SpikeWorld: Fast-State Adaptation for Frozen Spiking World Models
Ziqiao Yu
cs.CV, cs.AI
Submitted: 2026-08-07
Updated: 2026-08-11
Comments: 14 pages, 2 figures, 4 tables. Code: https://github.com/Oooorca/SpikeWorld
Code: https://github.com/Oooorca/SpikeWorld
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planning
- Revisiting Feature Prediction for Learning Visual Representations from Video
- World Models
- Masked Event Modeling: Self-Supervised Pretraining for Event Cameras
- EventCLIP: Adapting CLIP for Event-based Object Recognition
- Meta-World: A Benchmark and Evaluation for Multi-Task and Meta Reinforcement Learning
- EventBind: Learning a Unified Representation to Bind Them All for Event-based Open-world Understanding
- SpikeGPT: Generative Pre-trained Language Model with Spiking Neural Networks
Related papers
- Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
- AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
- Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
- MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
- TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
- A Survey on Efficient Vision-Language-Action Models