Author

Jinglun Li

h-index 8 View on Semantic Scholar

We have 2 of 21 papers

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

#artificial intelligence Preprint Aug 2026

EpaCache: Error-Propagation-Aware Caching for Accelerating Diffusion-Based Visual Generation

This work introduces Error-Propagation-Aware Cache (EpaCache), a training-free caching policy that adaptively allocates the reuse budget on timesteps with lower downstream impact and consistently improves the latency--fidelity trade-off over existing caching methods.

Yu-Han Liu, Zong-Wei Hong, Jinglun Li et al. · 0 citations

Preprint Aug 2026

SPARE: Structural Parameter-Free Affinity Regularization for Flow Matching

Structural Parameter-free Affinity Regularization (SPARE), a regularizer that matches the pairwise affinities of intermediate tokens to those of the clean latents across images, is proposed, a regularizer that attains the lowest FID among parameter-free regularizers in every tested setting.

Zong-Wei Hong, Jinglun Li, Shen Zhang et al. · 1 citation