← Back to all news
arXiv AI By Zengqi Zhao, Zun Wang, Shoubin Yu, Mohit Bansal, Yue Zhang

Representing the Unseen: Rethinking Visual Imagination for Spatial Reasoning

Read the original on arXiv AI →

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.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

Related stories

arXiv AI
Oct 12

SpatialASM: Internalizing Active Mentalization for Spatial Reasoning

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.

By Yuhong Liu, Shenxi Wu, Junyi Chi, Beichen Zhang, Xuanlang Dai, Jiaqi Wang, Yuhang Zang, Dahua Lin
llmsmultimodalbenchmarks
More like this →
arXiv Computation and Language
Oct 9

SpaceCast-Bench: Evaluating Predictive Spatial Reasoning in Vision-Language Models

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.

By Hongxing Li, Jinyue Su, Dingming Li, Wenqi Zhang, Weiming Lu, Jun Xiao, Yueting Zhuang, Yongliang Shen
llmsfine-tuningmultimodalbenchmarks
More like this →