# LILAC: Long-sequence Incremental Low-latency Arbitrary Motion Stylization via Streaming VAE-Diffusion with Causal Decoding

arXiv: https://arxiv.org/abs/2510.15392 · HTML: https://mlsanity.com/paper/2510.15392/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 11 of its 14 references that are in the map.
- First posted on arXiv 17 Oct 2025.

## Builds on (most cited first, 11 of 11)

- [T2M-GPT: Generating Human Motion from Textual Descriptions with Discrete Representations](https://mlsanity.com/paper/2301.06052/) (2023)
- [Executing your Commands via Motion Diffusion in Latent Space](https://mlsanity.com/paper/2212.04048/) (2022)
- [Action2Motion: Conditioned Generation of 3D Human Motions](https://mlsanity.com/paper/2007.15240/) (2020)
- [MotionCLIP: Exposing Human Motion Generation to CLIP Space](https://mlsanity.com/paper/2203.08063/) (2022)
- [MotionLCM: Real-time Controllable Motion Generation via Latent Consistency Model](https://mlsanity.com/paper/2404.19759/) (2024)
- [Unpaired Motion Style Transfer from Video to Animation](https://mlsanity.com/paper/2005.05751/) (2020)
- [MotionStreamer: Streaming Motion Generation via Diffusion-based Autoregressive Model in Causal Latent Space](https://mlsanity.com/paper/2503.15451/) (2025)
- [Motion Puzzle: Arbitrary Motion Style Transfer by Body Part](https://mlsanity.com/paper/2202.05274/) (2022)
- [Combining Recurrent Neural Networks and Adversarial Training for Human Motion Synthesis and Control](https://mlsanity.com/paper/1806.08666/) (2018)
- [SMooDi: Stylized Motion Diffusion Model](https://mlsanity.com/paper/2407.12783/) (2024)
- [MotionPCM: Real-Time Motion Synthesis with Phased Consistency Model](https://mlsanity.com/paper/2501.19083/) (2025)

## Abstract (arXiv)

Generating long and stylized human motions in real time is critical for applications that demand continuous and responsive character control. Despite its importance, existing streaming approaches often operate directly in the raw motion space, leading to substantial computational overhead and making it difficult to maintain temporal stability. In contrast, latent-space VAE-Diffusion-based frameworks alleviate these issues and achieve high-quality stylization, but they are generally confined to offline processing. To bridge this gap, LILAC (Long-sequence Incremental Low-latency Arbitrary Motion Stylization via Streaming VAE-Diffusion with Causal Decoding) builds upon a recent high-performing offline framework for arbitrary motion stylization and extends it to an online setting through a latent-space streaming architecture with a sliding-window causal design and the injection of decoded motion features to ensure smooth motion transitions. This architecture enables long-sequence real-time arbitrary stylization without relying on future frames or modifying the diffusion model architecture, achieving a favorable balance between stylization quality and responsiveness as demonstrated by experiments on benchmark datasets. Supplementary video and examples are available at the project page: https://pren1.github.io/lilac/