Towards Predictive, Aligned, and Scalable Robot Learning

• URL: http://arxiv.org/abs/2607.11270v1
• Date: Mon, 13 Jul 2026 08:53:34 GMT
• Title: Towards Predictive, Aligned, and Scalable Robot Learning
• Abstract summary: We introduce Lumo-2, a latent world-action model that generates actions by reasoning over world dynamics in latent space.<n>We study latent world modelling and modality alignment, analyzing their roles in scaling laws and out-of-distribution generalization.<n>Results show that Lumo-2 consistently outperforms strong vision-language-action (VLA) and world-action model (WAM) baselines.
• Score: 11.830982964522605
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Learning, at its core, extends beyond memorization to the ability to reason and solve novel problems by navigating a space of possibilities. We introduce Lumo-2, a latent world-action model that generates actions by reasoning over world dynamics in latent space. The learned latent world dynamics capture physically grounded visual transitions, naturally encoding future possibilities and providing a unified substrate for cross-modal alignment. This formulation enables predictive reasoning akin to world modelling while remaining lightweight and focused on physical dynamics relevant to control. Central to our approach is the hypothesis that action generation quality is governed by the geometry of the latent space. We observe that standard reconstruction-based action tokenization objectives induce representations biased toward low-level signal fidelity, leading to misalignment between reconstruction quality and downstream control performance. To address this limitation, we propose a multi-stage modality pre-alignment strategy in which action representations are progressively aligned with latent world dynamics, vision, and language. This process enforces cross-modal consistency, promotes abstraction, and induces a structured latent space for predictive reasoning. We provide a systematic empirical study of latent world modelling and modality alignment, analyzing their roles in scaling laws and out-of-distribution generalization. Results show that Lumo-2 consistently outperforms strong vision-language-action (VLA) and world-action model (WAM) baselines, with gains on challenging real-world tasks requiring temporal reasoning, physical understanding, or high control complexity, including long-horizon and dexterous manipulation. These findings suggest that structured multimodal alignment and predictive reasoning are fundamental principles for advancing embodied intelligence.

Related papers

• Decoupling Intention from Trajectory: A Representational Deduction Framework for World Action Models [22.16380408116294]
  World Action Models (WAMs) aim to construct a unified architecture capable of understanding world state evolution and guiding to generative motion planning.<n>We propose PILOT, whose core Representational Deduction (RD) bridges this gap by integrating motion thought-of-chain guidance as a native model capability.
  arXiv  Detail & Related papers  (2026-08-07T09:12:15Z)
• AnchorWorld: Embodied Egocentric World Simulation with View-based Evolution Customization [79.26935895370191]
  AnchorWorld is a framework that advances egocentric simulation through enhanced interaction integrity.<n> auxiliary training supervision incorporates viewpoints decoupled from the agent's first-person sensorium.<n>We propose a simple yet effective mechanism for customizing self-evolving worlds.
  arXiv  Detail & Related papers  (2026-06-05T14:43:13Z)
• X-Foresight: A Joint Vision-Action Causal Forecasting Network via Predictive World Modeling [47.54820149491433]
  We introduce X-Foresight, a predictive world model integrated directly into the Vision-Language-Action architecture.<n>By predicting semantically distant chunks rather than adjacent frames, X-Foresight escapes trivial extrapolation.<n> Comprehensive experiments demonstrate that X-Foresight significantly outperforms VLA baselines in planning performance.
  arXiv  Detail & Related papers  (2026-05-24T06:37:04Z)
• Self-Evolving Spatial Reasoning in Vision Language Models via Geometric Logic Consistency [53.28076739140119]
  We propose a framework that enforces logical consistency in Vision-Language Models (VLMs) through geometric and linguistic duality operations.<n>SAGE is model-agnostic, data-efficient compared to prior GRPO methods, and can be applied as a lightweight post-training stage to any existing VLM.<n> Experiments on video and spatial reasoning benchmarks demonstrate consistent improvements over strong baselines.
  arXiv  Detail & Related papers  (2026-05-18T10:05:21Z)
• World Action Models: The Next Frontier in Embodied AI [123.5787299299832]
  Vision-Language-Action (VLA) models have achieved strong semantic generalization for embodied policy learning.<n>They learn reactive observation-to-action mappings without explicitly modeling how the physical world evolves under intervention.<n>A growing body of work addresses this limitation by integrating world models, predictive models of environment dynamics, into the action generation pipeline.
  arXiv  Detail & Related papers  (2026-05-12T13:10:52Z)
• Aligning Agentic World Models via Knowledgeable Experience Learning [68.85843641222186]
  We introduce WorldMind, a framework that constructs a symbolic World Knowledge Repository by synthesizing environmental feedback.<n>WorldMind achieves superior performance compared to baselines with remarkable cross-model and cross-environment transferability.
  arXiv  Detail & Related papers  (2026-01-19T17:33:31Z)
• World Models Should Prioritize the Unification of Physical and Social Dynamics [57.91940497010114]
  This paper argues that the systematic, bidirectional unification of physical and social predictive capabilities is the next crucial frontier for world model development.<n>We contend that comprehensive world models must holistically integrate objective physical laws with the subjective, evolving, and context-dependent nature of social dynamics.
  arXiv  Detail & Related papers  (2025-10-24T07:42:37Z)
• Seeing Space and Motion: Enhancing Latent Actions with Spatial and Dynamic Awareness for VLA [21.362682837521632]
  Latent Action Models (LAMs) enable Vision- Language-Action systems to learn semantic action rep- resentations from large-scale unannotated data.<n>We propose Farsighted-LAM, a latent action framework with geometry- aware spatial encoding and multi-scale temporal modeling.<n>We further propose SSM-VLA, an end- to-end VLA framework built upon Farsighted-LAM, which integrates structured perception with a visual Chain-of-Thought module.
  arXiv  Detail & Related papers  (2025-09-30T13:41:43Z)
• From Perception to Cognition: A Survey of Vision-Language Interactive Reasoning in Multimodal Large Language Models [66.36007274540113]
  Multimodal Large Language Models (MLLMs) strive to achieve a profound, human-like understanding of and interaction with the physical world.<n>They often exhibit a shallow and incoherent integration when acquiring information (Perception) and conducting reasoning (Cognition)<n>This survey introduces a novel and unified analytical framework: From Perception to Cognition"
  arXiv  Detail & Related papers  (2025-09-29T18:25:40Z)
• VisionLaw: Inferring Interpretable Intrinsic Dynamics from Visual Observations via Bilevel Optimization [3.131272328696594]
  VisionLaw is a bilevel optimization framework that infers interpretable expressions of intrinsic dynamics from visual observations.<n>It significantly outperforms existing state-of-the-art methods and exhibits strong generalization for interactive simulation in novel scenarios.
  arXiv  Detail & Related papers  (2025-08-19T12:52:16Z)
• DreamVLA: A Vision-Language-Action Model Dreamed with Comprehensive World Knowledge [41.030494146004806]
  We propose DreamVLA, a novel VLA framework that integrates comprehensive world knowledge forecasting to enable inverse dynamics modeling.<n>DreamVLA introduces a dynamic-region-guided world knowledge prediction, integrated with the spatial and semantic cues, which provide compact yet comprehensive representations for action planning.<n>Experiments on both real-world and simulation environments demonstrate that DreamVLA achieves 76.7% success rate on real robot tasks.
  arXiv  Detail & Related papers  (2025-07-06T16:14:29Z)

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.