# BrainVista: Modeling Naturalistic Brain Dynamics as Multimodal Next-Token Prediction

arXiv: https://arxiv.org/abs/2602.04512 · HTML: https://mlsanity.com/paper/2602.04512/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 22 of its 53 references that are in the map.
- First posted on arXiv 4 Feb 2026.

## Builds on (most cited first, 22 of 22)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [A Time Series is Worth 64 Words: Long-term Forecasting with Transformers](https://mlsanity.com/paper/2211.14730/) (2022)
- [TimesNet: Temporal 2D-Variation Modeling for General Time Series Analysis](https://mlsanity.com/paper/2210.02186/) (2022)
- [iTransformer: Inverted Transformers Are Effective for Time Series Forecasting](https://mlsanity.com/paper/2310.06625/) (2023)
- [V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planning](https://mlsanity.com/paper/2506.09985/) (2025)
- [W2v-BERT: Combining Contrastive Learning and Masked Language Modeling for Self-Supervised Speech Pre-Training](https://mlsanity.com/paper/2108.06209/) (2021)
- [Reconstructing the Mind's Eye: fMRI-to-Image with Contrastive Learning and Diffusion Priors](https://mlsanity.com/paper/2305.18274/) (2023)
- [MindEye2: Shared-Subject Models Enable fMRI-To-Image With 1 Hour of Data](https://mlsanity.com/paper/2403.11207/) (2024)
- [Timer-XL: Long-Context Transformers for Unified Time Series Forecasting](https://mlsanity.com/paper/2410.04803/) (2024)
- [The Algonauts Project 2025 Challenge: How the Human Brain Makes Sense of Multimodal Movies](https://mlsanity.com/paper/2501.00504/) (2024)
- [TRIBE: TRImodal Brain Encoder for whole-brain fMRI response prediction](https://mlsanity.com/paper/2507.22229/) (2025)
- [MindSimulator: Exploring Brain Concept Localization via Synthetic FMRI](https://mlsanity.com/paper/2503.02351/) (2025)
- [Brain Harmony: A Multimodal Foundation Model Unifying Morphology and Function into 1D Tokens](https://mlsanity.com/paper/2509.24693/) (2025)
- [MindLLM: A Subject-Agnostic and Versatile Model for fMRI-to-Text Decoding](https://mlsanity.com/paper/2502.15786/) (2025)
- [CineBrain: A Large-Scale Multi-Modal Brain Dataset During Naturalistic Audiovisual Narrative Processing](https://mlsanity.com/paper/2503.06940/) (2025)
- [SynBrain: Enhancing Visual-to-fMRI Synthesis via Probabilistic Representation Learning](https://mlsanity.com/paper/2508.10298/) (2025)
- [SLIM-Brain: A Data- and Training-Efficient Foundation Model for fMRI Data Analysis](https://mlsanity.com/paper/2512.21881/) (2025)
- [Uncovering cognitive taskonomy through transfer learning in masked autoencoder-based fMRI reconstruction](https://mlsanity.com/paper/2407.00033/) (2024)
- [Hierarchical Characterization of Brain Dynamics via State Space-based Vector Quantization](https://mlsanity.com/paper/2506.22952/) (2025)
- [Improving Multimodal Brain Encoding Model with Dynamic Subject-awareness Routing](https://mlsanity.com/paper/2510.04670/) (2025)
- [BrainCodec: Neural fMRI codec for the decoding of cognitive brain states](https://mlsanity.com/paper/2410.04383/) (2024)

## Abstract (arXiv)

Naturalistic fMRI characterizes the brain as a dynamic predictive engine driven by continuous sensory streams. However, modeling the causal forward evolution in realistic neural simulation is impeded by the timescale mismatch between multimodal inputs and the complex topology of cortical networks. To address these challenges, we introduce BrainVista, a multimodal autoregressive framework designed to model the causal evolution of brain states. BrainVista incorporates Network-wise Tokenizers to disentangle system-specific dynamics and a Spatial Mixer Head that captures inter-network information flow without compromising functional boundaries. Furthermore, we propose a novel Stimulus-to-Brain (S2B) masking mechanism to synchronize high-frequency sensory stimuli with hemodynamically filtered signals, enabling strict, history-only causal conditioning. We validate our framework on Algonauts 2025, CineBrain, and HAD, achieving state-of-the-art fMRI encoding performance. In long-horizon rollout settings, our model yields substantial improvements over baselines, increasing pattern correlation by 36.0% and 33.3% on relative to the strongest baseline Algonauts 2025 and CineBrain, respectively.