Track papers across labs, topics, and trends.
Search papers, labs, and topics across Lattice.
The paper introduces Text2BFM, a novel text-to-motion (T2M) generation framework that leverages pre-trained Behavioral Foundation Models (BFMs) to decouple semantic planning from motion execution. It uses a text-aligned variational behavioral bottleneck to compress BFM policy-latent sequences into compact motion representations, enabling efficient generation in a learned behavioral manifold. Results demonstrate that Text2BFM achieves robust T2M generation and strong performance on long, compositional textual descriptions by operating in the latent space of a frozen BFM.
Achieve robust text-to-motion generation for long, compositional prompts by planning in the latent space of pre-trained behavioral foundation models, rather than relying on heavy end-to-end motion generators.
Text-to-motion (T2M) generation has broad applications in character animation, virtual avatars, and human-robot interaction. Existing methods typically generate pose trajectories or motion tokens directly from language, forcing a single model to handle semantic interpretation, long-horizon structure, and low-level physical realization. This coupling makes them costly and often unreliable for long, compositional, or semantically dense prompts. We propose Text2BFM, the first framework that aligns natural language with pretrained Behavioral Foundation Models (BFMs) for T2M generation without relying on heavy end-to-end motion generators. Text2BFM operates in the latent policy space of a frozen BFM, using it as an executable motion prior. A text-aligned variational behavioral bottleneck compresses BFM policy-latent sequences into compact motion representations that are compatible with language and preserve long-horizon behavioral structure. Generation is performed in this compact behavioral manifold with a lightweight conditional generator, and the resulting latent encoded behaviors are decoded into policy latents that drive the pretrained frozen BFM. By decoupling semantic planning from motion execution, Text2BFM achieves efficient, robust T2M generation and strong performance on long, compositional textual descriptions.