CoReDiT reduces self-attention FLOPs in DiTs by up to 55% via linear-time spatial coherence pruning and neighbor-based reconstruction, delivering 1.33x-1.72x speedups with maintained quality.
Effortless efficiency: Low-cost pruning of diffusion models
6 Pith papers cite this work. Polarity classification is still indexing.
6
Pith papers citing it
representative citing papers
HERO accelerates world model inference 1.73x via hierarchical patch-wise refresh in shallow layers and linear extrapolation in deeper layers with minimal quality loss.
2ndMatch finetunes pruned diffusion models via second-order Jacobian matching inspired by Finite-Time Lyapunov Exponents to reduce the quality gap with dense models on image generation tasks.
OASIS reduces redundancy in diffusion models for real-world video super-resolution via attention specialization routing and progressive training, delivering state-of-the-art quality with 6.2x faster inference than prior one-step baselines.
CR-Diff applies block-wise pruning followed by output amplification to diffusion models, improving consistency and fidelity at unseen resolutions while retaining default-resolution performance.
citing papers explorer
-
CoReDiT: Spatial Coherence-Guided Token Pruning and Reconstruction for Efficient Diffusion Transformers
CoReDiT reduces self-attention FLOPs in DiTs by up to 55% via linear-time spatial coherence pruning and neighbor-based reconstruction, delivering 1.33x-1.72x speedups with maintained quality.
-
HERO: Hierarchical Extrapolation and Refresh for Efficient World Models
HERO accelerates world model inference 1.73x via hierarchical patch-wise refresh in shallow layers and linear extrapolation in deeper layers with minimal quality loss.
-
2ndMatch: Finetuning Pruned Diffusion Models via Second-Order Jacobian Matching
2ndMatch finetunes pruned diffusion models via second-order Jacobian matching inspired by Finite-Time Lyapunov Exponents to reduce the quality gap with dense models on image generation tasks.
-
Towards Redundancy Reduction in Diffusion Models for Efficient Video Super-Resolution
OASIS reduces redundancy in diffusion models for real-world video super-resolution via attention specialization routing and progressive training, delivering state-of-the-art quality with 6.2x faster inference than prior one-step baselines.
-
Cross-Resolution Diffusion Models via Network Pruning
CR-Diff applies block-wise pruning followed by output amplification to diffusion models, improving consistency and fidelity at unseen resolutions while retaining default-resolution performance.
- Training-Free Inference for High-Resolution Sinogram Completion