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

• URL: http://arxiv.org/abs/2606.08242v1
• Date: Sat, 06 Jun 2026 15:58:12 GMT
• Title: Light-WAM: Efficient World Action Models with State-Fusion Action Decoding
• Abstract summary: Light-WAM is a lightweight World Action Model for efficient robot manipulation.<n>It is built with a compact video backbone and performs future-video supervision in a downsampled latent space.<n>Experiments demonstrate that Light-WAM maintains strong performance on LIBERO and achieves usable multi-task performance on RoboTwin 2.0.
• Score: 15.384126562001027
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: World Action Models (WAMs) extend robot policy learning by incorporating future prediction as an additional training objective, encouraging the policy to encode task-relevant temporal structure in its representations. Current WAMs often rely on large-scale generative architectures that incur high training costs and inference latency, making them difficult to deploy as efficient closed-loop policies. We propose Light-WAM, a lightweight World Action Model for efficient robot manipulation. Specifically, it is built with a compact video backbone and performs future-video supervision in a downsampled latent space, reducing the cost of video co-training while retaining its benefits for representation learning. For action prediction, Light-WAM introduces the StateFusionActionExpert, which reads adapted states from multiple backbone layers, fuses them through learned-query pooling, and directly predicts action chunks in a single forward pass. This design provides an efficient interface between video backbone representations and robot actions, avoiding the need for heavy generative action experts. Experiments demonstrate that Light-WAM maintains strong performance on LIBERO and achieves usable multi-task performance on RoboTwin 2.0, while using only 0.44B trainable parameters. It also achieves 72.03ms inference latency with 4.1GiB peak GPU memory and improved training throughput.

Related papers

• StreamPI: Streaming Multimodal Temporal Modeling for Vision-Language-Action Models [84.17128030384099]
  StreamPI is a streaming multimodal temporal modeling framework.<n>It equips single-frame VLA with temporal reasoning capability without introducing any additional parameters.<n> Experiments on real-robot tasks spanning memory-dependent and precise perception scenarios, as well as the simulation benchmark LIBERO, demonstrate that StreamPI outperforms pi0.5 across diverse tasks.
  arXiv  Detail & Related papers  (2026-08-26T17:33:19Z)
• GigaWorld-Policy-0.5: A Faster and Stronger WAM Empowered by AutoResearch [66.7936140772745]
  We present GigaWorld-Policy-0.5, an action-centered WAM designed for more efficient robot control.<n>For efficient inference, GigaWorld-Policy-0.5 introduces a Mixture-of-Transformers architecture that separates visual dynamics modeling and action generation into specialized experts.<n>Experiments and ablations show that GigaWorld-Policy-0.5 preserves the training benefits of future visual dynamics while improving inference efficiency for robot control.
  arXiv  Detail & Related papers  (2026-07-15T15:46:42Z)
• Efficient-WAM: A 1B-Parameter World-Action Model with Low-Cost Future Imagination [45.6948544726412]
  World-Action Models (WAMs)couple future visual prediction with action generation.<n>Most existing WAMs rely on future prediction, which incurs high inference latency and makes real-time robot deployment difficult.<n>We introduce Efficient-WAM, a World-Action Model that reduces the cost of future imagination while preserving its control benefit.
  arXiv  Detail & Related papers  (2026-06-08T18:14:08Z)
• GigaWorld-Policy: An Efficient Action-Centered World--Action Model [50.107640832046464]
  GigaWorld-Policy is an action-centered WAM that learns 2D pixel-action dynamics while enabling efficient action decoding, with optional video generation.<n> Experimental results on real-world robotic platforms show that GigaWorld-Policy runs 9x faster than the leading WAM baseline, Motus.
  arXiv  Detail & Related papers  (2026-03-18T00:52:02Z)
• DiT4DiT: Jointly Modeling Video Dynamics and Actions for Generalizable Robot Control [16.562259973551786]
  We introduce DiT4DiT, an end-to-end Video-Action Model that couples a video Diffusion Transformer with an action Diffusion Transformer.<n>Instead of relying on reconstructed future frames, DiT4DiT extracts intermediate denoising features from the video generation process.<n>It achieves state-of-the-art results, reaching average success rates of 98.6% on LIBERO and 50.8% on RoboCasa GR1.
  arXiv  Detail & Related papers  (2026-03-11T06:03:53Z)
• CLAP: Contrastive Latent Action Pretraining for Learning Vision-Language-Action Models from Human Videos [73.51386721543135]
  We propose Contrastive Latent Action Pretraining (CLAP), a framework that aligns the visual latent space from videos with a proprioceptive latent space from robot trajectories.<n>CLAP maps video transitions onto a quantized, physically executable codebook.<n>We introduce a dual-formulation VLA framework offering both CLAP-NTP, an autoregressive model excelling at instruction following and object generalization, and CLAP-RF, a Rectified Flow-based policy designed for high-frequency, precise manipulation.
  arXiv  Detail & Related papers  (2026-01-07T16:26:33Z)
• mimic-video: Video-Action Models for Generalizable Robot Control Beyond VLAs [5.109732854501585]
  We introduce mimic-video, a novel Video-Action Model (VAM) that pairs a pretrained Internet-scale video model with a flow matching-based action decoder conditioned on its latent representations.<n>Our approach achieves state-of-the-art performance on simulated and real-world robotic manipulation tasks, improving sample efficiency by 10x and convergence speed by 2x compared to traditional VLA architectures.
  arXiv  Detail & Related papers  (2025-12-17T18:47:31Z)
• Physical Autoregressive Model for Robotic Manipulation without Action Pretraining [65.8971623698511]
  We build upon autoregressive video generation models to propose a Physical Autoregressive Model (PAR)<n>PAR leverages the world knowledge embedded in video pretraining to understand physical dynamics without requiring action pretraining.<n>Experiments on the ManiSkill benchmark show that PAR achieves a 100% success rate on the PushCube task.
  arXiv  Detail & Related papers  (2025-08-13T13:54:51Z)
• Reinforcement Learning with Action-Free Pre-Training from Videos [95.25074614579646]
  We introduce a framework that learns representations useful for understanding the dynamics via generative pre-training on videos. Our framework significantly improves both final performances and sample-efficiency of vision-based reinforcement learning.
  arXiv  Detail & Related papers  (2022-03-25T19:44:09Z)

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.