{"total":45,"items":[{"citing_arxiv_id":"2607.08741","ref_index":45,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"ARDY: Autoregressive Diffusion with Hybrid Representation for Interactive Human Motion Generation","primary_cat":"cs.GR","submitted_at":"2026-07-09T17:41:49+00:00","verdict":"ACCEPT","verdict_confidence":"HIGH","novelty_score":7.0,"formal_verification":"none","one_line_summary":"An autoregressive diffusion model with a hybrid explicit-root/latent-body representation generates real-time, controllable 3D human motion from text and spatial constraints.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2607.07370","ref_index":17,"ref_count":2,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Behavior Foundations for Quadruped Robots: ABot-C0 Technical Report","primary_cat":"cs.RO","submitted_at":"2026-07-08T13:04:07+00:00","verdict":"CONDITIONAL","verdict_confidence":"HIGH","novelty_score":6.0,"formal_verification":"none","one_line_summary":"A multi-source 16,074-clip quadruped motion library plus a flow-matching generalist tracker shows empirical data scaling and zero-shot unseen tracking, integrated with all-terrain locomotion and real-robot deployment.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2607.02034","ref_index":8,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"ComplexMimic: Human-Scene Interaction Imitation in Complex 3D Environments","primary_cat":"cs.CV","submitted_at":"2026-07-02T11:01:20+00:00","verdict":"CONDITIONAL","verdict_confidence":"MODERATE","novelty_score":5.5,"formal_verification":"none","one_line_summary":"Dual-expert RL plus difficulty-aware multi-teacher distillation improves physics-based human–scene interaction imitation under complex 3D geometry versus prior single-policy baselines.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.28476","ref_index":20,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"FADA: Few-Shot Domain Adaptation via Dynamics Alignment for Humanoid Control","primary_cat":"cs.RO","submitted_at":"2026-06-26T16:05:10+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"FADA is a three-stage Planner-IDM method that achieves few-shot domain adaptation for humanoid control by distilling an oracle policy then finetuning only the IDM on short target-domain rollouts via supervised learning.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.27581","ref_index":3,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"SceneBot: Contact-Prompted General Humanoid Whole Body Tracking with Scene-Interaction","primary_cat":"cs.RO","submitted_at":"2026-06-25T22:13:29+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"SceneBot conditions a humanoid tracking policy on motion references and contact labels, using reconstructed scene-interaction data to unify free-space locomotion with contact-rich manipulation and terrain tasks.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.26741","ref_index":33,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"PressMimic: Pressure-Guided Motion Capture and Control for Humanoid Robot Imitation","primary_cat":"cs.RO","submitted_at":"2026-06-25T08:24:35+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"PressMimic fuses RGB and pressure for pose estimation via FRAPPE++ and uses pressure signals in RL policy PSP, backed by the MotionPRO dataset, to achieve physically consistent humanoid motion imitation.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.26201","ref_index":7,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"OmniContact: Chaining Meta-Skills via Contact Flow for Generalizable Humanoid Loco-Manipulation","primary_cat":"cs.RO","submitted_at":"2026-06-24T16:28:23+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"OmniContact introduces contact flow as a shared representation of body trajectories and contact signals to learn and chain loco-manipulation meta-skills, reporting 98.7% success on box carrying and 76.5% on push-stack tasks.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.22860","ref_index":17,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"HiL-ResRL: A Model-Agnostic Finetuning Adapter via Human-in-the-loop Residual Reinforcement Learning","primary_cat":"cs.RO","submitted_at":"2026-06-22T05:07:08+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"HiL-ResRL trains a model-agnostic residual policy on VLA actions using human-guided online RL, achieving over 95% success rate after 1.5 hours of real-robot training.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.12814","ref_index":23,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Stubborn: A Streamlined and Unified Reinforcement Learning Framework for Robust Motion Tracking and Fall Recovery for Humanoids","primary_cat":"cs.RO","submitted_at":"2026-06-11T02:13:53+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Stubborn introduces a unified RL framework with yaw-aligned representation, Bernoulli probabilistic termination, and adaptive sampling for robust humanoid motion tracking and fall recovery.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.12783","ref_index":21,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"A Tutorial on World Models and Physical AI","primary_cat":"cs.AI","submitted_at":"2026-06-11T00:52:39+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":2.0,"formal_verification":"none","one_line_summary":"A tutorial that unifies explicit and implicit world models through shared predictive structure for applications in physical AI such as robotics.