MemoBench: Benchmarking World Modeling in Dynamically Changing Environments

• URL: http://arxiv.org/abs/2606.27537v2
• Date: Tue, 30 Jun 2026 03:22:46 GMT
• Title: MemoBench: Benchmarking World Modeling in Dynamically Changing Environments
• Abstract summary: We introduce MemoBench, a diagnostic benchmark built around the disappear-and-reappear paradigm in dynamically changing environments.<n>We curate 360 ground-truth clips spanning synthetic and real-world scenes, and design an evaluation suite combining automated metrics with VQA-based assessment.
• Score: 72.23517478870605
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Video generation models aspire to simulate dynamic environments, and several benchmarks now evaluate memory consistency across frames. However, most assess consistency only while the target remains in view, and the few that force objects out of view evaluate static scenes where nothing changes during occlusion. To bridge this gap, we introduce MemoBench, a diagnostic benchmark built around the disappear-and-reappear paradigm in dynamically changing environments: a target object undergoes a physical process, disappears from view, and must be correctly recovered in its updated state upon reappearance. We curate 360 ground-truth clips spanning synthetic and real-world scenes, and design an evaluation suite combining automated metrics with VQA-based assessment across four diagnostic pillars. Evaluation of eight state-of-the-art models reveals key insights and open challenges regarding memory consistency under the disappear-and-reappear paradigm.

Related papers

• IDEAL-Bench: Indoor Dataset and Evaluation suite for Analyzing 3D Layout reasoning [30.654858163397662]
  We introduce I-Bench, an evaluation suite that requires Vision-Language Models to predict structured 3D layouts on indoor scenes.<n>I-Bench moves beyond CLEVR-style simple geometric primitives so that any image-space discrepancy reflects spatial reasoning alone.
  arXiv  Detail & Related papers  (2026-07-03T22:04:42Z)
• WorldRoamBench: An Open-World Benchmark for Long-Horizon Stability of Interactive World Models [37.59051701511746]
  We introduce WorldRoamBench, an open-world benchmark for long-horizon stability across four dimensions.<n>The benchmark comprises 600+ test cases across Nature, Urban, and Indoor scenes in first/third-person views with WASD 10-60s continuous interaction.
  arXiv  Detail & Related papers  (2026-06-30T13:51:44Z)
• A Physics-Grounded Benchmark for Multi-Agent Dynamics in World Models [96.64934195520802]
  We introduce CrashTwin, a physics-grounded evaluation framework designed to stress-test the physical trustworthiness of world models.<n>CrashTwin couples a diverse dataset of multi-agent collision scenarios, comprising 25K controllable synthetic 12K in-the-wild real-world collision sequences.<n>We propose a diagnostic suite that systematically evaluates three dimensions:-temporal consistency, momentum and kinetic energy conservation, and world-dynamics integrity.
  arXiv  Detail & Related papers  (2026-06-27T06:13:35Z)
• Mem-World: Memory-Augmented Action-Conditioned World Models for Persistent Robot Manipulation [55.42006264038458]
  Action-conditioned world models have emerged as a promising paradigm for robot learning.<n>Mem-World is a memory-augmented multi-view action-conditioned world model.<n>We present W-VMem, a 4D wrist-view-centered surfel-indexed memory that anchors historical observations to temporally evolving surface elements.
  arXiv  Detail & Related papers  (2026-06-17T11:42:00Z)
• CRONOS: Benchmarking Counterfactual Physical Consistency in Video Models [25.976578205889776]
  CRONOS is an intervention-based benchmark designed to evaluate counterfactual physical consistency.<n>Built in an Unreal Engine environment, CRONOS enables controlled, high-fidelity generation of videos across diverse scenes and dynamics.
  arXiv  Detail & Related papers  (2026-05-22T14:51:22Z)
• Beyond Binary Success: A Diagnostic Meta-Evaluation Framework for Fine-Grained Manipulation [98.79811866787263]
  We introduce MetaFine, a diagnostic meta-evaluation framework that disentangles manipulation competency along three axes.<n>We identify the visual encoder's ability to preserve local spatial structure as a key bottleneck for fine-grained precision.<n>By shifting evaluation from ranking to diagnosis, MetaFine turns benchmarking into an actionable compass for repairing the layered capacities underlying genuine physical dexterity.
  arXiv  Detail & Related papers  (2026-05-19T15:25:13Z)
• ReVSI: Rebuilding Visual Spatial Intelligence Evaluation for Accurate Assessment of VLM 3D Reasoning [59.558706734431276]
  Current evaluations of spatial intelligence can be systematically invalid under modern vision-language model (VLM) settings.<n>We introduce ReVSI, a benchmark and protocol that ensures each QA pair is answerable and correct under the model's actual inputs.
  arXiv  Detail & Related papers  (2026-04-27T10:45:51Z)
• Can Vision Foundation Models Navigate? Zero-Shot Real-World Evaluation and Lessons Learned [5.561294055181353]
  Visual Navigation Models (VNMs) promise generalizable, robot navigation by learning from large-scale visual demonstrations.<n>We present a real-world evaluation of five state-of-the-art VNMs across two robot platforms and five environments spanning indoor and outdoor settings.
  arXiv  Detail & Related papers  (2026-03-26T22:04:49Z)
• EvoEmpirBench: Dynamic Spatial Reasoning with Agent-ExpVer [5.855255212938064]
  We introduce two dynamic spatial benchmarks that evaluate models' abilities in spatial understanding and adaptive planning.<n>Experiments show that our benchmarks reveal key limitations of mainstream models in dynamic spatial reasoning and long-term memory.
  arXiv  Detail & Related papers  (2025-09-16T06:21:38Z)
• EOC-Bench: Can MLLMs Identify, Recall, and Forecast Objects in an Egocentric World? [52.99661576320663]
  multimodal large language models (MLLMs) have driven breakthroughs in egocentric vision applications.<n>EOC-Bench is an innovative benchmark designed to systematically evaluate object-centric embodied cognition in dynamic egocentric scenarios.<n>We conduct comprehensive evaluations of various proprietary, open-source, and object-level MLLMs based on EOC-Bench.
  arXiv  Detail & Related papers  (2025-06-05T17:44:12Z)
• DynaVINS++: Robust Visual-Inertial State Estimator in Dynamic Environments by Adaptive Truncated Least Squares and Stable State Recovery [11.37707868611451]
  We propose a robust VINS framework called mboxtextitDynaVINS++. Our approach shows promising performance in dynamic environments, including scenes with abruptly dynamic objects.
  arXiv  Detail & Related papers  (2024-10-20T12:13:45Z)
• Tracking through Containers and Occluders in the Wild [32.86030395660071]
  We introduce $textbfTCOW$, a new benchmark and model for visual tracking through heavy occlusion and containment. We create a mixture of synthetic and annotated real datasets to support both supervised learning and structured evaluation of model performance. We evaluate two recent transformer-based video models and find that while they can be surprisingly capable of tracking targets under certain settings of task variation, there remains a considerable performance gap before we can claim a tracking model to have acquired a true notion of object permanence.
  arXiv  Detail & Related papers  (2023-05-04T17:59:58Z)

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.