Beyond Quadratic Attention: Separable Gaussian Operators for ODE Vision Transformers
cs.LG, cs.CV
Submitted: 2026-11-05
Updated: 2026-11-05
Code: https://github.com/4rtemi5/ssog
Terminology
Sources
- ODE-ViT: Plug & Play Attention Layer from the Generalization of the ViT as an Ordinary Differential Equation
- Investigating Single-Block Recurrence in Vision Transformers for Image Recognition
- Gaussian Mixture Attention: Linear-Time Sequence Mixing via Probabilistic Latent Routing
- Segment Anything
- Linformer: Self-Attention with Linear Complexity
- Pay Attention to Attention Distribution: A New Local Lipschitz Bound for Transformers
Related papers
- A Physics-Regulated Neural Framework for Learning 3D Grain Growth Dynamics
- FlexMoE: Learning One-for-All Multi-Budget Expert Pruning for Flexible MoE Deployment
- OptiMind: Improving Small Language Models for Optimization Modeling through Formulation Guidance and Multi-Turn Learning
- Staying in the Sweet Spot: Boost Reasoning Evolution via Responsive Rollout Difficulty Manipulation
- Examining the Impact of Data and Training Methods on Emergent and Subliminal Misalignment
- Rethinking Black-Box On-Policy Distillation: A Rubric-based Analysis