The paper introduces ImagiRep, a benchmark that tests spatial reasoning using seven question types across two settings, offering RGB and six alternative representations of imagined states. It shows that accurate RGB generation does not guarantee correct spatial reasoning and that different questions benefit from different representations such as depth, panoramic views, or top‑down geometry. Building on these insights, the authors present GEARS, a lightweight strategy that adaptively selects representations at test time, outperforming existing methods and demonstrating that reasoning about unseen states requires more than just RGB generation.
arXiv:2602. 08236v2 Announce Type: replace-cross Abstract: Despite rapid progress in MLLMs, visual spatial reasoning remains unreliable when correct answers depend on how a scene would appear under unseen or alternative viewpoints.
arXiv:2606. 03988v1 Announce Type: new Abstract: Vision language models (VLMs) excel at many tasks but still struggle with spatial reasoning when critical information is not directly observable.
SpatialASM is a framework that teaches Large Vision‑Language Models (LVLMs) to perform Active Spatial Mentalization (ASM), enabling them to proactively plan and imagine viewpoints during spatial reasoning tasks. The method uses an allocentric novel‑view generator to create explicit ASM trajectories and perspective‑taking tasks, providing two forms of supervision that guide LVLMs in adaptive view planning and scene imagination. Experiments on seven spatial benchmarks show that SpatialASM improves performance across four LVLM backbones while preserving their general vision capabilities.
SpaceCast-Bench is a new benchmark that evaluates predictive spatial reasoning in vision‑language models, moving beyond simple spatial perception to tasks that require constructing scenes, anticipating interventions, and reasoning about unseen outcomes. It contains 3,862 questions from 182 real‑world scenes across 16 task types and three difficulty levels—static perception, local prediction, and global prediction—testing scene understanding, spatial state updating, and relational inference. Evaluation of 21 models shows a large performance gap, with the best model achieving only 58.0% versus 87.2% human accuracy, and fine‑tuning on the benchmark’s programmatically generated data can substantially improve model performance.
arXiv:2605.27310v2 Announce Type: replace Abstract: Cross-view spatial reasoning remains a weak spot for vision-language models (VLMs): they reason in language and discard the fine-grained geometry t...
arXiv:2607. 22864v1 Announce Type: cross Abstract: Multimodal large language models (MLLMs) excel at visual interpretation but fail on spatial reasoning tasks that humans solve reliably.
arXiv:2610.18694v1 Announce Type: cross Abstract: Vision-language models (VLMs) struggle with metric and multi-view relationships that remain implicit in RGB observations. Geometry foundation models...
The paper introduces GeoUG, a unified model that combines depth and multi-view generation with spatial understanding. It employs a multi-scale depth codec for metric-depth generation and demonstrates that joint training improves spatial tasks. Using the 3DCueBench benchmark, the authors show that generated depth aids fine-grained geometric reasoning and develop an adaptive interleaved reasoning strategy that balances accuracy with generation cost, achieving high accuracies on several benchmarks.
arXiv:2605.30557v2 Announce Type: replace-cross Abstract: Spatial reasoning benchmarks typically evaluate whether vision-language models can derive the correct answer from a visual observation. Yet i...
arXiv:2601. 19099v2 Announce Type: replace-cross Abstract: Vision--language models (VLMs) achieve strong performance on many multimodal benchmarks but remain brittle on spatial reasoning tasks that require aligning abstract overhead representations with egocentric views.
arXiv:2610.28622v1 Announce Type: cross Abstract: Spatial intelligence has recently been assessed through generative tasks such as spatially grounded image editing, yet language-guided generation of...
arXiv:2511. 07403v2 Announce Type: replace-cross Abstract: Multimodal large language models (MLLMs) have achieved remarkable progress in vision-language tasks, but continue to struggle with spatial reasoning.