Act2Goal: From World Model To General Goal-conditioned Policy

• URL: http://arxiv.org/abs/2512.23541v1
• Date: Mon, 29 Dec 2025 15:28:42 GMT
• Title: Act2Goal: From World Model To General Goal-conditioned Policy
• Abstract summary: Act2Goal is a goal-conditioned manipulation policy that integrates a goal-conditioned visual world model with multi-scale temporal control.<n>We show that Act2Goal improves success rates from 30% to 90% on challenging out-of-distribution tasks within minutes of autonomous interaction.
• Score: 14.222177107215648
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Specifying robotic manipulation tasks in a manner that is both expressive and precise remains a central challenge. While visual goals provide a compact and unambiguous task specification, existing goal-conditioned policies often struggle with long-horizon manipulation due to their reliance on single-step action prediction without explicit modeling of task progress. We propose Act2Goal, a general goal-conditioned manipulation policy that integrates a goal-conditioned visual world model with multi-scale temporal control. Given a current observation and a target visual goal, the world model generates a plausible sequence of intermediate visual states that captures long-horizon structure. To translate this visual plan into robust execution, we introduce Multi-Scale Temporal Hashing (MSTH), which decomposes the imagined trajectory into dense proximal frames for fine-grained closed-loop control and sparse distal frames that anchor global task consistency. The policy couples these representations with motor control through end-to-end cross-attention, enabling coherent long-horizon behavior while remaining reactive to local disturbances. Act2Goal achieves strong zero-shot generalization to novel objects, spatial layouts, and environments. We further enable reward-free online adaptation through hindsight goal relabeling with LoRA-based finetuning, allowing rapid autonomous improvement without external supervision. Real-robot experiments demonstrate that Act2Goal improves success rates from 30% to 90% on challenging out-of-distribution tasks within minutes of autonomous interaction, validating that goal-conditioned world models with multi-scale temporal control provide structured guidance necessary for robust long-horizon manipulation. Project page: https://act2goal.github.io/