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.09286","ref_index":17,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"VAIC: Vision-Guided Humanoid Agile Object Interaction Control via Decoupled Commands","primary_cat":"cs.RO","submitted_at":"2026-06-08T09:52:55+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"VAIC distills a teacher policy into a vision-and-proprioception student policy using recurrent adaptation and decoupled commands, enabling diverse real-robot tasks like box carrying and skateboarding that outperform baselines.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.08555","ref_index":50,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"FAWAM: Force-Aware World Action Models for Closed-Loop Contact-Rich Manipulation","primary_cat":"cs.RO","submitted_at":"2026-06-07T10:26:03+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"FAWAM integrates force signals into perception, prediction, and closed-loop correction, raising success rates 36% over vision baselines in contact-rich manipulation tasks.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.08495","ref_index":5,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"EgoPriMo: Egocentric Motion Generation for Interactive Humanoid Control","primary_cat":"cs.RO","submitted_at":"2026-06-07T07:49:19+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"EgoPriMo learns a unified egocentric motion prior with a Triple-stream DiT model that supports reconstruction, generation, and forecasting of SMPL motions from egocentric views and text, outperforming prior methods and transferable to humanoid controllers.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.08059","ref_index":45,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Perceptive Behavior Foundation Model: Adapting Human Motion Priors to Robot-Centric Terrain","primary_cat":"cs.RO","submitted_at":"2026-06-06T08:46:44+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Perceptive BFM grounds human motion priors in robot terrain perception via terrain-conformal reference synthesis and teacher-student transfer from adapted to raw-reference tracking.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.07934","ref_index":12,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"X-OP: Cross-Morphology Whole-Body Teleoperation via MPC Retargeting","primary_cat":"cs.RO","submitted_at":"2026-06-06T01:50:59+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"MPC-based retargeting framework enables cross-morphology whole-body teleoperation from a single XR device via dynamic feasibility optimization, state synchronization, and SLAM feedback, with reported gains in simulation and real-world tests.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.07118","ref_index":35,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"QuadVerse: An Integrated Framework Aligning Visual-Physical Reality for Quadruped Simulation","primary_cat":"cs.RO","submitted_at":"2026-06-05T10:18:24+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"QuadVerse integrates 3D Gaussian Splatting scene reconstruction, friction calibration via trajectory search, and a residual dynamics compensator to improve quadruped simulation fidelity and enable zero-shot policy transfer.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.06218","ref_index":43,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"TAM: Torque Adaptation Module for Robust Motion Transfer in Manipulation","primary_cat":"cs.RO","submitted_at":"2026-06-04T14:31:54+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"TAM is a policy-agnostic torque adaptation module trained in randomized simulation that improves zero-shot real-robot performance on dynamic manipulation tasks compared to system identification and RMA baselines.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.04829","ref_index":25,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"M3imic: Learning a Versatile Whole-Body Controller for Multimodal Motion Mimicking","primary_cat":"cs.RO","submitted_at":"2026-06-03T12:52:37+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"M3imic unifies heterogeneous motion modalities via encoders into a shared latent space for a single RL-trained whole-body controller achieving high sim success and sim-to-real transfer on Unitree G1.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.03985","ref_index":11,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Humanoid-GPT: Scaling Data and Structure for Zero-Shot Motion Tracking","primary_cat":"cs.RO","submitted_at":"2026-06-02T17:59:05+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"Humanoid-GPT is a causal Transformer pre-trained on a unified billion-scale motion dataset that tracks dynamic behaviors with zero-shot generalization to unseen motions and tasks.