# Not all tokens contribute equally to diffusion learning

arXiv: https://arxiv.org/abs/2604.07026 · HTML: https://mlsanity.com/paper/2604.07026/

## 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 32 of its 38 references that are in the map.
- First posted on arXiv 8 Apr 2026.

## Placed in

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

## Builds on (most cited first, 30 of 32)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [Score-Based Generative Modeling through Stochastic Differential Equations](https://mlsanity.com/paper/2011.13456/) (2020)
- [Classifier-Free Diffusion Guidance](https://mlsanity.com/paper/2207.12598/) (2022)
- [Flow Matching for Generative Modeling](https://mlsanity.com/paper/2210.02747/) (2022)
- [Scaling Rectified Flow Transformers for High-Resolution Image Synthesis](https://mlsanity.com/paper/2403.03206/) (2024)
- [Elucidating the Design Space of Diffusion-Based Generative Models](https://mlsanity.com/paper/2206.00364/) (2022)
- [Wan: Open and Advanced Large-Scale Video Generative Models](https://mlsanity.com/paper/2503.20314/) (2025)
- [Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets](https://mlsanity.com/paper/2311.15127/) (2023)
- [CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer](https://mlsanity.com/paper/2408.06072/) (2024)
- [VBench: Comprehensive Benchmark Suite for Video Generative Models](https://mlsanity.com/paper/2311.17982/) (2023)
- [Make-A-Video: Text-to-Video Generation without Text-Video Data](https://mlsanity.com/paper/2209.14792/) (2022)
- [HunyuanVideo: A Systematic Framework For Large Video Generative Models](https://mlsanity.com/paper/2412.03603/) (2024)
- [AnimateDiff: Animate Your Personalized Text-to-Image Diffusion Models without Specific Tuning](https://mlsanity.com/paper/2307.04725/) (2023)
- [Frozen in Time: A Joint Video and Image Encoder for End-to-End Retrieval](https://mlsanity.com/paper/2104.00650/) (2021)
- [CogVideo: Large-scale Pretraining for Text-to-Video Generation via Transformers](https://mlsanity.com/paper/2205.15868/) (2022)
- [Representation Alignment for Generation: Training Diffusion Transformers Is Easier Than You Think](https://mlsanity.com/paper/2410.06940/) (2024)
- [ModelScope Text-to-Video Technical Report](https://mlsanity.com/paper/2308.06571/) (2023)
- [MagicVideo: Efficient Video Generation With Latent Diffusion Models](https://mlsanity.com/paper/2211.11018/) (2022)
- [EvalCrafter: Benchmarking and Evaluating Large Video Generation Models](https://mlsanity.com/paper/2310.11440/) (2023)
- [SANA: Efficient High-Resolution Image Synthesis with Linear Diffusion Transformers](https://mlsanity.com/paper/2410.10629/) (2024)
- [Seedance 1.0: Exploring the Boundaries of Video Generation Models](https://mlsanity.com/paper/2506.09113/) (2025)
- [Video Generation From Text](https://mlsanity.com/paper/1710.00421/) (2017)
- [Make Pixels Dance: High-Dynamic Video Generation](https://mlsanity.com/paper/2311.10982/) (2023)
- [To Create What You Tell: Generating Videos from Captions](https://mlsanity.com/paper/1804.08264/) (2018)
- [Glyph-ByT5: A Customized Text Encoder for Accurate Visual Text Rendering](https://mlsanity.com/paper/2403.09622/) (2024)
- [Rethinking the Spatial Inconsistency in Classifier-Free Diffusion Guidance](https://mlsanity.com/paper/2404.05384/) (2024)
- [Smoothed Energy Guidance: Guiding Diffusion Models with Reduced Energy Curvature of Attention](https://mlsanity.com/paper/2408.00760/) (2024)
- [No Training, No Problem: Rethinking Classifier-Free Guidance for Diffusion Models](https://mlsanity.com/paper/2407.02687/) (2024)

## Abstract (arXiv)

With the rapid development of conditional diffusion models, significant progress has been made in text-to-video generation. However, we observe that these models often neglect semantically important tokens during inference, leading to biased or incomplete generations under classifier-free guidance. We attribute this issue to two key factors: distributional bias caused by the long-tailed token frequency in training data, and spatial misalignment in cross-attention where semantically important tokens are overshadowed by less informative ones. To address these issues, we propose Distribution-Aware Rectification and Spatial Ensemble (DARE), a unified framework that improves semantic guidance in diffusion models from the perspectives of distributional debiasing and spatial consistency. First, we introduce Distribution-Rectified Classifier-Free Guidance (DR-CFG), which regularizes the training process by dynamically suppressing dominant tokens with low semantic density, encouraging the model to better capture underrepresented semantic cues and learn a more balanced conditional distribution. This design mitigates the risk of the model distribution overfitting to tokens with low semantic density. Second, we propose Spatial Representation Alignment (SRA), which adaptively reweights cross-attention maps according to token importance and enforces representation consistency, enabling semantically important tokens to exert stronger spatial guidance during generation. This mechanism effectively prevents low semantic-density tokens from dominating the attention allocation, thereby avoiding the dilution of the spatial and distributional guidance provided by high semantic-density tokens. Extensive experiments on multiple benchmark datasets demonstrate that DARE consistently improves generation fidelity and semantic alignment, achieving significant gains over existing approaches.