SOURCE-LINKED INTELLIGENCE

SwiftExplorer: Training-free Diffusion Model Alignment with Swift Diversity Exploration

arXiv · AI, language, vision and robotics · article · Sep 6, 2026 · UTC

Diffusion models have general generative abilities but struggle to align with specific objectives. Fine-tuning can improve alignment, yet its training cost is often prohibitive. This led to training-free methods that apply objective-guided terms in sampling to bias the generation distribution toward designated regions, e.g., high-reward areas. However, these methods face two issues: (1) the strong directional bias narrows the pretrained distribution and generation diversity, and (2) indiscriminate constant guidance fails to prune redundant signals, hurting both quality and efficiency. To addre

Read original source ↗ Open in workspace

recordType

paper

region

Global