ARDY: Autoregressive Diffusion with Hybrid Representation for Interactive Human Motion Generation

• URL: http://arxiv.org/abs/2607.08741v1
• Date: Thu, 09 Jul 2026 17:41:49 GMT
• Title: ARDY: Autoregressive Diffusion with Hybrid Representation for Interactive Human Motion Generation
• Abstract summary: offline motion generation approaches offer precise control via text and kinematic constraints, but lack inference speed required for interactive settings.<n>We introduce ARDY, a streaming generation framework that bridges this gap by enabling high-fidelity motion generation controllable via online text prompts and flexible kinematic constraints.<n>We demonstrate ARDY's high motion quality and constraint adherence through an interactive demo featuring dynamic text control, diverse pose constraints, path following, and interactive locomotion via mouse and keyboard.
• Score: 26.662645657689364
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Generating realistic 3D human motions in real-time within interactive applications is key for animation, simulation, and humanoid robotics. While recent offline motion generation approaches offer precise control via text and kinematic constraints, they lack the inference speed required for interactive settings. Conversely, existing online methods enable real-time synthesis but often sacrifice controllability or struggle with complex text semantics and long-horizon goals due to limited context windows. In this work, we introduce ARDY, a streaming generation framework that bridges this gap by enabling high-fidelity motion generation controllable via online text prompts and flexible kinematic constraints. ARDY employs a hybrid representation that combines explicit root features with a latent body embedding, balancing precise trajectory control with efficient generative learning. We propose a two-stage autoregressive transformer denoiser that features variable history context and supports conditioning on flexible, long-horizon kinematic constraints. By training on a large-scale motion capture dataset and being directly conditioned on text labels and kinematic constraints sampled from ground truth poses, ARDY natively learns controllable generation that supports online prompting and flexible long-horizon goals. Extensive evaluations on the HumanML3D benchmark and the large-scale, high-fidelity Bones Rigplay dataset demonstrate ARDY's high motion quality and constraint adherence, validating the efficacy of our key architectural decisions. Finally, we demonstrate the method's practical versatility through an interactive demo featuring dynamic text control, diverse keyframe pose constraints, path following, and interactive locomotion control via mouse and keyboard. Supplementary video results, code, and model releases can be found at https://research.nvidia.com/labs/sil/projects/ardy/.

Related papers

• SparseCtrl-HOI: Sparse Temporal Control for Human-Object Interaction Video Generation [29.683204938136758]
  Human-Object Interaction generation aims to synthesize realistic humans manipulating diverse objects.<n>Existing approaches to this problem rely on dense temporal guidance.<n>We introduce SparseCtrl-HOI, a novel sparse temporal control framework for HOI video generation.
  arXiv  Detail & Related papers  (2026-07-07T08:29:25Z)
• Directing the World: Fast Autoregressive Video Generation with Compositional Human-Camera Control [56.828569670698975]
  "Directing the World" is a fast autoregressive framework for controllable world-model video generation with compositional human-motion and camera-trajectory control.<n>Our key idea is to decouple control learning while preserving a unified autoregressive video prior.<n>For human motion control, we design a t-guided Dynamic Projection mechanism and a refined Motion-CFG strategy.
  arXiv  Detail & Related papers  (2026-06-26T11:08:09Z)
• TEXEDO : Test Time Scaling for Controller-aware Language-conditioned Humanoid Motion Generation [48.72797830886802]
  We introduce TEXEDO, a test-time scaling framework for humanoid motion generation.<n>It improves motion quality without requiring a stronger underlying generator.<n>We show it consistently improves both tracking fidelity and text alignment.
  arXiv  Detail & Related papers  (2026-06-22T08:14:35Z)
• CLAW: Composable Language-Annotated Whole-body Motion Generation [55.99805728566105]
  We present CLAW, a pipeline for scalable generation of language-annotated whole-body motion data.<n>CLAW composes motion primitives from a kinematic planner, parameterized by movement, heading, speed, pelvis height, and duration.<n>A low-level controller tracks these references in MuJoCo simulation, yielding physically grounded trajectories.
  arXiv  Detail & Related papers  (2026-04-13T10:02:04Z)
• QuadFM: Foundational Text-Driven Quadruped Motion Dataset for Generation and Control [18.78068897227934]
  We introduce Quadruped Foundational Motion (QuadFM), the first large-scale, ultra-high-fidelity dataset for text-to-motion generation and general motion control.<n>QuadFM contains 11,784 curated motion clips spanning locomotion, interactive, and emotion-expressive behaviors.<n>We propose Gen2Control RL, a unified framework that jointly trains a general motion controller and a text-to-motion generator.
  arXiv  Detail & Related papers  (2026-03-25T07:30:25Z)
• TextOp: Real-time Interactive Text-Driven Humanoid Robot Motion Generation and Control [62.93681680333618]
  TextOp is a real-time text-driven humanoid motion generation and control framework.<n>It supports streaming language commands and on-the-fly instruction modification during execution.<n>By bridging interactive motion generation with robust whole-body control, TextOp unlocks free-form intent expression.
  arXiv  Detail & Related papers  (2026-02-07T08:42:11Z)
• Towards Robust and Controllable Text-to-Motion via Masked Autoregressive Diffusion [33.9786226622757]
  We propose a robust motion generation framework MoMADiff to generate 3D human motion from text descriptions.<n>Our model supports flexible user-provided specification, enabling precise control over both spatial and temporal aspects of motion synthesis.<n>Our method consistently outperforms state-of-the-art models in motion quality, instruction fidelity, and adherence.
  arXiv  Detail & Related papers  (2025-05-16T09:06:15Z)
• InterDyn: Controllable Interactive Dynamics with Video Diffusion Models [50.38647583839384]
  We propose InterDyn, a framework that generates videos of interactive dynamics given an initial frame and a control signal encoding the motion of a driving object or actor.<n>Our key insight is that large video generation models can act as both neurals and implicit physics simulators'', having learned interactive dynamics from large-scale video data.
  arXiv  Detail & Related papers  (2024-12-16T13:57:02Z)
• Motion Prompting: Controlling Video Generation with Motion Trajectories [57.049252242807874]
  We train a video generation model conditioned on sparse or dense video trajectories.<n>We translate high-level user requests into detailed, semi-dense motion prompts.<n>We demonstrate our approach through various applications, including camera and object motion control, "interacting" with an image, motion transfer, and image editing.
  arXiv  Detail & Related papers  (2024-12-03T18:59:56Z)
• DartControl: A Diffusion-Based Autoregressive Motion Model for Real-Time Text-Driven Motion Control [12.465927271402442]
  Text-conditioned human motion generation allows for user interaction through natural language.<n>DartControl is a Diffusion-based Autoregressive motion primitive model for Real-time Text-driven motion control.<n>Our model effectively learns a compact motion primitive space jointly conditioned on motion history and text inputs.
  arXiv  Detail & Related papers  (2024-10-07T17:58:22Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.