SafeMo: Trustworthy Motion Generation

ICLR 2026 Conference Submission15955 Authors

Keywords: motion generation, motion synthesis, synthesis, generative models, diffusion, animation, machine unlearning, AI safety

Abstract: Text-to-motion (T2M) generation with diffusion backbones achieves strong realism and alignment. Safety concerns in T2M methods have been raised in recent years; existing methods replace discrete VQ-VAE codebook entries to steer the model away from unsafe behaviors. However, discrete codebook replacement based methods have two critical flaws: firstly, replacing codebook entries which are reused by benign prompts leads to drifts on everyday tasks, degrading the model’s benign performance; secondly, discrete token-based methods introduce quantization and smoothness loss, resulting in artifacts and jerky transitions. Moreover, existing text-to-motion datasets naturally contain unsafe intents and corresponding motions, making them unsuitable for safety-driven machine learning. To address these challenges, we propose SafeMo, a trustworthy motion generative framework integrating Minimal Motion Unlearning (MMU), a two-stage machine unlearning strategy, enabling safe human motion generation in continuous space, preserving continuous kinematics without codebook loss and delivering strong safety-utility trade-offs compared to current baselines. Additionally, we present the first safe text-to-motion dataset SafeMoVAE-29K integrating rewritten safe text prompts and continuous refined motion for trustworthy human motion unlearning. Built upon CLoSD’s DiP, SafeMo efficiently generates safe human motions with natural transitions. Experiments demonstrate effective unlearning performance of SafeMo, increasing unsafe prompt generation FID by +150.5% and +1344.5% on HumanML3D and Motion-X respectively, with benign performance on safe prompts being better or comparable compared to the previous SOTA human motion unlearning method LCR.

Primary Area: applications to computer vision, audio, language, and other modalities

Submission Number: 15955