Driving · 2026-10-05

IGNITE Tokamak World Model Architecture

Peter Steiner, Azarakhsh Jalalvand, Nathaniel Chen, Kouroche Bouchiat, Ricardo Shousha, SangKyeun Kim, Egemen Kolemen

arXiv:2610.02515PDF

AI-assisted summary based on the paper. Consult the linked source for methods and limitations. Benchmark numbers appear after editor verification.

TL;DR

IGNITE is a generative, multi-modal, actuator-conditioned world foundation model for fusion plasma behavior at the DIII-D tokamak. Trained self-supervised on over a decade of unlabeled experimental data (8000+ discharges), it autoregressively forecasts future diagnostics given initial latent plasma states and actuator trajectories, using spatio-temporal tokenizers with discrete FSQ codes and a transformer dynamics backbone.

Why it matters

The authors propose the first large-scale world model for fusion plasma and a first multi-modal approach spanning signals from Hz to MHz and multiple diagnostic modalities. IGNITE can simulate DIII-D discharges from actuator trajectories and can accept trajectories supplied or generated on-the-fly (from text prompts or desired outcomes), aiming to support efficient AI-driven experimental planning and world modeling for nuclear fusion.

Method

  • Self-supervised training on 8000+ DIII-D discharges using modality-specific spatio-temporal tokenizers with discrete FSQ codes, creating a shared latent space for dynamics modeling.
  • An actuator-conditioned autoregressive transformer dynamics model (adapted from Genie; spatiotemporal factorized transformer) predicts next-frame token codes over a context of 20 windows of 50 ms and rolls out over the discharge.
  • Two-stage training: pre-train codecs per modality, then fix them and train the dynamics model with maskGIT-style masked-token prediction for autoregressive rollout.

Limitation

The paper reports that uncertainty quantification was not run, and error-bar/statistical-significance reporting is not provided.

Abstract (from arXiv)

We introduce IGNITE, a generative world foundation model for fusion plasma behavior simulation trained in a self-supervised manner from over a decade of unlabeled experimental data at the DIII-D National Fusion Facility. The core of IGNITE is a dynamics model that can simulate DIII-D discharges from a given set of actuator trajectories. These trajectories can be supplied or generated on-the-fly from a textual prompt or from desired experimental outcomes. The model architecture consists of several spatio-temporal tokenizers that embed the different input modalities, including time-series like spatio-temporal measurement data, image sequences, and high-resolution spectrograms, each of which collected at vastly different time scales. The backbone is composed of an auto-regressive dynamics model that has the capacity to predict entire DIII-D discharges given initial latent plasma states and actuator trajectories over a theoretical infinite horizon. IGNITE paves the way towards efficient AI-driven experimental planning and world modeling for nuclear fusion.

Related papers

Publication record

Bibliographic evidence describes where and when a record appeared. It does not validate scientific claims.

First public release: 2026-10-01 · Indexed by Pub-AI: 2026-10-05 UTC

preprint

IGNITE Tokamak World Model Architecture

Peter Steiner, Azarakhsh Jalalvand, Nathaniel Chen, Kouroche Bouchiat, Ricardo Shousha, SangKyeun Kim, Egemen Kolemen

Preprint posted: 2026-10-01 · Original record ↗

arxiv
2610.02515
Explicit source versions (1)
  • v1 · 2026-10-01
  1. Preprint available

    Source date: 2026-10-01 · First detected: 2026-10-25 UTC · Historical baseline

    Source evidence (1)
Abstract · arxiv

We introduce IGNITE, a generative world foundation model for fusion plasma behavior simulation trained in a self-supervised manner from over a decade of unlabeled experimental data at the DIII-D National Fusion Facility. The core of IGNITE is a dynamics model that can simulate DIII-D discharges from a given set of actuator trajectories. These trajectories can be supplied or generated on-the-fly from a textual prompt or from desired experimental outcomes. The model architecture consists of several spatio-temporal tokenizers that embed the different input modalities, including time-series like spatio-temporal measurement data, image sequences, and high-resolution spectrograms, each of which collected at vastly different time scales. The backbone is composed of an auto-regressive dynamics model that has the capacity to predict entire DIII-D discharges given initial latent plasma states and actuator trajectories over a theoretical infinite horizon. IGNITE paves the way towards efficient AI-driven experimental planning and world modeling for nuclear fusion.