# Self-Supervised Flow Matching for Scalable Multi-Modal Synthesis

arXiv: https://arxiv.org/abs/2603.06507 · HTML: https://mlsanity.com/paper/2603.06507/

## Key facts

- Cited by 31 papers in the map (data through 14 Oct 2026).
- Placed in Flow matching, time series and science, one of 14 directions in Diffusion models.
- Builds on 65 of its 79 references that are in the map.
- First posted on arXiv 6 Mar 2026.

## Placed in

- Diffusion models / [Flow matching, time series and science](https://mlsanity.com/diffusion/flow-matching-time-series-and-science/)

## Builds on (most cited first, 30 of 65)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Diffusion Models Beat GANs on Image Synthesis](https://mlsanity.com/paper/2105.05233/) (2021)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [Masked Autoencoders Are Scalable Vision Learners](https://mlsanity.com/paper/2111.06377/) (2021)
- [Emerging Properties in Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.14294/) (2021)
- [Scalable Diffusion Models with Transformers](https://mlsanity.com/paper/2212.09748/) (2022)
- [Flow Matching for Generative Modeling](https://mlsanity.com/paper/2210.02747/) (2022)
- [Bootstrap your own latent: A new approach to self-supervised Learning](https://mlsanity.com/paper/2006.07733/) (2020)
- [RoFormer: Enhanced Transformer with Rotary Position Embedding](https://mlsanity.com/paper/2104.09864/) (2021)
- [Going Deeper with Convolutions](https://mlsanity.com/paper/1409.4842/) (2014)
- [Scaling Rectified Flow Transformers for High-Resolution Image Synthesis](https://mlsanity.com/paper/2403.03206/) (2024)
- [Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flow](https://mlsanity.com/paper/2209.03003/) (2022)
- [Sigmoid Loss for Language Image Pre-Training](https://mlsanity.com/paper/2303.15343/) (2023)
- [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)
- [BEiT: BERT Pre-Training of Image Transformers](https://mlsanity.com/paper/2106.08254/) (2021)
- [Improved Baselines with Momentum Contrastive Learning](https://mlsanity.com/paper/2003.04297/) (2020)
- [GLU Variants Improve Transformer](https://mlsanity.com/paper/2002.05202/) (2020)
- [An Empirical Study of Training Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.02057/) (2021)
- [Context Encoders: Feature Learning by Inpainting](https://mlsanity.com/paper/1604.07379/) (2016)
- [Towards Accurate Generative Models of Video: A New Metric & Challenges](https://mlsanity.com/paper/1812.01717/) (2018)
- [SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Features](https://mlsanity.com/paper/2502.14786/) (2025)
- [Self-Supervised Learning from Images with a Joint-Embedding Predictive Architecture](https://mlsanity.com/paper/2301.08243/) (2023)
- [FLUX.1 Kontext: Flow Matching for In-Context Image Generation and Editing in Latent Space](https://mlsanity.com/paper/2506.15742/) (2025)
- [Building Normalizing Flows with Stochastic Interpolants](https://mlsanity.com/paper/2209.15571/) (2022)
- [SiT: Exploring Flow and Diffusion-based Generative Models with Scalable Interpolant Transformers](https://mlsanity.com/paper/2401.08740/) (2024)
- [Large-scale Contrastive Language-Audio Pretraining with Feature Fusion and Keyword-to-Caption Augmentation](https://mlsanity.com/paper/2211.06687/) (2022)
- [Representation Alignment for Generation: Training Diffusion Transformers Is Easier Than You Think](https://mlsanity.com/paper/2410.06940/) (2024)

