Dual-Rate Diffusion: Accelerating diffusion models with an interleaved heavy-light network
cs.LG, cs.CV
Submitted: 2026-05-18
Updated: 2026-11-06
Terminology
Sources
- Generative Modeling via Drifting
- Mean Flows for One-step Generative Modeling
- Clockwork Diffusion: Efficient Generation With Model-Step Distillation
- Classifier-Free Diffusion Guidance
- Adaptive Caching for Faster Video Generation with Diffusion Transformers
- Consistency Trajectory Models: Learning Probability Flow ODE Trajectory of Diffusion
- Adam: A Method for Stochastic Optimization
- DiffWave: A Versatile Diffusion Model for Audio Synthesis
- Faster Diffusion via Temporal Attention Decomposition
- SmoothCache: A Universal Inference Acceleration Technique for Diffusion Transformers
- Token Caching for Diffusion Transformer Acceleration
- Simplifying, Stabilizing and Scaling Continuous-Time Consistency Models
- Generative Modelling With Inverse Heat Dissipation
- Accelerating Diffusion Transformers with Token-wise Feature Caching
- Rethinking Token-wise Feature Caching: Accelerating Diffusion Transformers with Dual Feature Caching
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