Morse: Dual-Sampling for Lossless Acceleration of Diffusion Models

Chao Li, Jiawei Fan, Anbang Yao
2/14/2026

No official code found. Best implementation: deep-optimization/Morse (11 stars, Apache-2.0, last commit 2025-06-23).

DOISemantic Scholar

Code Implementations(1)

deep-optimization/MorseCommunity68%
Apache-2.0

The official project website of "Morse: Dual-Sampling for Lossless Acceleration of Diffusion Models" (accepted to ICML 2025).

110May 27, 20251 years agoApache-2.0

Similar Papers

ALAM: Averaged Low-Precision Activation for Memory-Efficient Training of Transformer Models

99% match2026

MetaAT: Active Testing for Label-Efficient Evaluation of Dense Recognition Tasks

99% match2026

Intersecting-Boundary-Sensitive Fingerprinting for Tampering Detection of DNN Models

98% match2026

TAU-106K: A New Dataset for Comprehensive Understanding of Traffic Accident

98% match1 repo232026

Inverse M-Kernels for Linear Universal Approximators of Non-Negative Functions

98% match2026

NUDGE: Lightweight Non-Parametric Fine-Tuning of Embeddings for Retrieval

98% match2026

Cite this paper

@article{li2026morse,
  title  = {Morse: Dual-Sampling for Lossless Acceleration of Diffusion Models},
  author = {Chao Li and Jiawei Fan and Anbang Yao},
  year   = {2026},
  doi    = {10.48550/arXiv.2506.18251},
  url    = {https://doi.org/10.48550/arXiv.2506.18251},
  journal = {ICML 2025 2025}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/421e791dfa3c308ee2f25f317efb855be54c4be3.svg)](https://codeofpaper.com/paper/421e791dfa3c308ee2f25f317efb855be54c4be3)

Discussion