RA-CFGCache: From Branch-Level Criteria to Guided-Risk Control under Classifier-Free Guidance

arXiv:2609.36433 · cs.CV · Submitted 2026-09-29 · Read on arXiv

cs.CV

Submitted: 2026-09-29

Updated: 2026-09-29

Comments: 30 pages, 17 figures, NeurIPS 2026

Code: https://github.com/yiming-l21/RA-CFGCache

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Calibration — 48× in this paper · explained in 7 episodes
• Alignment — 47× in this paper · explained in 1 episode
• Fidelity — 28× in this paper · explained in 2 episodes
• Diffusion Model — 17× in this paper · explained in 8 episodes
• Transformer — 14× in this paper · explained in 2 episodes
• Diffusion Models — 12× in this paper · explained in 6 episodes
• Ablation — 6× in this paper · explained in 1 episode
• Cosine Similarity — 5× in this paper · explained in 3 episodes
• Redundancy — 5× in this paper · explained in 2 episodes
• Robustness — 5× in this paper · explained in 5 episodes
• Generative Model — 4× in this paper · explained in 2 episodes
• Generative Models — 4× in this paper · explained in 2 episodes
• Distillation — 3× in this paper · explained in 2 episodes
• Pruning — 2× in this paper · explained in 4 episodes
• Trace — 2× in this paper · explained in 2 episodes
• Ablation Studies — 1× in this paper · explained in 1 episode
• Benchmark — 1× in this paper · explained in 2 episodes
• Consistency — 1× in this paper · explained in 3 episodes
• Core — 1× in this paper · explained in 2 episodes
• Generative Modeling — 1× in this paper · explained in 3 episodes
• Transferability — 1× in this paper · explained in 4 episodes

Sources

• Denoising Diffusion Probabilistic Models
• Generative Modeling by Estimating Gradients of the Data Distribution
• Diffusion Models Beat GANs on Image Synthesis
• Scalable Diffusion Models with Transformers
• Adversarial Diffusion Distillation
• Denoising Diffusion Implicit Models
• DPM-Solver: A Fast ODE Solver for Diffusion Probabilistic Model Sampling in Around 10 Steps
• Token Pruning for Caching Better: 9 Times Acceleration on Stable Diffusion for Free
• DeepCache: Accelerating Diffusion Models for Free
• LeMiCa: Lexicographic Minimax Path Caching for Efficient Diffusion-Based Video Generation
• Faster Diffusion: Rethinking the Role of the Encoder for Diffusion Model Inference
• Real-Time Video Generation with Pyramid Attention Broadcast
• $\Delta$-DiT: A Training-Free Acceleration Method Tailored for Diffusion Transformers
• DiCache: Let Diffusion Model Determine Its Own Cache
• SenCache: Accelerating Diffusion Model Inference via Sensitivity-Aware Caching
• Forecast then Calibrate: Feature Caching as ODE for Efficient Diffusion Transformers
• FasterCache: Training-Free Video Diffusion Model Acceleration with High Quality
• Analysis of Classifier-Free Guidance Weight Schedulers
• Applying Guidance in a Limited Interval Improves Sample and Distribution Quality in Diffusion Models
• MAMBO-G: Magnitude-Aware Mitigation for Boosted Guidance

Related papers

• Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
• AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
• Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
• MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
• TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
• A Survey on Efficient Vision-Language-Action Models