# CaReFlow: Cyclic Adaptive Rectified Flow for Multimodal Fusion

arXiv: https://arxiv.org/abs/2602.19140 · HTML: https://mlsanity.com/paper/2602.19140/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in Image generation, text-to-image and editing, one of 14 directions in Diffusion models.
- Builds on 34 of its 59 references that are in the map.
- First posted on arXiv 22 Feb 2026.

## Placed in

- Diffusion models / [Image generation, text-to-image and editing](https://mlsanity.com/diffusion/image-generation-text-to-image-and-editing/)

## Builds on (most cited first, 30 of 34)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flow](https://mlsanity.com/paper/2209.03003/) (2022)
- [Multimodal Machine Learning: A Survey and Taxonomy](https://mlsanity.com/paper/1705.09406/) (2017)
- [VideoLLaMA 2: Advancing Spatial-Temporal Modeling and Audio Understanding in Video-LLMs](https://mlsanity.com/paper/2406.07476/) (2024)
- [Qwen2.5-Omni Technical Report](https://mlsanity.com/paper/2503.20215/) (2025)
- [Multimodal Transformer for Unaligned Multimodal Language Sequences](https://mlsanity.com/paper/1906.00295/) (2019)
- [Tensor Fusion Network for Multimodal Sentiment Analysis](https://mlsanity.com/paper/1707.07250/) (2017)
- [Efficient Low-rank Multimodal Fusion with Modality-Specific Factors](https://mlsanity.com/paper/1806.00064/) (2018)
- [MISA: Modality-Invariant and -Specific Representations for Multimodal Sentiment Analysis](https://mlsanity.com/paper/2005.03545/) (2020)
- [Learning Modality-Specific Representations with Self-Supervised Multi-Task Learning for Multimodal Sentiment Analysis](https://mlsanity.com/paper/2102.04830/) (2021)
- [Towards Multimodal Sarcasm Detection (An _Obviously_ Perfect Paper)](https://mlsanity.com/paper/1906.01815/) (2019)
- [Memory Fusion Network for Multi-view Sequential Learning](https://mlsanity.com/paper/1802.00927/) (2018)
- [Found in Translation: Learning Robust Joint Representations by Cyclic Translations Between Modalities](https://mlsanity.com/paper/1812.07809/) (2018)
- [UR-FUNNY: A Multimodal Language Dataset for Understanding Humor](https://mlsanity.com/paper/1904.06618/) (2019)
- [Improving Multimodal Fusion with Hierarchical Mutual Information Maximization for Multimodal Sentiment Analysis](https://mlsanity.com/paper/2109.00412/) (2021)
- [Improving the Training of Rectified Flows](https://mlsanity.com/paper/2405.20320/) (2024)
- [Decoupled Multimodal Distilling for Emotion Recognition](https://mlsanity.com/paper/2303.13802/) (2023)
- [Multimodal Information Bottleneck: Learning Minimal Sufficient Unimodal and Multimodal Representations](https://mlsanity.com/paper/2210.17444/) (2022)
- [OmniFlow: Any-to-Any Generation with Multi-Modal Rectified Flows](https://mlsanity.com/paper/2412.01169/) (2024)
- [Modality to Modality Translation: An Adversarial Representation Learning and Graph Fusion Network for Multimodal Fusion](https://mlsanity.com/paper/1911.07848/) (2019)
- [Reliable Conflictive Multi-View Learning](https://mlsanity.com/paper/2402.16897/) (2024)
- [Make Acoustic and Visual Cues Matter: CH-SIMS v2.0 Dataset and AV-Mixup Consistent Module](https://mlsanity.com/paper/2209.02604/) (2022)
- [Hybrid Contrastive Learning of Tri-Modal Representation for Multimodal Sentiment Analysis](https://mlsanity.com/paper/2109.01797/) (2021)
- [CubeMLP: An MLP-based Model for Multimodal Sentiment Analysis and Depression Estimation](https://mlsanity.com/paper/2207.14087/) (2022)
- [Multimodal Learning using Optimal Transport for Sarcasm and Humor Detection](https://mlsanity.com/paper/2110.10949/) (2021)
- [Variational Rectified Flow Matching](https://mlsanity.com/paper/2502.09616/) (2025)
- [Towards Multimodal Sentiment Analysis Debiasing via Bias Purification](https://mlsanity.com/paper/2403.05023/) (2024)
- [DLF: Disentangled-Language-Focused Multimodal Sentiment Analysis](https://mlsanity.com/paper/2412.12225/) (2024)
- [Enriching Multimodal Sentiment Analysis through Textual Emotional Descriptions of Visual-Audio Content](https://mlsanity.com/paper/2412.10460/) (2024)

## Built on by (most cited first, 2 of 2)

- [Reliability-aware Cross-sample Enhancement for Robust Multimodal Sentiment Analysis](https://mlsanity.com/paper/2609.30470/) (2026)
- [InstMoE: Adaptive Multimodal Routing with Specialized Experts](https://mlsanity.com/paper/2610.05111/) (2026)

## Abstract (arXiv)

Modality gap significantly restricts the effectiveness of multimodal fusion. Previous methods often use techniques such as diffusion models and adversarial learning to reduce the modality gap, but they typically focus on one-to-one alignment without exposing the data points of the source modality to the global distribution information of the target modality. To this end, leveraging the characteristic of rectified flow that can map one distribution to another via a straight trajectory, we extend rectified flow for modality distribution mapping. Specifically, we leverage the `one-to-many mapping' strategy in rectified flow that allows each data point of the source modality to observe the overall target distribution. This also alleviates the issue of insufficient paired data within each sample, enabling a more robust distribution transformation. Moreover, to achieve more accurate distribution mapping and address the ambiguous flow directions in one-to-many mapping, we design `adaptive relaxed alignment', enforcing stricter alignment for modality pairs belonging to the same sample, while applying relaxed mapping for pairs not belonging to the same sample or category. Additionally, to prevent information loss during distribution mapping, we introduce `cyclic rectified flow' to ensure the transferred features can be translated back to the original features, allowing multimodal representations to learn sufficient modality-specific information. After distribution alignment, our approach achieves very competitive results on multiple tasks of multimodal affective computing even with a simple fusion method, and visualizations verify that it can effectively reduce the modality gap.