paper-with-me

홈 › Papers

ARMFlow: AutoRegressive MeanFlow for Online 3D Human Reaction Generation

2025-12-18 · Zichen Geng, Zeeshan Hayder, Wei Liu, Hesheng Wang, Ajmal Mian arxiv

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.

📄 PDF Abstract BibTeX arXiv:2512.16234

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Score-Based One-step MeanFlow Policy Optimization

2026-05-22 · Kyungyoon Kim, Donghyeon Ki, Hee-Jun Ahn, Byung-Jun Lee arxiv

Diffusion and flow matching have emerged as expressive policy classes in reinforcement learning, but their reliance on multi-step denoising imposes substantial computational overhead at inference time, which is particula…

Reinforcement Learning

Mean Flow Policy Optimization

2026-04-16 · Xiaoyi Dong, Xi Sheryl Zhang, Jian Cheng arxiv

Diffusion models have recently emerged as expressive policy representations for online reinforcement learning (RL). However, their iterative generative processes introduce substantial training and inference overhead. To …

Reinforcement Learning

Towards Scalable One-Step Generative Modeling for Autoregressive Dynamical System Forecasting

2026-05-07 · Tianyue Yang, Xiao Xue arxiv

Fast surrogate modeling for high-dimensional physical dynamics requires more than low short-term error: useful models must roll out efficiently while preserving the statistical structure of long trajectories. Neural oper…

MeanFlowNFT: Bringing Forward-Process RL to Average-Velocity Generators

2026-07-16 · Yushi Huang, Xiangxin Zhou, Jun Zhang, Liefeng Bo 외 hf

MeanFlow generators achieve fast few-step sampling by predicting average velocities over time intervals, making them attractive for efficient generation. Reinforcement learning (RL) has become a powerful way to align dif…

Reinforcement LearningVideo Generation

FlowerDance: MeanFlow for Efficient and Refined 3D Dance Generation

2025-11-26 · Kaixing Yang, Xulong Tang, Ziqiao Peng, Xiangyue Zhang 외 arxiv

Music-to-dance generation aims to translate auditory signals into expressive human motion, with broad applications in virtual reality, choreography, and digital entertainment. Despite promising progress, the limited gene…