, TotalEnergies, Shell, Enel, Statkraft, EnBW, EDF, Hydro-Québec, Adani Energy, Vitol, BKW, ESB).
- [Energy trading](https://jua.ai/energy-trading): deep dive on Athena for energy traders — inputs, capabilities, forecast skill.
- [Blog](https://jua.ai/blog): technical reports, product launches, research notes.
- [Careers](https://jua.ai/careers): open roles in research, engineering, and go-to-market. Based in Zürich.
- [Contact](https://jua.ai/contact): book a demo, email sales, or open Athena.

## Papers

- [Universal Diffusion-Based Probabilistic Downscaling (ICLR 2026)](https://openreview.net/forum?id=8N6HgVeXbo) — Molinaro, Siegenheim, Martin, Frey, Poulsen, Seitz, Gabler.
- [EPT-2 Technical Report (arXiv 2025)](https://arxiv.org/abs/2507.09703) — Jua Team.
- [Poseidon: Efficient Foundation Models for PDEs (NeurIPS 2024)](https://proceedings.neurips.cc/paper_files/paper/2024/hash/84e1b1ec17bb11c57234e96433022a9a-Abstract-Conference.html) — Herde, Raonić, Rohner, Käppeli, Molinaro, de Bézenac, Mishra (ETH Zurich).
- [Generative AI for fast and accurate statistical computation of fluids (arXiv 2024)](https://arxiv.org/abs/2409.18359).
- [EPT-1.5 Technical Report (arXiv 2024)](https://arxiv.org/abs/2410.15076).

## Social

- LinkedIn: https://www.linkedin.com/company/juaai/
- GitHub: https://github.com/juaAI

## Sitemap

- https://jua.ai/sitemap.xml