From Imagined Futures to Executable Actions: Mixture of Latent Actions for Robot Manipulation

From Imagined Futures to Executable Actions: Mixture of Latent Actions for Robot Manipulation

Yajie Li, Bozhou Zhang, Chun Gu, Zipei Ma, Jiahui Zhang, Jiankang Deng, Xiatian Zhu, Li Zhang · · 2026

Framework

N/A

License

N/A

Stars

0

Summary

Video foundation-models models offer a promising imagination mechanism for robot manipulation by predicting long-horizon future observations, but effectively exploiting these imagined futures for action execution remains challenging. Existing approaches...

Abstract Summary

Video foundation-models models offer a promising imagination mechanism for robot manipulation by predicting long-horizon future observations, but effectively exploiting these imagined futures for action execution remains challenging. Existing approaches either condition policies on predicted frames or directly decode generated videos into actions, both suffering from a mismatch between visual realism and control relevance. As a result, predicted observations emphasize perceptual fidelity rather than action-centric causes of state transitions, leading to indirect and unstable control. To address this gap, we propose MoLA (Mixture of Latent Actions), a control-oriented interface that transforms imagined future videos into executable representations. Instead of passing predicted frames directly to the policy, MoLA leverages a mixture of pretrained inverse dynamics models to infer a mixture of latent actions implied by generated visual transitions. These modality-aware inverse dynamics models capture complementary semantic, depth, and flow cues, providing a structured and physically grounded action representation that bridges video imagination and policy execution. We evaluate our approach on simulated benchmarks (LIBERO, CALVIN, and LIBERO-Plus) and real-world robot manipulation tasks, achieving consistent gains in task success, temporal consistency, and generalization.

Key Points

  • Introduces From Imagined Futures to Executable Actions, advancing vla research.
  • Detailed evaluation demonstrates effectiveness on benchmarks and real-world scenarios.
  • Provides insights into methodology and architectural choices.

Abstract

Video foundation-models models offer a promising imagination mechanism for robot manipulation by predicting long-horizon future observations, but effectively exploiting these imagined futures for action execution remains challenging. Existing approaches either condition policies on predicted frames or directly decode generated videos into actions, both suffering from a mismatch between visual realism and control relevance. As a result, predicted observations emphasize perceptual fidelity rather than action-centric causes of state transitions, leading to indirect and unstable control. To address this gap, we propose MoLA (Mixture of Latent Actions), a control-oriented interface that transforms imagined future videos into executable representations. Instead of passing predicted frames directly to the policy, MoLA leverages a mixture of pretrained inverse dynamics models to infer a mixture of latent actions implied by generated visual transitions. These modality-aware inverse dynamics models capture complementary semantic, depth, and flow cues, providing a structured and physically grounded action representation that bridges video imagination and policy execution. We evaluate our approach on simulated benchmarks (LIBERO, CALVIN, and LIBERO-Plus) and real-world robot manipulation tasks, achieving consistent gains in task success, temporal consistency, and generalization.

Share

Related Papers

DynaFLIP: Rethinking Robotics Perception via Tri-Modal-Dynamics Guided Representation

DynaFLIP: Rethinking Robotics Perception via Tri-Modal-Dynamics Guided Representation

Jusuk Lee, Seungjae Lee, Jonghun Shin et al. · arXiv preprint · May 2026

Robot manipulation critically depends on perception that preserves the action-relevant aspects of a scene. Yet most robot learning pipelines are built upon visual encoders pre-trained for static recog

foundation-models perception manipulation representation-learning vla
PDF Intermediate
No code repo Code updated: May 2026