VisionHOPE: Visual Backbones as Self-Modifying Learning Systems
Visual backbones have evolved from Convolutional Neural Networks (CNNs) with local aggregation to Vision Transformers (ViTs) with global interactions, State-Space Models (SSMs) with input-dependent state transitions, and Test-Time Training (TTT) layers that adapt an inner learner while processing an image. Across this progression, visual computation has become increasingly adaptive to each input, yet the rules governing that adaptation remain largely prescribed by the trained backbone. We introduce VisionHOPE, the first generic visual backbone formulated as a self-modifying learning system, in which what the model remembers and how it learns co-evolve within an image. Building on the self...
| Authors | Siran Peng, Tianshuo Zhang, Tianyu Fu et al. |
|---|---|
| Primary category | cs.CV |
| Published | 27 September 2026 |
| Last updated at source | 27 September 2026 |
Connected in the knowledge graph
- PSRben/VisionHOPEModel · cited by
Models and datasets referencing this paper
- PSRben/VisionHOPEModel
Silytics shows public metadata from arXiv and links to the original. Information may be incomplete or out of date. Last refreshed 17 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.