# SpikeWorld: Fast-State Adaptation for Frozen Spiking World Models

arXiv: https://arxiv.org/abs/2608.07712 · HTML: https://mlsanity.com/paper/2608.07712/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Embodied and robot world models, one of 11 directions in World models.
- Builds on 21 of its 24 references that are in the map.
- First posted on arXiv 7 Aug 2026.

## Placed in

- World models / [Embodied and robot world models](https://mlsanity.com/wm/embodied-and-robot-world-models/)

## Builds on (most cited first, 21 of 21)

- [World Models](https://mlsanity.com/paper/1803.10122/) (2018)
- [Meta-World: A Benchmark and Evaluation for Multi-Task and Meta Reinforcement Learning](https://mlsanity.com/paper/1910.10897/) (2019)
- [Event-based Vision: A Survey](https://mlsanity.com/paper/1904.08405/) (2019)
- [V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planning](https://mlsanity.com/paper/2506.09985/) (2025)
- [Surrogate Gradient Learning in Spiking Neural Networks](https://mlsanity.com/paper/1901.09948/) (2019)
- [Revisiting Feature Prediction for Learning Visual Representations from Video](https://mlsanity.com/paper/2404.08471/) (2024)
- [Continual Test-Time Domain Adaptation](https://mlsanity.com/paper/2203.13591/) (2022)
- [RMA: Rapid Motor Adaptation for Legged Robots](https://mlsanity.com/paper/2107.04034/) (2021)
- [Efficient Test-Time Model Adaptation without Forgetting](https://mlsanity.com/paper/2204.02610/) (2022)
- [Efficient Off-Policy Meta-Reinforcement Learning via Probabilistic Context Variables](https://mlsanity.com/paper/1903.08254/) (2019)
- [Learning to Adapt in Dynamic, Real-World Environments Through Meta-Reinforcement Learning](https://mlsanity.com/paper/1803.11347/) (2018)
- [Spikformer: When Spiking Neural Network Meets Transformer](https://mlsanity.com/paper/2209.15425/) (2022)
- [SuperSpike: Supervised learning in multi-layer spiking neural networks](https://mlsanity.com/paper/1705.11146/) (2017)
- [Using Fast Weights to Attend to the Recent Past](https://mlsanity.com/paper/1610.06258/) (2016)
- [The Heidelberg spiking datasets for the systematic evaluation of spiking neural networks](https://mlsanity.com/paper/1910.07407/) (2019)
- [SpikeGPT: Generative Pre-trained Language Model with Spiking Neural Networks](https://mlsanity.com/paper/2302.13939/) (2023)
- [Masked Event Modeling: Self-Supervised Pretraining for Event Cameras](https://mlsanity.com/paper/2212.10368/) (2022)
- [EventCLIP: Adapting CLIP for Event-based Object Recognition](https://mlsanity.com/paper/2306.06354/) (2023)
- [EventBind: Learning a Unified Representation to Bind Them All for Event-based Open-world Understanding](https://mlsanity.com/paper/2308.03135/) (2023)
- [Beyond Rate Coding: Surrogate Gradients Enable Spike Timing Learning in Spiking Neural Networks](https://mlsanity.com/paper/2507.16043/) (2025)
- [Algorithm-hardware co-design of neuromorphic networks with dual memory pathways](https://mlsanity.com/paper/2512.07602/) (2025)

## Abstract (arXiv)

A predictive model receives a self-supervised signal whenever the consequence of an action is observed. Using that signal after deployment is difficult when dynamics and semantics share parameters: freezing prevents adaptation, whereas weight updates require optimizer state and may alter the learned representation. Here we introduce SpikeWorld, a 1.45M-parameter sparse spiking model jointly trained for heterogeneous sensory prediction, semantics, image-text binding and action-conditioned dynamics. At deployment, all trained parameters are frozen. Delayed next-state residuals update two external paths: cumulative fixed-bank losses select the bounded action correction, while route-specific residual matrices refine next-state prediction. Neither path uses labels, teacher outputs, rewards, success signals or the true shift value. Joint optimization improves action next-state MSE by 17.10% while also improving multimodal prediction, semantic accuracy and image-text retrieval. On held-out shear and attenuation streams, the combined external state improves aggregate prediction by 5.48% and 30.01%; its fixed-bank action path improves tracking by 24.20% and 3.94%, respectively. In a six-arm study comprising 450 new Meta-World trajectories (75 per arm), SpikeWorld raises frozen-policy reward by 7.90 (95% CI [2.48, 14.06]); the 13.33-point success difference is descriptive (CI [0, 40]). For identical sensory inputs, model parameters and inherited semantic outputs remain bitwise unchanged. A 16-byte RLS estimator obtains the highest non-oracle reward on linear attenuation, showing that the contribution is not superior linear identification, but its integration with a frozen multimodal spiking checkpoint. Reference code is publicly available at https://github.com/Oooorca/SpikeWorld.