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

arXiv: https://arxiv.org/abs/2609.06651 · HTML: https://mlsanity.com/paper/2609.06651/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Diffusion foundations and sampling, one of 14 directions in Diffusion models.
- Builds on 29 of its 53 references that are in the map.
- First posted on arXiv 6 Sep 2026.

## Placed in

- Diffusion models / [Diffusion foundations and sampling](https://mlsanity.com/diffusion/diffusion-foundations-and-sampling/)
- LLM alignment / RLHF / preference optimisation / [Diffusion and multimodal model alignment](https://mlsanity.com/alignment/diffusion-and-multimodal-model-alignment/)

## Builds on (most cited first, 29 of 29)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [Diffusion Models Beat GANs on Image Synthesis](https://mlsanity.com/paper/2105.05233/) (2021)
- [Hierarchical Text-Conditional Image Generation with CLIP Latents](https://mlsanity.com/paper/2204.06125/) (2022)
- [Improved Techniques for Training GANs](https://mlsanity.com/paper/1606.03498/) (2016)
- [DiffWave: A Versatile Diffusion Model for Audio Synthesis](https://mlsanity.com/paper/2009.09761/) (2020)
- [ImageReward: Learning and Evaluating Human Preferences for Text-to-Image Generation](https://mlsanity.com/paper/2304.05977/) (2023)
- [Training Diffusion Models with Reinforcement Learning](https://mlsanity.com/paper/2305.13301/) (2023)
- [Pick-a-Pic: An Open Dataset of User Preferences for Text-to-Image Generation](https://mlsanity.com/paper/2305.01569/) (2023)
- [GenEval: An Object-Focused Framework for Evaluating Text-to-Image Alignment](https://mlsanity.com/paper/2310.11513/) (2023)
- [Improved Precision and Recall Metric for Assessing Generative Models](https://mlsanity.com/paper/1904.06991/) (2019)
- [WaveGrad: Estimating Gradients for Waveform Generation](https://mlsanity.com/paper/2009.00713/) (2020)
- [GeoDiff: a Geometric Diffusion Model for Molecular Conformation Generation](https://mlsanity.com/paper/2203.02923/) (2022)
- [Inference-Time Scaling for Diffusion Models beyond Scaling Denoising Steps](https://mlsanity.com/paper/2501.09732/) (2025)
- [A General Framework for Inference-time Scaling and Steering of Diffusion Models](https://mlsanity.com/paper/2501.06848/) (2025)
- [Geometric Latent Diffusion Models for 3D Molecule Generation](https://mlsanity.com/paper/2305.01140/) (2023)
- [DiffSinger: Singing Voice Synthesis via Shallow Diffusion Mechanism](https://mlsanity.com/paper/2105.02446/) (2021)
- [Aligning Diffusion Models by Optimizing Human Utility](https://mlsanity.com/paper/2404.04465/) (2024)
- [Inference-Time Alignment of Diffusion Models with Direct Noise Optimization](https://mlsanity.com/paper/2405.18881/) (2024)
- [Inference-time Scaling of Diffusion Models through Classical Search](https://mlsanity.com/paper/2505.23614/) (2025)
- [Diffusion-RPO: Aligning Diffusion Models through Relative Preference Optimization](https://mlsanity.com/paper/2406.06382/) (2024)
- [DyMO: Training-Free Diffusion Model Alignment with Dynamic Multi-Objective Scheduling](https://mlsanity.com/paper/2412.00759/) (2024)
- [ChordEdit: One-Step Low-Energy Transport for Image Editing](https://mlsanity.com/paper/2602.19083/) (2026)
- [Measuring Diversity in Co-creative Image Generation](https://mlsanity.com/paper/2403.13826/) (2024)
- [Manipulating Embeddings of Stable Diffusion Prompts](https://mlsanity.com/paper/2308.12059/) (2023)
- [VideoCoCo: Code-as-CoT for Physically-Consistent Video Generation via an Agentic Dual-Engine System](https://mlsanity.com/paper/2607.27380/) (2026)
- [Do Less, Achieve More: Do We Need Every-Step Optimization for RL Fine-tuning of Diffusion Models?](https://mlsanity.com/paper/2605.15855/) (2026)
- [GenTrack: Physical Alignment for Robot-Native Motion Generation and Zero-Shot Humanoid Tracking](https://mlsanity.com/paper/2608.01410/) (2026)
- [Can We Perform Online RL for Image Editing without Editing Rewards?](https://mlsanity.com/paper/2608.22780/) (2026)

## Abstract (arXiv)

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 address the above challenges, we propose SwiftExplorer, a plugin that mitigates distribution collapse caused by excessive diversity loss and reduces compute costs. First, we adopt an Inheritance-Restart exploration mechanism to avoid early convergence, while exploration also increases the likelihood of high-reward trajectories. Additionally, it balances diversity and fidelity, adding diversity without causing a distribution over-shift. Second, our Quality-Efficiency arbitration mechanism improves guidance by removing incorrect signals, and it reduces computation by dynamically stopping generation when completeness and marginal reward gain are optimal. In an extensive number of experiments and different types of evaluation metrics, the proposed SwiftExplorer achieves excellent performance on all metrics, including preference, fidelity, diversity, and richness.