CVPR Findings2026
Inference-Time Alignment of Diffusion Models with Evolutionary Algorithms
Purvish Jajal, Nicholas John Eliopoulos, Benjamin Shiue-Hal Chou, George K Thiruvathukal, James C. Davis, Yung-Hsiang Lu
问 Lune
几分钟读透这篇 Paper,不用再花一下午。
Lune 能读完全文,也能读引用它的顶会 Paper,讲清它的结论、证据和局限,每一点都注明出自哪篇 Paper。不用硬啃,也不靠猜。
相关 Paper
- Diffusion Models are Evolutionary AlgorithmsYanbo Zhang, Benedikt Hartl, Hananel Hazan, Michael LevinICLR 2025
- Diffusion Blend: Inference-Time Multi-Preference Alignment for Diffusion ModelsMin Cheng, Fatemeh Doudi, Dileep Kalathil, Mohammad Ghavamzadeh 等ICLR 2026 · 6 次引用
- Efficient Denoising Diffusion via Probabilistic MaskingWeizhong Zhang, Zhiwei Zhang, Renjie Pi, Zhongming Jin 等ICML 2024
- GLASS Flows: Efficient Inference for Reward Alignment of Flow and Diffusion ModelsPeter Holderrieth, Uriel Singer, Tommi Jaakkola, Ricky T. Q. Chen 等ICLR 2026 · 7 次引用
- RAISE: Requirement-Adaptive Evolutionary Refinement for Training-Free Text-to-Image AlignmentLiyao Jiang, Ruichen Chen, Chao Gao, Di NiuCVPR 2026 · 7 次引用
