OmniXtreme: Breaking the Generality Barrier in High-Dynamic Humanoid Control

• URL: http://arxiv.org/abs/2602.23843v1
• Date: Fri, 27 Feb 2026 09:28:06 GMT
• Title: OmniXtreme: Breaking the Generality Barrier in High-Dynamic Humanoid Control
• Abstract summary: High-fidelity motion tracking serves as the litmus test for generalizable, human-level motor skills.<n>Current policies often hit a "generality barrier" as motion libraries scale in diversity.<n>We introduce OmniXtreme, a scalable framework that decouples general motor skill learning from sim-to-real physical skill refinement.
• Score: 41.16304916968901
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: High-fidelity motion tracking serves as the ultimate litmus test for generalizable, human-level motor skills. However, current policies often hit a "generality barrier": as motion libraries scale in diversity, tracking fidelity inevitably collapses - especially for real-world deployment of high-dynamic motions. We identify this failure as the result of two compounding factors: the learning bottleneck in scaling multi-motion optimization and the physical executability constraints that arise in real-world actuation. To overcome these challenges, we introduce OmniXtreme, a scalable framework that decouples general motor skill learning from sim-to-real physical skill refinement. Our approach uses a flow-matching policy with high-capacity architectures to scale representation capacity without interference-intensive multi-motion RL optimization, followed by an actuation-aware refinement phase that ensures robust performance on physical hardware. Extensive experiments demonstrate that OmniXtreme maintains high-fidelity tracking across diverse, high-difficulty datasets. On real robots, the unified policy successfully executes multiple extreme motions, effectively breaking the long-standing fidelity-scalability trade-off in high-dynamic humanoid control.

