Evolving Cache Schedules for Fast Diffusion Policy Inference
Diffusion policies achieve strong visuomotor control by iteratively denoising action chunks, but repeated denoising makes real-time deployment computationally demanding. Cache-based methods reduce inference cost by reusing intermediate activations, but existing training-free schedules typically allocate computation uniformly across blocks, ignoring heterogeneous redundancy across blocks and leading to a suboptimal performance-efficiency trade-off. To bridge this gap, we introduce Evolving Cache Schedules (EVO), a training-free acceleration framework that globally schedules cache refreshes via
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.
- FuzzySimilar title/name (fuzzy) · 59%stabilityai/stable-diffusion-xl-base-1.0 →
“Fuzzy title match (0.73): “Evolving Cache Schedules for Fast Diffusion Policy Inference” ≈ “stabilityai/stable-diffusion-xl-base-1.0””
- FuzzySimilar title/name (fuzzy) · 59%CompVis/stable-diffusion-v1-4 →
“Fuzzy title match (0.73): “Evolving Cache Schedules for Fast Diffusion Policy Inference” ≈ “CompVis/stable-diffusion-v1-4””
- FuzzySimilar title/name (fuzzy) · 59%stabilityai/stable-diffusion-3.5-large →
“Fuzzy title match (0.73): “Evolving Cache Schedules for Fast Diffusion Policy Inference” ≈ “stabilityai/stable-diffusion-3.5-large””
- PossiblePossibly related (embedding) · 53%Exploring continual learning without replay buffers: Our findings using dynamic task-similarity routing [P] →
- PossiblePossibly related (embedding) · 49%Scaling Up Reinforcement Learning for Traffic Smoothing: A 100-AV Highway Deployment →
- FuzzySimilar title/name (fuzzy) · 87%LMCache/LMCache →
“Fuzzy title match (0.94): “Evolving Cache Schedules for Fast Diffusion Policy Inference” ≈ “LMCache/LMCache””
- FuzzySimilar title/name (fuzzy) · 84%xorbitsai/inference →
“Fuzzy title match (0.92): “Evolving Cache Schedules for Fast Diffusion Policy Inference” ≈ “xorbitsai/inference””
- FuzzyOverlapping authors or contributors · 62%ray-project/ray →
“Shared author/contributor keys: wang”