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.03536","ref_index":37,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Bionic Human-Motion Style Transfer for Physically Executable Whole-Body Control of Humanoid Robots","primary_cat":"cs.RO","submitted_at":"2026-06-02T11:59:01+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"A multi-condition latent diffusion model transfers human motion styles to diverse humanoid robot contents with physics regularizations, achieving 96% success in real-robot trials on Unitree G1.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.30313","ref_index":25,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"UniLab: A Heterogeneous Architecture for Robot RL Beyond GPU-Dominant Paradigms","primary_cat":"cs.RO","submitted_at":"2026-05-28T17:53:50+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"UniLab is a CPU/GPU heterogeneous system for robot RL training using MuJoCoUni and MotrixSim backends that reports 3-10x end-to-end efficiency improvements and cross-platform compatibility beyond CUDA.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.28549","ref_index":6,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"SPRINT: Efficient Spectral Priors for Humanoid Athletic Sprints","primary_cat":"cs.RO","submitted_at":"2026-05-27T14:40:29+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"SPRINT generates sprint trajectories for humanoids via spectral priors from five human motion sequences, achieving 6 m/s peak velocity with zero-shot sim-to-real transfer on Unitree G1.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.27046","ref_index":16,"ref_count":2,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Learning to Balance Motor Thermal Safety and Quadrupedal Locomotion Performance with Residual Policy","primary_cat":"cs.RO","submitted_at":"2026-05-26T14:00:10+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"A thermal residual policy on a pre-trained quadruped locomotion controller prevents motor overheating under payload while preserving performance, lasting over 13 minutes on a Unitree A1 versus ~5 minutes for the nominal policy.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.26879","ref_index":13,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Natural Human Motion Recovery by Aligning High-Order Temporal Dynamics from Monocular Videos","primary_cat":"cs.CV","submitted_at":"2026-05-26T11:38:36+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":4.0,"formal_verification":"none","one_line_summary":"HTD-Refine uses a temporal transformer (PVA-Net) to predict high-order dynamics and refines HMR outputs via optimization for more natural motion.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.25782","ref_index":21,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"ParkourFormer: Integrating Predictive Supervision and Sequence Modeling into Parkour Locomotion","primary_cat":"cs.RO","submitted_at":"2026-05-25T12:29:47+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"ParkourFormer achieves 93.85% average success on multi-terrain humanoid parkour by fusing Transformer sequence modeling with supervised future-state prediction.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.24592","ref_index":53,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"MuGen: Multi-Skill Generative Locomotion Controller for Humanoid Robots","primary_cat":"cs.RO","submitted_at":"2026-05-23T14:06:06+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"MuGen learns a generative latent representation of multi-skill humanoid locomotion from heterogeneous human data using VQ-VAEs and RL, then distills a deployable policy that tracks unseen motions and reuses the latent space.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.22272","ref_index":24,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Imagine2Real: Towards Zero-shot Humanoid-Object Interaction via Video Generative Priors","primary_cat":"cs.RO","submitted_at":"2026-05-21T10:15:39+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Imagine2Real enables zero-shot humanoid-object interaction by unifying motions as 4D point trajectories, tracking only base/hands/object keypoints inside a BFM latent space, and training with progressive simple rewards for mocap deployment.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.05110","ref_index":26,"ref_count":2,"confidence":0.9,"is_internal_anchor":false,"paper_title":"LineRides: Line-Guided Reinforcement Learning for Bicycle Robot Stunts","primary_cat":"cs.RO","submitted_at":"2026-05-06T16:43:28+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"LineRides enables commandable bicycle robot stunts via line-guided RL that uses spatial guidelines, a tracking margin for feasibility, distance-based progress, and sparse key-orientations.","context_count":1,"top_context_role":"background","top_context_polarity":"background","context_text":"M. Kitani, C. Liu, and G. Shi, \"Omnih2o: Universal and dexterous human-to- humanoid whole-body teleoperation and learning,\" inConference on Robot Learning. PMLR, 2025, pp. 1516-1540. [25] Z. Chen, M. Ji, X. Cheng, X. Peng, X. B. Peng, and X. Wang, \"Gmt: General motion tracking for humanoid whole-body control,\"arXiv preprint arXiv:2506.14770, 2025. [26] T. He, J. Gao, W. Xiao, Y . Zhang, Z. Wang, J. Wang, Z. Luo, G. He, N. Sobanbab, C. Panet al., \"Asap: Aligning simulation and real-world physics for learning agile humanoid whole-body skills,\"arXiv preprint arXiv:2502.01143, 