Related papers

• WorldScape Policy 2.0: Empowering Steerable World Action Modeling with Reasoning-Augmented Memory [50.19449886428936]
  We introduce WorldScape Policy 2.0, a controllable WAM with reasoning-augmented long short-term memory.<n>The retrieved history augments perception and autoregressively generated planning tokens, yielding an implicit subgoal condition for autonomous planning.<n>Experiments in both simulation and real-world platforms demonstrate superior capabilities in long-horizon autonomous planning, fine-grained instruction following, and in-context adaptation.
  arXiv  Detail & Related papers  (2026-07-21T08:25:37Z)
• ABot-M0.5: Unified Mobility-and-Manipulation World Action Model [27.262271208923995]
  ABot-M0.5 is built on the insight that mobile manipulation requires alignment at three levels: temporal granularity, action space, and train-test consistency.<n> Experiments on challenging mobile and fine-grained manipulation benchmarks demonstrate that ABot-M0.5 achieves state-of-the-art performance in both long-horizon task success and finegrained control accuracy.
  arXiv  Detail & Related papers  (2026-07-01T09:21:20Z)
• Foresight: Failure Detection for Long-Horizon Robotic Manipulation with Action-Conditioned World Model Latents [58.49879338545782]
  Long-horizon tasks are common in real-world robotic deployments, yet failure detection for such tasks remains underexplored.<n>We present Foresight, a failure detection framework that monitors manipulation trajectories using latent representations from an action-conditioned world model.<n>Our results suggest that action-conditioned world-model embeddings provide a scalable representation for reliable failure monitoring in long-horizon manipulation.
  arXiv  Detail & Related papers  (2026-06-22T09:32:28Z)
• DisCo: World Models with Discrete Camera Motion Control [79.86256515640231]
  We propose DisCo, a controllable video world model that conditions generation on a compact set of discrete action primitives to improve action separability.<n>DisCo achieves significantly more reliable action following while preserving visual quality.
  arXiv  Detail & Related papers  (2026-06-06T03:50:45Z)
• WAM-Nav: Asymmetric Latent World-Action Modeling for Unified Visual Navigation [31.539730066120374]
  Visual navigation requires generating smooth and collision-free trajectories under complex geometric and physical constraints.<n>We propose WAM-Nav, a Latent World-Action Model for embodied visual navigation that jointly learns action generation and latent visual foresight.
  arXiv  Detail & Related papers  (2026-06-03T14:05:19Z)
• Lifting Embodied World Models for Planning and Control [59.09016913513998]
  We train a lightweight policy that maps high-level actions to sequences of low-level joint actions.<n>We instantiate this framework for a human-like embodiment, defining the high-level action space as a small set of 2D waypoints.<n>We show that the lifted world model substantially outperforms searching directly in low-level joint space.
  arXiv  Detail & Related papers  (2026-04-28T23:59:19Z)
• ULTRA: Unified Multimodal Control for Autonomous Humanoid Whole-Body Loco-Manipulation [55.467742403416175]
  We introduce a physics-driven neural algorithm that translates large-scale motion capture to humanoid embodiments.<n>We learn a unified multimodal controller that supports both dense references and sparse task specifications.<n>Results show that ULTRA generalizes to autonomous, goal-conditioned whole-body loco-manipulation from egocentric perception.
  arXiv  Detail & Related papers  (2026-03-03T18:59:29Z)
• H-WM: Robotic Task and Motion Planning Guided by Hierarchical World Model [26.305515799597714]
  We propose a Hierarchical World Model (H-WM) that jointly predicts logical and visual state transitions within a unified framework.<n>H-WM combines a high-level logical world model with a low-level visual world model, integrating the long-horizon of symbolic reasoning with visual grounding.<n> Experiments across multiple vision-language-action (VLA) control policies demonstrate the effectiveness and generality of H-WM's guidance.
  arXiv  Detail & Related papers  (2026-02-11T19:08:36Z)
• Envision: Embodied Visual Planning via Goal-Imagery Video Diffusion [61.63215708592008]
  Embodied visual planning aims to enable manipulation tasks by imagining how a scene evolves toward a desired goal.<n>Video diffusion models provide a promising foundation for such visual imagination.<n>We propose Envision, a diffusion-based framework that performs visual planning for embodied agents.
  arXiv  Detail & Related papers  (2025-12-27T15:46:41Z)
• AstraNav-World: World Model for Foresight Control and Consistency [40.07910402326578]
  Embodied navigation in dynamic environments demands accurate foresight of how the world will evolve and how actions will unfold over time.<n>We propose AstraNav-World, an end-to-end world model that jointly reasons about future visual states and action sequences.<n>Our framework integrates a diffusion-based video generator with a vision-language policy, enabling synchronized rollouts.
  arXiv  Detail & Related papers  (2025-12-25T15:31:24Z)
• Active Intelligence in Video Avatars via Closed-loop World Modeling [55.29966567726842]
  Current video avatar generation methods excel at identity preservation and motion alignment but lack genuine agency.<n>We introduce L-IVA (Long-horizon Interactive Visual Avatar), a task and benchmark for evaluating goal-directed planning in generative environments.<n>We also present ORCA, the first framework enabling active intelligence in video avatars.
  arXiv  Detail & Related papers  (2025-12-23T18:59:16Z)
• Real-World Robot Control by Deep Active Inference With a Temporally Hierarchical World Model [0.7284556903703034]
  Deep active inference is a framework that accounts for human goal-directed and exploratory actions.<n>We propose a novel deep active inference framework that consists of a world model, an action model, and an abstract world model.<n>We evaluate the framework on object-manipulation tasks with a real-world robot.
  arXiv  Detail & Related papers  (2025-12-01T17:41:01Z)
• Weakly-supervised Latent Models for Task-specific Visual-Language Control [2.10305808315957]
  We propose a task-specific latent dynamics model that learns state-specific action-induced shifts in a shared latent space using only goal-state supervision.<n>In experiments, our approach achieves 71% success and generalizes to unseen images and instructions.
  arXiv  Detail & Related papers  (2025-11-23T07:18:28Z)
• Ctrl-World: A Controllable Generative World Model for Robot Manipulation [53.71061464925014]
  Generalist robot policies can perform a wide range of manipulation skills.<n> evaluating and improving their ability with unfamiliar objects and instructions remains a significant challenge.<n>World models offer a promising, scalable alternative by enabling policies to rollout within imagination space.
  arXiv  Detail & Related papers  (2025-10-11T09:13:10Z)
• ODYSSEY: Open-World Quadrupeds Exploration and Manipulation for Long-Horizon Tasks [46.676862567167625]
  ODYSSEY is a unified mobile manipulation framework for agile quadruped robots equipped with manipulators.<n>To address the challenge of egocentric perception in language-conditioned tasks, we introduce a hierarchical planner powered by a vision-language model.<n>At the control level, our novel whole-body policy achieves robust coordination across challenging terrains.
  arXiv  Detail & Related papers  (2025-08-11T17:54:31Z)
• 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)
• Diffusion Transformer Policy [48.50988753948537]
  We propose a large multi-modal diffusion transformer, dubbed as Diffusion Transformer Policy, to model continuous end-effector actions.<n>By leveraging the scaling capability of transformers, the proposed approach can effectively model continuous end-effector actions across large diverse robot datasets.
  arXiv  Detail & Related papers  (2024-10-21T12:43:54Z)

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.