What if? Emulative Simulation with World Models for Situated Reasoning

• URL: http://arxiv.org/abs/2603.06445v1
• Date: Fri, 06 Mar 2026 16:37:15 GMT
• Title: What if? Emulative Simulation with World Models for Situated Reasoning
• Abstract summary: WanderDream is the first large-scale dataset designed for the emulative simulation of mental exploration.<n>WanderDream-Gen comprises 15.8K panoramic videos across 1,088 real scenes from HM3D, ScanNet++, and real-world captures.<n>WanderDream-QA contains 158K question-answer pairs, covering starting states, paths, and end states along each trajectory.
• Score: 51.770776877972956
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Situated reasoning often relies on active exploration, yet in many real-world scenarios such exploration is infeasible due to physical constraints of robots or safety concerns of visually impaired users. Given only a limited observation, can an agent mentally simulate a future trajectory toward a target situation and answer spatial what-if questions? We introduce WanderDream, the first large-scale dataset designed for the emulative simulation of mental exploration, enabling models to reason without active exploration. WanderDream-Gen comprises 15.8K panoramic videos across 1,088 real scenes from HM3D, ScanNet++, and real-world captures, depicting imagined trajectories from current viewpoints to target situations. WanderDream-QA contains 158K question-answer pairs, covering starting states, paths, and end states along each trajectory to comprehensively evaluate exploration-based reasoning. Extensive experiments with world models and MLLMs demonstrate (1) that mental exploration is essential for situated reasoning, (2) that world models achieve compelling performance on WanderDream-Gen, (3) that imagination substantially facilitates reasoning on WanderDream-QA, and (4) that WanderDream data exhibit remarkable transferability to real-world scenarios. The source code and all data will be released.

Related papers

• Self-supervised Hierarchical Visual Reasoning with World Model [82.64295546475257]
  3D open-world environments with adversarial opponents remain a core challenge for reinforcement learning.<n>We propose ResDreamer, a hierarchical world model in which each higher-level layer is trained to reconstruct the residuals of the layer below.<n>This design enables progressive abstraction of increasingly sophisticated world dynamics and fosters the emergence of richer latent representations.
  arXiv  Detail & Related papers  (2026-05-17T16:42:42Z)
• IndustryNav: Exploring Spatial Reasoning of Embodied Agents in Dynamic Industrial Navigation [56.43007596544299]
  IndustryNav is the first dynamic industrial navigation benchmark for active spatial reasoning.<n>A study of nine state-of-the-art Visual Large Language Models reveals that closed-source models maintain a consistent advantage.
  arXiv  Detail & Related papers  (2025-11-21T16:48:49Z)
• AirScape: An Aerial Generative World Model with Motion Controllability [29.696659138543136]
  AirScape is the first world model designed for six-degree-of-bodied aerial agents.<n>It predicts future observation based on current visual inputs and motion intentions.
  arXiv  Detail & Related papers  (2025-07-10T16:05:30Z)
• Imagine, Verify, Execute: Memory-guided Agentic Exploration with Vision-Language Models [81.08295968057453]
  We present IVE, an agentic exploration framework inspired by human curiosity.<n>We evaluate IVE in both simulated and real-world tabletop environments.
  arXiv  Detail & Related papers  (2025-05-12T17:59:11Z)
• DriveDreamer: Towards Real-world-driven World Models for Autonomous Driving [76.24483706445298]
  We introduce DriveDreamer, a world model entirely derived from real-world driving scenarios. In the initial phase, DriveDreamer acquires a deep understanding of structured traffic constraints, while the subsequent stage equips it with the ability to anticipate future states. DriveDreamer enables the generation of realistic and reasonable driving policies, opening avenues for interaction and practical applications.
  arXiv  Detail & Related papers  (2023-09-18T13:58:42Z)
• NavDreams: Towards Camera-Only RL Navigation Among Humans [35.57943738219839]
  We investigate whether the world model concept, which has shown results for modeling and learning policies in Atari games, can also be applied to the camera-based navigation problem. We create simulated environments where a robot must navigate past static and moving humans without colliding in order to reach its goal. We find that state-of-the-art methods are able to achieve success in solving the navigation problem, and can generate dream-like predictions of future image-sequences.
  arXiv  Detail & Related papers  (2022-03-23T09:46:44Z)
• Pathdreamer: A World Model for Indoor Navigation [62.78410447776939]
  We introduce Pathdreamer, a visual world model for agents navigating in novel indoor environments. Given one or more previous visual observations, Pathdreamer generates plausible high-resolution 360 visual observations. In regions of high uncertainty, Pathdreamer can predict diverse scenes, allowing an agent to sample multiple realistic outcomes.
  arXiv  Detail & Related papers  (2021-05-18T18:13:53Z)
• Out of the Box: Embodied Navigation in the Real World [45.97756658635314]
  We show how to transfer knowledge acquired in simulation into the real world. We deploy our models on a LoCoBot equipped with a single Intel RealSense camera. Our experiments indicate that it is possible to achieve satisfying results when deploying the obtained model in the real world.
  arXiv  Detail & Related papers  (2021-05-12T18:00:14Z)

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.