GPC: Large-Scale Generative Pretraining for Transferable Motor Control

Key points

• It learns a discrete motion representation based on Finite Scalar Quantization (FSQ), which avoids the codebook problems of VQ-VAE.
• It models motion tokens with a GPT-style autoregressive transformer using next-token prediction.
• It is trained on a dataset with more than 600 hours of motion data and achieves a 99.98% tracking success rate.
• It shows emergent behaviors such as disturbance recovery and fall recovery strategies.
• It supports adaptation to new tasks through Parameter-Efficient Fine-Tuning (PEFT).
• It is a SIGGRAPH 2026 paper from NVIDIA and Simon Fraser University.

Paper links

External research summaries. These are not HDATF publications or measured product results.