# AViTS: Adaptive Spatiotemporal Token Selection for Efficient Dynamic-Resolution Generation

arXiv: https://arxiv.org/abs/2608.17995 · HTML: https://mlsanity.com/paper/2608.17995/

## 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 24 of its 28 references that are in the map.
- First posted on arXiv 18 Aug 2026.

## Placed in

- Diffusion models / [Diffusion foundations and sampling](https://mlsanity.com/diffusion/diffusion-foundations-and-sampling/)

## Builds on (most cited first, 24 of 24)

- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Denoising Diffusion Implicit Models](https://mlsanity.com/paper/2010.02502/) (2020)
- [Deep Unsupervised Learning using Nonequilibrium Thermodynamics](https://mlsanity.com/paper/1503.03585/) (2015)
- [Scalable Diffusion Models with Transformers](https://mlsanity.com/paper/2212.09748/) (2022)
- [Generating Long Sequences with Sparse Transformers](https://mlsanity.com/paper/1904.10509/) (2019)
- [Cascaded Diffusion Models for High Fidelity Image Generation](https://mlsanity.com/paper/2106.15282/) (2021)
- [Qwen-Image Technical Report](https://mlsanity.com/paper/2508.02324/) (2025)
- [FLUX.1 Kontext: Flow Matching for In-Context Image Generation and Editing in Latent Space](https://mlsanity.com/paper/2506.15742/) (2025)
- [Q-Diffusion: Quantizing Diffusion Models](https://mlsanity.com/paper/2302.04304/) (2023)
- [Timestep Embedding Tells: It's Time to Cache for Video Diffusion Model](https://mlsanity.com/paper/2411.19108/) (2024)
- [Post-training Quantization on Diffusion Models](https://mlsanity.com/paper/2211.15736/) (2022)
- [Token Merging for Fast Stable Diffusion](https://mlsanity.com/paper/2303.17604/) (2023)
- [Structural Pruning for Diffusion Models](https://mlsanity.com/paper/2305.10924/) (2023)
- [Accelerating Diffusion Transformers with Token-wise Feature Caching](https://mlsanity.com/paper/2410.05317/) (2024)
- [FORA: Fast-Forward Caching in Diffusion Transformer Acceleration](https://mlsanity.com/paper/2407.01425/) (2024)
- [From Reusing to Forecasting: Accelerating Diffusion Models with TaylorSeers](https://mlsanity.com/paper/2503.06923/) (2025)
- [SpeCa: Accelerating Diffusion Transformers with Speculative Feature Caching](https://mlsanity.com/paper/2509.11628/) (2025)
- [Rethinking Token-wise Feature Caching: Accelerating Diffusion Transformers with Dual Feature Caching](https://mlsanity.com/paper/2412.18911/) (2024)
- [Training-free Diffusion Acceleration with Bottleneck Sampling](https://mlsanity.com/paper/2503.18940/) (2025)
- [FreqCa: Accelerating Diffusion Models via Frequency-Aware Caching](https://mlsanity.com/paper/2510.08669/) (2025)
- [A Survey on Cache Methods in Diffusion Models: Toward Efficient Multi-Modal Generation](https://mlsanity.com/paper/2510.19755/) (2025)
- [Training-free Mixed-Resolution Latent Upsampling for Spatially Accelerated Diffusion Transformers](https://mlsanity.com/paper/2507.08422/) (2025)
- [From Sketch to Fresco: Efficient Diffusion Transformer with Progressive Resolution](https://mlsanity.com/paper/2601.07462/) (2026)
- [LESA: Learnable Stage-Aware Predictors for Diffusion Model Acceleration](https://mlsanity.com/paper/2602.20497/) (2026)

## Abstract (arXiv)

Diffusion Transformers (DiTs) achieve high-quality generation but are costly due to iterative sampling. Dynamic-resolution sampling reduces early-stage cost by denoising at low resolution; however, uniformly upsampling all latent tokens at resolution transitions incurs redundant computation and may degrade fine-detail consistency. Existing partial upsampling strategies typically rely on local latent structure cues or single-step statistics, making it difficult to jointly capture token-text semantic relevance and token-wise representation dynamics across diffusion steps. We propose AViTS, an adaptive spatiotemporal token selection framework for dynamic-resolution DiTs. AViTS models spatial importance via latent-text attention and temporal importance via token-level feature variation across diffusion timesteps, and fuses them to enable spatiotemporal importance-aware selective upsampling: it prioritizes resolution refinement for critical tokens while deferring less important ones, thereby reducing redundant high-resolution computation and improving the quality-efficiency trade-off. AViTS achieves up to 6.34x on FLUX and nearly 9x FLOPs reduction on Qwen-Image-Edit and FLUX.1-Kontext-dev, orthogonal to distillation, quantization, and feature caching, and reaching 14.76x with distilled models. Code: https://github.com/QHR69/AViTS