Related papers

• Extreme-RGMT: Continual Learning of Highly Dynamic Skills for Robust Generalist Humanoid Control [12.247654049983522]
  We introduce Extreme-RGMT, a two-stage continual learning framework for robust generalist humanoid control.<n>Extreme-RGMT learns a generalist motion-tracking base policy from diverse multi-source motion data, then employs an asymmetric skill acquisition and capability consolidation mechanism.<n>Experiments show that Extreme-RGMT achieves state-of-the-art generalist whole-body motion-tracking performance.
  arXiv  Detail & Related papers  (2026-07-22T13:10:22Z)
• A Physics-Grounded Benchmark for Multi-Agent Dynamics in World Models [96.64934195520802]
  We introduce CrashTwin, a physics-grounded evaluation framework designed to stress-test the physical trustworthiness of world models.<n>CrashTwin couples a diverse dataset of multi-agent collision scenarios, comprising 25K controllable synthetic 12K in-the-wild real-world collision sequences.<n>We propose a diagnostic suite that systematically evaluates three dimensions:-temporal consistency, momentum and kinetic energy conservation, and world-dynamics integrity.
  arXiv  Detail & Related papers  (2026-06-27T06:13:35Z)
• OMG: Omni-Modal Motion Generation for Generalist Humanoid Control [30.236954254902614]
  We argue that the key to general-purpose humanoid control is to build a scalable brain, atop a reactive motion tracking system.<n>We present OMG, which addresses two challenges: acquiring a vast amount of high-quality data to achieve general purpose control, and equipping the generator with the capability to condition on compositional, multi-modal inputs.
  arXiv  Detail & Related papers  (2026-06-09T02:46:14Z)
• AnyMo: Scaling Any-Modality Conditional Motion Generation with Masked Modeling [60.13338774249153]
  We introduce OmniHuMo, a dataset of over 5,000 hours of motion and 3.2 million sequences with precisely aligned multimodal annotations.<n>We propose AnyMo, a unified multimodal framework combining a Residual FSQ-based motion tokenizer with a scalable masked modeling transformer.<n>Experiments show that AnyMo achieves high-fidelity synthesis while offering flexible control over both spatial and stylistic attributes.
  arXiv  Detail & Related papers  (2026-05-28T07:15:19Z)
• Unleashing the Agility of Wheeled-Legged Robots for High-Dynamic Reflexive Obstacle Evasion [2.3784505606578916]
  AWARE is a hierarchical reinforcement learning framework for high-dynamic obstacle avoidance in wheeled-legged robots.<n>We show that AWARE achieves robust and agile obstacle avoidance while revealing behaviorally distinct evasive strategies.
  arXiv  Detail & Related papers  (2026-04-26T15:21:33Z)
• RPG: Robust Policy Gating for Smooth Multi-Skill Transitions in Humanoid Fighting [52.18271301977709]
  We propose RPG, a hybrid expert policy framework, for smooth and stable humanoid multi-skills transition.<n>Our approach incorporates motion transition randomization and temporal randomization to train a unified policy that generates agile fighting actions.<n>We design a control pipeline that integrates walking/running locomotion with fighting skills, allowing humanlike long-time combat of arbitrary duration.
  arXiv  Detail & Related papers  (2026-04-23T07:14:35Z)
• ULTRA: Unified Multimodal Control for Autonomous Humanoid Whole-Body Loco-Manipulation [55.467742403416175]
  We introduce a physics-driven neural algorithm that translates large-scale motion capture to humanoid embodiments.<n>We learn a unified multimodal controller that supports both dense references and sparse task specifications.<n>Results show that ULTRA generalizes to autonomous, goal-conditioned whole-body loco-manipulation from egocentric perception.
  arXiv  Detail & Related papers  (2026-03-03T18:59:29Z)
• D-REX: Differentiable Real-to-Sim-to-Real Engine for Learning Dexterous Grasping [66.22412592525369]
  We introduce a real-to-sim-to-real engine that leverages the Gaussian Splat representations to build a differentiable engine.<n>We show that our engine achieves accurate and robust performance in mass identification across various object geometries and mass values.<n>Those optimized mass values facilitate force-aware policy learning, achieving superior and high performance in object grasping.
  arXiv  Detail & Related papers  (2026-03-01T15:32:04Z)
• OmniTrack: General Motion Tracking via Physics-Consistent Reference [54.256312586493415]
  We introduce OmniTrack, a general tracking framework that explicitly decouples physical feasibility from general motion tracking.<n>Experiments show that OmniTrack improves tracking accuracy and demonstrates strong generalization to unseen motions.<n>In real-world tests, OmniTrack achieves hour-long, consistent, and stable tracking, including complex acrobatic motions such as flips and cartwheels.
  arXiv  Detail & Related papers  (2026-02-27T09:12:15Z)
• A Kung Fu Athlete Bot That Can Do It All Day: Highly Dynamic, Balance-Challenging Motion Dataset and Autonomous Fall-Resilient Tracking [5.968082051565195]
  Martial arts are characterized by rapid center-of-mass shifts, complex coordination, and abrupt posture transitions.<n>KungFuAthlete is a high-dynamic martial arts motion dataset derived from professional athletes' daily training videos.<n>We propose a novel training paradigm that enables a single policy to jointly learn high-dynamic motion tracking and fall recovery.
  arXiv  Detail & Related papers  (2026-02-14T07:49:56Z)
• HAIC: Humanoid Agile Object Interaction Control via Dynamics-Aware World Model [56.4392302336014]
  We present HAIC, a framework for robust interaction across diverse object dynamics without external state estimation.<n>Our key contribution is a dynamics predictor that estimates high-order object states (velocity, acceleration) solely from proprioceptive history.<n> Experiments on a humanoid robot show HAIC achieves high success rates in agile tasks.
  arXiv  Detail & Related papers  (2026-02-12T09:34:35Z)
• OmniMotion-X: Versatile Multimodal Whole-Body Motion Generation [52.579531290307926]
  This paper introduces OmniMotion-X, a versatile framework for whole-body human motion generation.<n> OmniMotion-X efficiently supports diverse multimodal tasks, including text-to-motion, music-to-dance, speech-to-gesture.<n>To enable high-quality multimodal training, we construct OmniMoCap-X, the largest unified multimodal motion dataset to date.
  arXiv  Detail & Related papers  (2025-10-22T17:25:33Z)
• KungfuBot2: Learning Versatile Motion Skills for Humanoid Whole-Body Control [30.738592041595933]
  We present VMS, a unified whole-body controller that enables humanoid robots to learn diverse and dynamic behaviors within a single policy.<n>Our framework integrates a hybrid tracking objective that balances local motion fidelity with global trajectory consistency.<n>We validate VMS specialization extensively in both simulation and real-world experiments, demonstrating accurate imitation of dynamic skills, stable performance over minute-long sequences, and strong generalization to unseen motions.
  arXiv  Detail & Related papers  (2025-09-20T11:31:14Z)
• Learning to Move in Rhythm: Task-Conditioned Motion Policies with Orbital Stability Guarantees [45.137864140049814]
  We introduce Orbitally Stable Motion Primitives (OSMPs) - a framework that combines a learned diffeomorphic encoder with a supercritical Hopf bifurcation in latent space.<n>We validate the proposed approach through extensive simulation and real-world experiments across a diverse range of robotic platforms.
  arXiv  Detail & Related papers  (2025-07-12T17:10:03Z)
• AMO: Adaptive Motion Optimization for Hyper-Dexterous Humanoid Whole-Body Control [14.403489342466049]
  We propose a framework that integrates sim-to-real reinforcement learning with trajectory optimization for real-time, adaptive whole-body control.<n>We show that AMO's consistent performance supports autonomous task execution via imitation learning.
  arXiv  Detail & Related papers  (2025-05-06T17:59:51Z)
• CAIMAN: Causal Action Influence Detection for Sample-efficient Loco-manipulation [17.94272840532448]
  We present CAIMAN, a reinforcement learning framework that encourages robots to gain control over other entities in the environment.<n>We empirically demonstrate CAIMAN's superior sample efficiency and adaptability to diverse scenarios in simulation.
  arXiv  Detail & Related papers  (2025-02-02T16:16:53Z)
• First Steps: Latent-Space Control with Semantic Constraints for Quadruped Locomotion [73.37945453998134]
  Traditional approaches to quadruped control employ simplified, hand-derived models. This significantly reduces the capability of the robot since its effective kinematic range is curtailed. In this work, these challenges are addressed by framing quadruped control as optimisation in a structured latent space. A deep generative model captures a statistical representation of feasible joint configurations, whilst complex dynamic and terminal constraints are expressed via high-level, semantic indicators. We validate the feasibility of locomotion trajectories optimised using our approach both in simulation and on a real-worldmal quadruped.
  arXiv  Detail & Related papers  (2020-07-03T07:04:18Z)

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.