{"ID":5675293,"CreatedAt":"2026-07-03T01:40:09.565152011Z","UpdatedAt":"2026-07-07T01:06:03.009715918Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2607.01990","arxiv_id":"2607.01990","title":"Training-free Controllable Human Motion Generation under Heterogeneous Constraints","abstract":"Training-free controllable motion generation has attracted growing interest for enabling flexible constraint enforcement without constraint-specific training. However, existing training-free methods require constraints to be continuous objective-based with differentiable losses, while many real-world requirements are criterion-based and provide only discontinuous, sparse, or even black-box feedback. In this paper, we propose Motion-Inference-as-Control (MIC), the first training-free motion generation framework that handles both continuous objective-based and criterion-based motion constraints under a shared mechanism. The key idea is to cast diffusion-based motion generation as a stochastic control problem. This perspective not only provides principled and practically effective step-wise control laws that support criterion-based constraints without requiring differentiability and naturally accommodate objective-based constraints as a special case, but also motivates a control-oriented constraint coordination mechanism that adaptively balances and reconciles motion constraints during generation. Experiments across diverse constraint settings demonstrate the effectiveness of our framework.","short_abstract":"Training-free controllable motion generation has attracted growing interest for enabling flexible constraint enforcement without constraint-specific training. However, existing training-free methods require constraints to be continuous objective-based with differentiable losses, while many real-world requirements are c...","url_abs":"https://arxiv.org/abs/2607.01990","url_pdf":"https://arxiv.org/pdf/2607.01990v1","authors":"[\"Xiaofei Hui\",\"Bo Yan\",\"Haoxuan Qu\",\"Hossein Rahmani\",\"Jun Liu\"]","published":"2026-07-02T10:24:50Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[\"Diffusion Model\"]","has_code":false}