{"ID":2827413,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2512.16234","arxiv_id":"2512.16234","title":"ARMFlow: AutoRegressive MeanFlow for Online 3D Human Reaction Generation","abstract":"3D human reaction generation faces three main challenges:(1) high motion fidelity, (2) real-time inference, and (3) autoregressive adaptability for online scenarios. Existing methods fail to meet all three simultaneously. We propose ARMFlow, a MeanFlow-based autoregressive framework that models temporal dependencies between actor and reactor motions. It consists of a causal context encoder and an MLP-based velocity predictor. We introduce Bootstrap Contextual Encoding (BSCE) in training, encoding generated history instead of the ground-truth ones, to alleviate error accumulation in autoregressive generation. We further introduce the offline variant ReMFlow, achieving state-of-the-art performance with the fastest inference among offline methods. Our ARMFlow addresses key limitations of online settings by: (1) enhancing semantic alignment via a global contextual encoder; (2) achieving high accuracy and low latency in a single-step inference; and (3) reducing accumulated errors through BSCE. Our single-step online generation surpasses existing online methods on InterHuman and InterX by about 30% in FID, while matching offline state-of-the-art performance despite using only partial sequence conditions.","short_abstract":"3D human reaction generation faces three main challenges:(1) high motion fidelity, (2) real-time inference, and (3) autoregressive adaptability for online scenarios. Existing methods fail to meet all three simultaneously. We propose ARMFlow, a MeanFlow-based autoregressive framework that models temporal dependencies be...","url_abs":"https://arxiv.org/abs/2512.16234","url_pdf":"https://arxiv.org/pdf/2512.16234v2","authors":"[\"Zichen Geng\",\"Zeeshan Hayder\",\"Wei Liu\",\"Hesheng Wang\",\"Ajmal Mian\"]","published":"2025-12-18T06:28:42Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[]","has_code":false}