## Built on by (most cited first, 30 of 31)

- [Improved Baselines with Representation Autoencoders](https://mlsanity.com/paper/2605.18324/) (2026)
- [D-OPSD: On-Policy Self-Distillation for Continuously Tuning Step-Distilled Diffusion Models](https://mlsanity.com/paper/2605.05204/) (2026)
- [End-to-End Training for Unified Tokenization and Latent Denoising](https://mlsanity.com/paper/2603.22283/) (2026)
- [Denoising, Fast and Slow: Difficulty-Aware Adaptive Sampling for Image Generation](https://mlsanity.com/paper/2604.19141/) (2026)
- [Self-Improving 4D Perception via Self-Distillation](https://mlsanity.com/paper/2604.08532/) (2026)
- [Trajectory Forcing: Structure-First Generation with Controllable Semantic Trajectories](https://mlsanity.com/paper/2606.22527/) (2026)
- [ReWorld: Representation Learning for World Action Models](https://mlsanity.com/paper/2606.27504/) (2026)
- [SANA-Video 2.0: Hybrid Linear Attention with Attention Residuals for Efficient Video Generation](https://mlsanity.com/paper/2607.21553/) (2026)
- [Mask Forcing: Improving Autoregressive Video Diffusion Distillation via Dual-Noise Masking Rollout](https://mlsanity.com/paper/2609.09123/) (2026)
- [Salt++: Context-Aligned Post-Training for Few-Step Streaming Multimodal Generation](https://mlsanity.com/paper/2609.36995/) (2026)
- [Exploring Time Conditioning in Diffusion Generative Models from Disjoint Noisy Data Manifolds](https://mlsanity.com/paper/2604.25289/) (2026)
- [FlowSep 2: Self-Supervised Flow Matching for Language-Queried Audio Source Separation](https://mlsanity.com/paper/2608.22111/) (2026)
- [UniCSG: Unified High-Fidelity Content-Constrained Style-Driven Generation via Staged Semantic and Frequency Disentanglement](https://mlsanity.com/paper/2604.17850/) (2026)
- [AsyncPatch Diffusion: spatially-flexible image generation](https://mlsanity.com/paper/2606.07079/) (2026)
- [From SRA to Self-Flow: Data Augmentation or Self-Supervision?](https://mlsanity.com/paper/2607.02508/) (2026)
- [Where Does Generative Difficulty Reside? An Empirical Study of Target Representations](https://mlsanity.com/paper/2608.00626/) (2026)
- [Drift Variation Autoencoder: Unifying Generation and Representation Learning through Conditional Posterior Flow Matching](https://mlsanity.com/paper/2608.25138/) (2026)
- [An Action Is Worth One Patch: Unified World-Action Modeling with PatchWAM](https://mlsanity.com/paper/2609.25961/) (2026)
- [Learning a Flow to Self-Supervised Representations](https://mlsanity.com/paper/2609.29350/) (2026)
- [RepFlow: Reciprocal Supervision Improves Generation and Representation in Flow Models](https://mlsanity.com/paper/2609.33217/) (2026)
- [Scaffold Then Internalize: Representation Injection for Diffusion Transformers](https://mlsanity.com/paper/2609.35292/) (2026)
- [On the spectral properties of generative denoiser Jacobians](https://mlsanity.com/paper/2609.36210/) (2026)
- [Representation by Design in Generation: Cross-View Class-Token Alignment in Diffusion Transformers](https://mlsanity.com/paper/2609.36348/) (2026)
- [Just Align bmx: Aligning Predictions, Not Representations](https://mlsanity.com/paper/2610.00600/) (2026)
- [DEPICT: Scoring Text-to-Image Alignment by Answer Agreement](https://mlsanity.com/paper/2610.03617/) (2026)
- [ProAR: Learning Prospective Reasoning with Autoregressive Video Models](https://mlsanity.com/paper/2610.03664/) (2026)
- [Learning to Read the Contextual Tokens in Diffusion Transformers](https://mlsanity.com/paper/2610.06844/) (2026)
- [Position Forcing: Self-Conditioning 3D Generation](https://mlsanity.com/paper/2610.10342/) (2026)
- [TRIG: Toward Measuring Texture Realism in Image Generation](https://mlsanity.com/paper/2610.15164/) (2026)
- [MiMaAlign: Hierarchical Micro-Macro Alignment for Physically Plausible Video Generation](https://mlsanity.com/paper/2610.16482/) (2026)

## Abstract (arXiv)

Strong semantic representations improve the convergence and generation quality of diffusion and flow models. Existing approaches largely rely on external models, which require separate training, operate on misaligned objectives, and exhibit unexpected scaling behavior. We argue that this dependence arises from the model's training objective, which poses a denoising task with little incentive to learn semantic representations. We introduce Self-Flow: a self-supervised flow matching paradigm that integrates representation learning within the generative framework. Our key mechanism, Dual-Timestep Scheduling, applies heterogeneous noise levels across tokens, creating an information asymmetry that forces the model to infer missing information from corrupted inputs. This drives learning strong representations alongside generative capabilities without external supervision. Our method generalizes across modalities and enables multi-modal training while following expected scaling laws, achieving superior image, video, and audio generation.