# MoCA: Identity-Preserving Text-to-Video Generation via Mixture of Cross Attention

arXiv: https://arxiv.org/abs/2508.03034 · HTML: https://mlsanity.com/paper/2508.03034/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Placed in Video generation, one of 14 directions in Diffusion models.
- Builds on 3 of its 3 references that are in the map.
- First posted on arXiv 5 Aug 2025.

## Placed in

- Diffusion models / [Video generation](https://mlsanity.com/diffusion/video-generation/)

## Builds on (most cited first, 3 of 3)

- [CLIPScore: A Reference-free Evaluation Metric for Image Captioning](https://mlsanity.com/paper/2104.08718/) (2021)
- [A Survey on Video Diffusion Models](https://mlsanity.com/paper/2310.10647/) (2023)
- [State of the Art on Diffusion Models for Visual Computing](https://mlsanity.com/paper/2310.07204/) (2023)

## Built on by (most cited first, 5 of 5)

- [BIFE: Better Interaction, Fewer Errors for Minute-Long Video Generation](https://mlsanity.com/paper/2511.22973/) (2025)
- [Identity-Preserving Image-to-Video Generation via Reward-Guided Optimization](https://mlsanity.com/paper/2510.14255/) (2025)
- [Inferix: A Block-Diffusion based Next-Generation Inference Engine for World Simulation](https://mlsanity.com/paper/2511.20714/) (2025)
- [SocialDirector: Training-Free Social Interaction Control for Multi-Person Video Generation](https://mlsanity.com/paper/2605.10079/) (2026)
- [EverybodyDance: Bipartite Graph-Based Identity Correspondence for Multi-Character Animation](https://mlsanity.com/paper/2512.16360/) (2025)

## Abstract (arXiv)

Achieving ID-preserving text-to-video (T2V) generation remains challenging despite recent advances in diffusion-based models. Existing approaches often fail to capture fine-grained facial dynamics or maintain temporal identity coherence. To address these limitations, we propose MoCA, a novel Video Diffusion Model built on a Diffusion Transformer (DiT) backbone, incorporating a Mixture of Cross-Attention mechanism inspired by the Mixture-of-Experts paradigm. Our framework improves inter-frame identity consistency by embedding MoCA layers into each DiT block, where Hierarchical Temporal Pooling captures identity features over varying timescales, and Temporal-Aware Cross-Attention Experts dynamically model spatiotemporal relationships. We further incorporate a Latent Video Perceptual Loss to enhance identity coherence and fine-grained details across video frames. To train this model, we collect CelebIPVid, a dataset of 10,000 high-resolution videos from 1,000 diverse individuals, promoting cross-ethnicity generalization. Extensive experiments on CelebIPVid show that MoCA outperforms existing T2V methods by over 5% across Face similarity.