{"ID":2900866,"CreatedAt":"2026-06-01T05:51:17.9442275Z","UpdatedAt":"2026-06-01T06:23:29.641557848Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2605.30925","arxiv_id":"2605.30925","title":"MultiAct: Text-to-Motion Generation from Composite Text via Tailored Attention Guidance","abstract":"Text-to-motion generation has progressed rapidly in recent years, offering an expressive interface for animation and human-computer interaction. However, current models remain brittle when handling prompts that describe multiple actions occurring at the same time. Rather than realizing all components of a composite description, models frequently prioritize a single dominant action and neglect the rest, leading to incomplete or ambiguous motion. We present MultiAct, an unpaired, inference-time framework for compositional text-to-motion synthesis that operates directly on pretrained motion generators without retraining or architectural modification. Our method counteracts semantic collapse by adaptively amplifying cross-attention scores associated with underrepresented prompt components. We note that effective modulation depends on prompt-specific choices, such as which tokens and layers to target, and introduce a lightweight auxiliary decision scheme that determines the most effective attention-strengthening parametrization. Extensive quantitative and qualitative evaluations demonstrate that MultiAct consistently outperforms existing baselines on composite prompts, achieving improved semantic coverage while preserving motion realism. Project page: https://natsala13.github.io/multiact.github.io.","short_abstract":"Text-to-motion generation has progressed rapidly in recent years, offering an expressive interface for animation and human-computer interaction. However, current models remain brittle when handling prompts that describe multiple actions occurring at the same time. Rather than realizing all components of a composite des...","url_abs":"https://arxiv.org/abs/2605.30925","url_pdf":"https://arxiv.org/pdf/2605.30925v1","authors":"[\"Nathan Sala\",\"Ofir Abramovich\",\"Ariel Shamir\",\"Daniel Cohen-Or\",\"Andreas Aristidou\",\"Sigal Raab\"]","published":"2026-05-29T07:14:48Z","proceeding":"cs.CV","tasks":"[\"cs.CV\",\"cs.GR\"]","methods":"[]","has_code":false}