WALL-SS: Scaling Long-horizon World Models via Next-Scale Autoregression

• URL: http://arxiv.org/abs/2608.26239v1
• Date: Wed, 26 Aug 2026 17:57:12 GMT
• Title: WALL-SS: Scaling Long-horizon World Models via Next-Scale Autoregression
• Abstract summary: Generative world models provide robots with predictive models of how the world evolves under interaction.<n>We introduce WALL-SS, a world model that generates visual futures through Scale-wise autoregressive Scaling.<n>We show that WALL-SS improves action following and trajectory accuracy, supports coherent minute-long streaming rollout under bounded memory, and consistently benefits from on-policy alignment.
• Score: 24.010807495676605
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Generative world models provide robots with predictive models of how the world evolves under interaction, with growing potential for simulation, planning, policy evaluation, and robot learning. Beyond clip-level future prediction, a unified generative formulation should relate actions to consequences, support flexible horizons and continuous interaction, and enable reward-driven optimization. We introduce WALL-SS, a world model that generates visual futures through Scale-wise autoregressive Scaling, enabling action-controllable and long-horizon robotic simulation. WALL-SS represents embodied trajectories as causal sequences of temporally interleaved observations and actions, making action-dependent state transitions explicit while naturally supporting variable-length generation, streaming extension through reusable causal states, and direct optimization through sequence probabilities. To make this formulation effective over long horizons, we generate each future observation in a coarse-to-fine manner and develop three complementary components within the same hierarchy. Action-conditioned next-scale prediction injects scale-aligned action representations to improve action-future coupling and model both successful and failed behaviors. Scale-compressed long-horizon memory retains recent interactions at fine resolution while compressing distant observations and actions, with scale-wise dream forcing enhancing robustness to self-generated context. Finally, on-policy alignment optimizes autoregressive visual dynamics with action-following and long-term consistency rewards while preserving the pretrained visual distribution. Experiments show that WALL-SS improves action following and trajectory accuracy, supports coherent minute-long streaming rollout under bounded memory, and consistently benefits from on-policy alignment in reducing action drift and long-horizon inconsistency.

Related papers

• Drive-HWM: Hierarchical World Models for Dynamic-Latent Guided Autonomous Driving [78.83165764484562]
  Drive-HWM is a hierarchical slow--fast world modeling framework that organizes future representation prediction and action generation at complementary temporal scales.<n>Next-frame prediction encourages the fast model to capture imminent scene evolution, while one-step action generation allows decisions to be continuously updated as new observations arrive.
  arXiv  Detail & Related papers  (2026-09-03T09:21:19Z)
• SLIM-0.5B: Learning Action-Grounded Predictive Latents for Robot Manipulation [35.54319311306262]
  We present SLIM, a compact latent interaction policy.<n>It learns representations through self-supervised masked trajectory prediction.<n>SLIM matches or exceeds representative large-scale VLA and world-action-model baselines with fewer parameters.
  arXiv  Detail & Related papers  (2026-08-10T15:58:39Z)
• ActSWM: Action-Sensitive World Models for Long-Horizon Planning in Open-World Games [6.8149466180197]
  We propose ActSWM, an action-sensitive latent world model grounded in a transition-separation principle.<n>Across step-drift analysis, closed-loop Minecraft planning, and cross-game local action recovery, ActSWM preserves larger action-dependent rollout gaps than existing baselines.
  arXiv  Detail & Related papers  (2026-07-29T09:55:54Z)
• ForgeDrive: Bidirectional Cross-Conditioning for Unified Visual-Action Generation in Autonomous Driving [12.68658021226119]
  We introduce ForgeDrive, a unified autoregressive diffusion framework with visual-action cross-conditioning.<n>We find that ForgeDrive not only unifies driving simulation, planning, and visual odometry into a single model, but also outperforms existing strong planners without any post-training strategy.
  arXiv  Detail & Related papers  (2026-06-30T07:05:48Z)
• From Imagined Futures to Executable Actions: Mixture of Latent Actions for Robot Manipulation [88.39072412680633]
  We propose MoLA, a control-oriented interface that transforms imagined future videos into executable representations.<n>We evaluate our approach on simulated benchmarks and real-world robot manipulation tasks.
  arXiv  Detail & Related papers  (2026-05-12T14:15:16Z)
• SPIRAL: A Closed-Loop Framework for Self-Improving Action World Models via Reflective Planning Agents [135.00390535239129]
  We introduce SPIRAL, a self-improving planning and iterative reflective action world modeling framework.<n> SPIRAL formulates ActWM as a closed-loop think-act-reflect process, where generation proceeds step by step under explicit planning and feedback.<n> Experiments across multiple TI2V backbones demonstrate consistent gains on ActWM-Bench and mainstream video generation benchmarks.
  arXiv  Detail & Related papers  (2026-03-09T14:00:36Z)
• Self-Correcting VLA: Online Action Refinement via Sparse World Imagination [55.982504915794514]
  We propose Self-Correcting VLA (SC-VLA), which achieve self-improvement by intrinsically guiding action refinement through sparse imagination.<n>SC-VLA achieve state-of-the-art performance, yielding the highest task throughput with 16% fewer steps and a 9% higher success rate than the best-performing baselines.
  arXiv  Detail & Related papers  (2026-02-25T06:58:06Z)
• Astra: General Interactive World Model with Autoregressive Denoising [73.6594791733982]
  Astra is an interactive general world model that generates real-world futures for diverse scenarios.<n>We propose an autoregressive denoising architecture and use temporal causal attention to aggregate past observations.<n>Astra achieves interactive, consistent, and general long-term video prediction and supports various forms of interactions.
  arXiv  Detail & Related papers  (2025-12-09T18:59:57Z)
• SAMPO:Scale-wise Autoregression with Motion PrOmpt for generative world models [42.814012901180774]
  textbfSAMPO is a hybrid framework that combines visual autoregressive modeling for intra-frame generation with causal modeling for next-frame generation.<n>We show that SAMPO achieves competitive performance in action-conditioned video prediction and model-based control.<n>We also evaluate SAMPO's zero-shot generalization and scaling behavior, demonstrating its ability to generalize to unseen tasks.
  arXiv  Detail & Related papers  (2025-09-19T02:41:37Z)
• Dita: Scaling Diffusion Transformer for Generalist Vision-Language-Action Policy [73.75271615101754]
  We present Dita, a scalable framework that leverages Transformer architectures to directly denoise continuous action sequences.<n>Dita employs in-context conditioning -- enabling fine-grained alignment between denoised actions and raw visual tokens from historical observations.<n>Dita effectively integrates cross-embodiment datasets across diverse camera perspectives, observation scenes, tasks, and action spaces.
  arXiv  Detail & Related papers  (2025-03-25T15:19:56Z)

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.