# Auto-Conditioned Recurrent Networks for Extended Complex Human Motion Synthesis

arXiv: https://arxiv.org/abs/1707.05363 · HTML: https://mlsanity.com/paper/1707.05363/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 17 Jul 2017.

## Built on by (most cited first, 6 of 6)

- [Robust Motion In-betweening](https://mlsanity.com/paper/2102.04942/) (2021)
- [Real-Time Style Modelling of Human Locomotion via Feature-Wise Transformations and Local Motion Phases](https://mlsanity.com/paper/2201.04439/) (2022)
- [HumanCM: One Step Human Motion Prediction](https://mlsanity.com/paper/2510.16709/) (2025)
- [Unified Simulation, Perception, and Generation of Human Behavior](https://mlsanity.com/paper/2204.13678/) (2022)
- [Invisible Strings: Revealing Latent Dancer-to-Dancer Interactions with Graph Neural Networks](https://mlsanity.com/paper/2503.04816/) (2025)
- [Contact Matrix: Enhancing Dance Motion Synthesis with Precise Interaction Modeling](https://mlsanity.com/paper/2605.04662/) (2026)

## Abstract (arXiv)

We present a real-time method for synthesizing highly complex human motions using a novel training regime we call the auto-conditioned Recurrent Neural Network (acRNN). Recently, researchers have attempted to synthesize new motion by using autoregressive techniques, but existing methods tend to freeze or diverge after a couple of seconds due to an accumulation of errors that are fed back into the network. Furthermore, such methods have only been shown to be reliable for relatively simple human motions, such as walking or running. In contrast, our approach can synthesize arbitrary motions with highly complex styles, including dances or martial arts in addition to locomotion. The acRNN is able to accomplish this by explicitly accommodating for autoregressive noise accumulation during training. Our work is the first to our knowledge that demonstrates the ability to generate over 18,000 continuous frames (300 seconds) of new complex human motion w.r.t. different styles.