Evolving Cache Schedules for Fast Diffusion Policy Inference
Ranking
Overall
72
Content
85
Popularity
40
Observed public metrics from 1 member.
Merged summary
TL;DR - EVO uses evolutionary search to optimize cache-refresh schedules for pretrained diffusion policies, accelerating visuomotor action generation without retraining. It achieves up to an 8.05Ă— speedup while retaining near-full task performance.
- Searches globally across transformer blocks and denoising timesteps to identify reusable activations.
- Uses redundancy-aware initialization and target-conditioned early stopping to make offline schedule optimization practical.
- Plugs optimized schedules directly into existing diffusion policies.
- Reduces inference compute from 15.77G FLOPs to as little as 1.96G on manipulation benchmarks.
Sources (1)
Evolving Cache Schedules for Fast Diffusion Policy Inference
Public signals
Semantic Scholar citations 0 · Semantic Scholar influential citations 0
TL;DR - EVO uses evolutionary search to optimize cache-refresh schedules for pretrained diffusion policies, accelerating visuomotor action generation without retraining. It achieves up to an 8.05Ă— speedup while retaining near-full task performance.
- Searches globally across transformer blocks and denoising timesteps to identify reusable activations.
- Uses redundancy-aware initialization and target-conditioned early stopping to make offline schedule optimization practical.
- Plugs optimized schedules directly into existing diffusion policies.
- Reduces inference compute from 15.77G FLOPs to as little as 1.96G on manipulation benchmarks.