A training-free speculative decoding method for block-based autoregressive video diffusion uses a quality router on worst-frame ImageReward scores to accept drafter proposals, achieving up to 2.09x speedup at 95.7% quality retention.
T-stitch: Accelerating sampling in pre-trained diffusion models with trajectory stitching
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
representative citing papers
Early and late denoising steps in masked diffusion LMs are robust to smaller-model replacement, enabling 17% FLOPs reduction with modest generative 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.
citing papers explorer
-
Speculative Decoding for Autoregressive Video Generation
A training-free speculative decoding method for block-based autoregressive video diffusion uses a quality router on worst-frame ImageReward scores to accept drafter proposals, achieving up to 2.09x speedup at 95.7% quality retention.
-
Not All Denoising Steps Are Equal: Model Scheduling for Faster Masked Diffusion Language Models
Early and late denoising steps in masked diffusion LMs are robust to smaller-model replacement, enabling 17% FLOPs reduction with modest generative 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.