2025. [27] Z. Li, X. B. Peng, P. Abbeel, S. Levine, G. Berseth, and K. Sreenath, \"Reinforcement learning for versatile, dynamic, and robust bipedal"},{"citing_arxiv_id":"2605.03452","ref_index":33,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"BifrostUMI: Bridging Robot-Free Demonstrations and Humanoid Whole-Body Manipulation","primary_cat":"cs.RO","submitted_at":"2026-05-05T07:35:09+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"BifrostUMI enables robot-free human demonstration capture via VR and wrist cameras to train visuomotor policies that predict keypoint trajectories for transfer to humanoid whole-body control through retargeting.","context_count":1,"top_context_role":"method","top_context_polarity":"use_method","context_text":"track complex full-body motions and transfer the learned be- haviors from simulation to real hardware [29]-[32]. Inspired by these advances, we design our own learned whole-body controller (WBC) as the execution layer of BifrostUMI. After the desired robot motion is obtained by SKR and inverse kinematics, it is executed by the WBC trained in MJLab [33]. The WBC tracks a short horizon of robot-native full-body reference motion, consisting of the root pose and the 29-DoF joint configuration, while maintaining dynamic consistency and robustness to sim-to-real discrepancies. At each high-level update, the reference motion is repre- sented as a motion chunk Mref = n pr t ,q r t ,q j t oT t=1 ,(2) wherep r"},{"citing_arxiv_id":"2605.01518","ref_index":17,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"VOFA: Visual Object Goal Pushing with Force-Adaptive Control for Humanoids","primary_cat":"cs.RO","submitted_at":"2026-05-02T16:16:23+00:00","verdict":"CONDITIONAL","verdict_confidence":"MODERATE","novelty_score":6.0,"formal_verification":"none","one_line_summary":"VOFA combines a depth-image visuomotor policy with a force-adaptive whole-body controller to push objects of unknown mass to arbitrary goals on a humanoid.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.25459","ref_index":16,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"GS-Playground: A High-Throughput Photorealistic Simulator for Vision-Informed Robot Learning","primary_cat":"cs.RO","submitted_at":"2026-04-28T10:05:39+00:00","verdict":null,"verdict_confidence":null,"novelty_score":null,"formal_verification":null,"one_line_summary":null,"context_count":1,"top_context_role":"other","top_context_polarity":"unclear","context_text":"InProceedings of the Computer Vision and Pattern Recognition Conference, pages 21537-21546, 2025. [15] Alex Hanson, Allen Tu, Vasu Singla, Mayuka Jayaward- hana, Matthias Zwicker, and Tom Goldstein. Pup 3d-gs: Principled uncertainty pruning for 3d gaussian splatting. InProceedings of the Computer Vision and Pattern Recognition Conference, pages 5949-5958, 2025. [16] Tairan He, Jiawei Gao, Wenli Xiao, Yuanhang Zhang, Zi Wang, Jiashun Wang, Zhengyi Luo, Guanqi He, Nikhil Sobanbab, Chaoyi Pan, et al. Asap: Aligning simula- tion and real-world physics for learning agile humanoid whole-body skills.arXiv preprint arXiv:2502.01143, 2025. [17] Tairan He, Zi Wang, Haoru Xue, Qingwei Ben, Zhengyi Luo, Wenli Xiao, Ye Yuan, Xingye Da, Fernando"},{"citing_arxiv_id":"2604.21355","ref_index":13,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"RPG: Robust Policy Gating for Smooth Multi-Skill Transitions in Humanoid Fighting","primary_cat":"cs.RO","submitted_at":"2026-04-23T07:14:35+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":4.0,"formal_verification":"none","one_line_summary":"RPG trains a unified humanoid robot policy using motion and temporal randomization to achieve smooth, stable transitions between fighting skills and locomotion.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.21351","ref_index":3,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Learn Weightlessness: Imitate Non-Self-Stabilizing Motions on Humanoid Robot","primary_cat":"cs.RO","submitted_at":"2026-04-23T07:10:05+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"A weightlessness mechanism enables humanoid robots to dynamically relax joints for stable, contact-rich motions across diverse environments without task-specific tuning.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.20841","ref_index":12,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"DeVI: Physics-based Dexterous Human-Object Interaction via Synthetic Video Imitation","primary_cat":"cs.CV","submitted_at":"2026-04-22T17:59:55+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"DeVI enables zero-shot physically plausible dexterous control by imitating synthetic videos via a hybrid 3D-human plus 2D-object tracking reward.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.14834","ref_index":2,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Switch: Learning Agile Skills Switching for Humanoid Robots","primary_cat":"cs.RO","submitted_at":"2026-04-16T10:11:28+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"Switch enables humanoid robots to perform agile, seamless transitions between locomotion skills via a kinematic skill graph, DRL tracking policy, and real-time graph-search scheduler.