Pinned
🚀 OBS-Diff is accepted to #ICLR2026!
Thrilled to have my first paper as lead author accepted!
Huge thanks to my supervisor, Prof. Wang (@huanwangx), and everyone at ENCODE LAB for the support!
Let's talk about sparsity and efficiency in Brazil! 🇧🇷☕️
🚀 OBS-Diff
We introduce OBS-Diff: a novel, training-free, one-shot pruning framework for diffusion models, supporting diverse architectures and pruning granularities.
📄 Paper: arxiv.org/abs/2510.06751
💻 Code: github.com/Alrightlone/OB…
🌐 Web: alrightlone.github.io/OBS-Diff-Webpa…
