Institution profile

LimX Dynamics

Industry researchasia · cn
Research library9linked papers
Opportunities0open roles
Selected work

Representative Papers

Humanoid World Action Model With Joint State--Action Generation

Oct 08, 2026

This study addresses the discrepancy between reference actions and actual execution in humanoid robots by proposing the HWAM model. For the first time, this work introduces post-execution proprioceptive states as an explicit prediction target, jointly generating reference actions and proprioceptive states via a diffusion model. Furthermore, three complementary conditioning pathways are incorporated to connect actions, states, and visual outcomes, enabling multimodal conditional generation for both forward and inverse dynamics. This architecture explicitly models execution discrepancies to optimize action learning. Experimental evaluations conducted on the LimX OLI humanoid robot demonstrate that the proposed method significantly outperforms baseline approaches, achieving a 70.6% success rate in a candy-picking task.

0 citationsRead paper

ACG-WAM: World-Action Modeling via Action-Conditioned Geometric Latent Prediction

Oct 03, 2026

This study addresses the limitations of existing world action models, which lack explicit geometric supervision and are prone to future information leakage through visual features. We propose ACG-WAM, which introduces an action-conditioned geometric Joint Embedding Predictive Architecture (JEPA) that applies geometric supervision prior to temporal mixing, targeting a frozen VGGT encoder. Furthermore, we pioneer an action-conditioned geometric latent prediction mechanism that eliminates information leakage and enables efficient deployment by removing auxiliary modules during inference. The approach is further enhanced by multi-camera shared visual embeddings for improved representation learning. Extensive evaluations demonstrate that ACG-WAM achieves a 93.46% success rate on the RoboTwin 2.0 benchmark and 85% on real-world robotic tasks, significantly outperforming the Motus baseline.

0 citationsRead paper

Continue, Abort, or Fall: Viability-Aware Policy Selection (VAPS) for Safe Humanoid Acrobatics

Oct 01, 2026

This study addresses the risk of hardware damage in humanoid robots executing highly dynamic motions due to policy failures or external disturbances. We propose VAPS (Viability-based Adaptive Protective Selection), a framework that formulates safety as a receding-horizon decision-making problem. By employing a learned viability predictor to evaluate, in real time, the execution conditions of nominal, abort, and protective falling policies, VAPS constructs a hierarchical decision mechanism that dynamically selects the minimum-cost strategy. Experiments on physical Unitree G1 and LimX Oli platforms demonstrate that VAPS significantly reduces head and hand ground-contact frequencies. The proposed approach achieves a Pareto-optimal balance between task success rate and safety, effectively ensuring hardware integrity during extreme maneuvers.

0 citationsRead paper

Timo: $\textbf{T}$aming Mult$\textbf{i}$modal Diffusion Transformer for Human $\textbf{Mo}$tion Generation

Sep 24, 2026

This study addresses the incoherent motion generation in existing multimodal diffusion models caused by the absence of bidirectional text-motion modeling. To this end, we propose a kinematics-aware framework that integrates a multimodal diffusion Transformer with a flow matching architecture, enabling bidirectional interaction via shared attention mechanisms. Furthermore, geometric rotation supervision and two-stage curriculum learning are introduced to enforce kinematic constraints, effectively mitigating weak joint correlations. We also construct a unified evaluation benchmark encompassing six dimensions. Experimental results demonstrate that the proposed method significantly outperforms existing state-of-the-art approaches, achieving a 40.8% relative improvement in average score and surpassing Kinemo on five of the six evaluated dimensions.

0 citationsRead paper
Recent publications

Latest Papers

Humanoid World Action Model With Joint State--Action Generation

Oct 08, 2026

This study addresses the discrepancy between reference actions and actual execution in humanoid robots by proposing the HWAM model. For the first time, this work introduces post-execution proprioceptive states as an explicit prediction target, jointly generating reference actions and proprioceptive states via a diffusion model. Furthermore, three complementary conditioning pathways are incorporated to connect actions, states, and visual outcomes, enabling multimodal conditional generation for both forward and inverse dynamics. This architecture explicitly models execution discrepancies to optimize action learning. Experimental evaluations conducted on the LimX OLI humanoid robot demonstrate that the proposed method significantly outperforms baseline approaches, achieving a 70.6% success rate in a candy-picking task.

0 citationsRead paper

ACG-WAM: World-Action Modeling via Action-Conditioned Geometric Latent Prediction

Oct 03, 2026

This study addresses the limitations of existing world action models, which lack explicit geometric supervision and are prone to future information leakage through visual features. We propose ACG-WAM, which introduces an action-conditioned geometric Joint Embedding Predictive Architecture (JEPA) that applies geometric supervision prior to temporal mixing, targeting a frozen VGGT encoder. Furthermore, we pioneer an action-conditioned geometric latent prediction mechanism that eliminates information leakage and enables efficient deployment by removing auxiliary modules during inference. The approach is further enhanced by multi-camera shared visual embeddings for improved representation learning. Extensive evaluations demonstrate that ACG-WAM achieves a 93.46% success rate on the RoboTwin 2.0 benchmark and 85% on real-world robotic tasks, significantly outperforming the Motus baseline.

0 citationsRead paper

Continue, Abort, or Fall: Viability-Aware Policy Selection (VAPS) for Safe Humanoid Acrobatics

Oct 01, 2026

This study addresses the risk of hardware damage in humanoid robots executing highly dynamic motions due to policy failures or external disturbances. We propose VAPS (Viability-based Adaptive Protective Selection), a framework that formulates safety as a receding-horizon decision-making problem. By employing a learned viability predictor to evaluate, in real time, the execution conditions of nominal, abort, and protective falling policies, VAPS constructs a hierarchical decision mechanism that dynamically selects the minimum-cost strategy. Experiments on physical Unitree G1 and LimX Oli platforms demonstrate that VAPS significantly reduces head and hand ground-contact frequencies. The proposed approach achieves a Pareto-optimal balance between task success rate and safety, effectively ensuring hardware integrity during extreme maneuvers.

0 citationsRead paper

Timo: $\textbf{T}$aming Mult$\textbf{i}$modal Diffusion Transformer for Human $\textbf{Mo}$tion Generation

Sep 24, 2026

This study addresses the incoherent motion generation in existing multimodal diffusion models caused by the absence of bidirectional text-motion modeling. To this end, we propose a kinematics-aware framework that integrates a multimodal diffusion Transformer with a flow matching architecture, enabling bidirectional interaction via shared attention mechanisms. Furthermore, geometric rotation supervision and two-stage curriculum learning are introduced to enforce kinematic constraints, effectively mitigating weak joint correlations. We also construct a unified evaluation benchmark encompassing six dimensions. Experimental results demonstrate that the proposed method significantly outperforms existing state-of-the-art approaches, achieving a 40.8% relative improvement in average score and surpassing Kinemo on five of the six evaluated dimensions.

0 citationsRead paper