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.10351","ref_index":37,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Trajectory-based actuator identification via differentiable simulation","primary_cat":"cs.RO","submitted_at":"2026-04-11T21:36:34+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Differentiable simulation enables torque-sensor-free actuator model identification from trajectory data, achieving 1.88x better position tracking than a stand-trained baseline and 46% longer travel in downstream locomotion policies.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.07331","ref_index":10,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"RoSHI: A Versatile Robot-oriented Suit for Human Data In-the-Wild","primary_cat":"cs.RO","submitted_at":"2026-04-08T17:48:46+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"RoSHI is a hybrid wearable that combines sparse IMUs and egocentric SLAM to capture accurate full-body 3D pose and shape data in natural environments for robot learning.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2602.11758","ref_index":14,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"HAIC: Humanoid Agile Object Interaction Control via Dynamics-Aware World Model","primary_cat":"cs.RO","submitted_at":"2026-02-12T09:34:35+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"HAIC enables robust humanoid interactions with underactuated objects by predicting their dynamics from proprioceptive history and using a world model for adaptive control.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2602.03205","ref_index":13,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"HUSKY: Humanoid Skateboarding System via Physics-Aware Whole-Body Control","primary_cat":"cs.RO","submitted_at":"2026-02-03T07:18:01+00:00","verdict":"CONDITIONAL","verdict_confidence":"MODERATE","novelty_score":6.0,"formal_verification":"none","one_line_summary":"HUSKY combines humanoid-skateboard dynamics modeling with adversarial motion priors and physics-guided lean-to-steer strategies to achieve real-world stable skateboarding on a humanoid robot.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2601.14617","ref_index":9,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"UniCon: A Unified System for Efficient Robot Learning Transfers","primary_cat":"cs.RO","submitted_at":"2026-01-21T03:19:32+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"UniCon standardizes states and control logic into modular execution graphs for efficient transfer of learning controllers across heterogeneous robots, with lower latency than ROS.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2512.06571","ref_index":33,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Learning Agile Striker Skills for Humanoid Soccer Robots from Noisy Sensory Input","primary_cat":"cs.RO","submitted_at":"2025-12-06T21:27:50+00:00","verdict":"CONDITIONAL","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"A four-stage RL system with teacher-student distillation and online constrained adaptation enables humanoid robots to achieve robust ball-kicking accuracy under noisy perception in simulation and on physical hardware.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2511.22963","ref_index":14,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Commanding Humanoid by Free-form Language: A Large Language Action Model with Unified Motion Vocabulary","primary_cat":"cs.RO","submitted_at":"2025-11-28T08:11:24+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Humanoid-LLA converts unconstrained natural language commands into stable whole-body motions for humanoid robots using a unified motion vocabulary and two-stage supervised-plus-reinforcement fine-tuning.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2511.07820","ref_index":16,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"SONIC: Supersizing Motion Tracking for Natural Humanoid Whole-Body Control","primary_cat":"cs.RO","submitted_at":"2025-11-11T04:37:40+00:00","verdict":null,"verdict_confidence":null,"novelty_score":null,"formal_verification":null,"one_line_summary":null,"context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2510.25241","ref_index":8,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"One-shot Adaptation of Humanoid Whole-body Motion with Walking Priors","primary_cat":"cs.RO","submitted_at":"2025-10-29T07:48:10+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"A one-shot adaptation technique for humanoid whole-body motion that computes order-preserving optimal transport distances between walking and target sequences, interpolates geodesic intermediate poses, optimizes for collision-free retargeting, and adapts via reinforcement learning.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2508.08241","ref_index":33,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"BeyondMimic: From Motion Tracking to Versatile Humanoid Control via Guided Diffusion","primary_cat":"cs.RO","submitted_at":"2025-08-11T17:55:26+00:00","verdict":"CONDITIONAL","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"BeyondMimic combines compact motion tracking with a unified guided latent diffusion model to master diverse agile behaviors from human demos and solve unseen downstream tasks via test-time classifier guidance.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null}],"limit":50,"offset":0}