Efficient Inference for World Action Models

Overview

World action models predict actions together with how the world may change, and efficient inference studies how to run these models within real-time and memory limits. Approaches include using compact latent, motion, or object representations instead of dense video, distilling models to generate actions in few steps, and reusing cached computations across control cycles. Systems also use pruning, quantization, asynchronous streaming, and adaptive compute, with evaluation on robot manipulation benchmarks such as LIBERO and RoboTwin as well as real robots and navigation tasks. The central tension is that future prediction can aid robustness and long-horizon planning, but generating or reusing it adds cost and can introduce stale or inaccurate information.

Latest papers

CardsList

103 papers26 papers in the last four weeks, down 40% on the four weeks before. 0.2% of all new papers.

  1. C3^3ache: Accelerating World Action Models with Cross Inference Chunk Cache

    Jun 8, 2026Weisen Zhao, Lam Nguyen, Zhicong Lu +1World Model LearningAction-Conditioned World Models

  2. Light-WAM: Efficient World Action Models with State-Fusion Action Decoding

    Jun 6, 2026Ziang Li, Dongzhou Cheng, Yibin Wang +5Robot Policy LearningWorld Models for Robotics

  3. Flash-WAM: Modality-Aware Distillation for World Action Models

    Jun 3, 2026Arman Akbari, Ci Zhang, Arash Akbari +6Video Diffusion ModelsAction-Conditioned World Models

  4. WorldKV: Efficient World Memory with World Retrieval and Compression

    May 21, 2026Jung Yi, Minjae Kim, Paul Hyunbin Cho +3KV CachingMemory-Augmented Video Generation

  5. Motubrain: An Advanced World Action Model for Robot Control

    Apr 30, 2026Motubrain Team, Chendong Xiang, Fan Bao +17Robotic ControlWorld Models for Robotics

  6. Describe-Then-Act: Proactive Agent Steering via Distilled Language-Action World Models

    Mar 24, 2026Massimiliano Pappa, Luca Romani, Valentino Sacco +5Efficient Inference for World Action ModelsAI Agent Safety

  7. Fast-WAM: Do World Action Models Need Test-time Future Imagination?

    Mar 17, 2026Tianyuan Yuan, Zibin Dong, Yicheng Liu +1World Action ModelsEfficient Inference for World Action Models

  8. MWM: Mobile World Models for Action-Conditioned Consistent Prediction

    Mar 8, 2026Han Yan, Zishang Xiang, Zeyu Zhang +1World Models for RoboticsAction-Conditioned World Models

  9. World Action Models are Zero-shot Policies

    Feb 17, 2026Seonghyeon Ye, Yunhao Ge, Kaiyuan Zheng +33World Action ModelsZero-Shot Robotic Manipulation