TableVision: A Large-Scale Benchmark for Spatially Grounded Reasoning over Complex Hierarchical Tables

• URL: http://arxiv.org/abs/2604.03660v1
• Date: Sat, 04 Apr 2026 09:26:09 GMT
• Title: TableVision: A Large-Scale Benchmark for Spatially Grounded Reasoning over Complex Hierarchical Tables
• Abstract summary: We find that as task complexity scales, the number of involved discrete visual regions increases disproportionately.<n>This processing density leads to an internal "Perceptual Overload"<n>We introduce TableVision, a trajectory-aware benchmark designed for spatially grounded reasoning.
• Score: 13.218805579902048
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Structured tables are essential for conveying high-density information in professional domains such as finance, healthcare, and scientific research. Despite the progress in Multimodal Large Language Models (MLLMs), reasoning performance remains limited for complex tables with hierarchical layouts. In this paper, we identify a critical Perception Bottleneck through quantitative analysis. We find that as task complexity scales, the number of involved discrete visual regions increases disproportionately. This processing density leads to an internal "Perceptual Overload," where MLLMs struggle to maintain accurate spatial attention during implicit generation. To address this bottleneck, we introduce TableVision, a large-scale, trajectory-aware benchmark designed for spatially grounded reasoning. TableVision stratifies tabular tasks into three cognitive levels (Perception, Reasoning, and Analysis) across 13 sub-categories. By utilizing a rendering-based deterministic grounding pipeline, the dataset explicitly couples multi-step logical deductions with pixel-perfect spatial ground truths, comprising 6,799 high-fidelity reasoning trajectories. Our empirical results, supported by diagnostic probing, demonstrate that explicit spatial constraints significantly recover the reasoning potential of MLLMs. Furthermore, our two-stage decoupled framework achieves a robust 12.3% overall accuracy improvement on the test set. TableVision provides a rigorous testbed and a fresh perspective on the synergy between perception and logic in document understanding.

Related papers

• MV-STRIDE: Enabling MLLMs to Master Multi-View Spatial Reasoning via Hierarchical Capability Modeling [22.069318507340423]
  We introduce MV-STRIDE, a hierarchical SpaTial Reasoning dataset with Interdependent and DE capabilitiEs.<n>Moving beyond flat data structures, MV-STRIDE explicitly models the dependency relationships between perception, scene understanding, and complex contextual reasoning.<n>We develop a systematic QA generation pipeline leveraging diverse 3D scene sources that enforces cross-view dependency constraints.
  arXiv  Detail & Related papers  (2026-09-07T09:14:13Z)
• HoloCount: A Holistic Visual Counting Benchmark for MLLMs [17.08907754405721]
  HoloCount is a diagnostically rich benchmark structured around a three-level hierarchical taxonomy.<n>We evaluate over 20 state-of-the-art Multimodal Large Language Models (MLLMs)<n>Our findings offer a roadmap for developing more grounded and reliable multimodal systems.
  arXiv  Detail & Related papers  (2026-07-07T15:48:57Z)
• SpaceEra++: A Unified Framework Towards 3D Spatial Reasoning in Video [88.79625979053873]
  We propose a novel framework, SpaceEra, for pre-trained vision-language models (VLMs)<n>We extend the original framework into a comprehensive system, termed SpaceEra++, which spans data construction, model design, training optimization, and prompting inference.<n>In addition, to enhance spatial reasoning, we develop SpaceAlign, which enforces pairwise object constraints by jointly exploiting absolute coordinates and relative spatial relations.
  arXiv  Detail & Related papers  (2026-07-02T06:56:29Z)
• Embodied3DBench: Benchmarking Low-Level Embodied Spatial Intelligence of Vision Language Models [50.6415287154632]
  Embodied3DBench is a robot-centric benchmark targeting low-level spatial intelligence in 3D environments.<n>The benchmark spans 12 subcategories and contains over 21k high-quality question-answer pairs.
  arXiv  Detail & Related papers  (2026-05-27T20:28:56Z)
• From Indoor to Open World: Revealing the Spatial Reasoning Gap in MLLMs [65.04549036809557]
  We introduce a benchmark built from pedestrian-perspective videos captured with synchronized stereo cameras, LiDAR, and IMU/GPS sensors.<n>This dataset provides metrically precise 3D information, enabling the automatic generation of spatial reasoning questions.<n> Evaluations reveal that the performance gains observed in structured indoor benchmarks vanish in open-world settings.
  arXiv  Detail & Related papers  (2025-12-22T18:58:12Z)
• Reasoning Path and Latent State Analysis for Multi-view Visual Spatial Reasoning: A Cognitive Science Perspective [17.592210658831902]
  spatial reasoning is a core aspect of human intelligence that allows perception, inference and planning in 3D environments.<n>Current vision-language models (VLMs) struggle to maintain geometric coherence and cross-view consistency for spatial reasoning in multi-view settings.<n>We present ReMindView-Bench, a cognitively grounded benchmark for evaluating how VLMs construct, align and maintain spatial mental models across complementary viewpoints.
  arXiv  Detail & Related papers  (2025-12-02T02:21:29Z)
• LTD-Bench: Evaluating Large Language Models by Letting Them Draw [57.237152905238084]
  LTD-Bench is a breakthrough benchmark for large language models (LLMs)<n>It transforms LLM evaluation from abstract scores to directly observable visual outputs by requiring models to generate drawings through dot matrices or executable code.<n> LTD-Bench's visual outputs enable powerful diagnostic analysis, offering a potential approach to investigate model similarity.
  arXiv  Detail & Related papers  (2025-11-04T08:11:23Z)
• Why Do MLLMs Struggle with Spatial Understanding? A Systematic Analysis from Data to Architecture [16.15618237704827]
  We present a systematic analysis of spatial understanding from both data and architectural perspectives.<n>From the data perspective, the performance of spatial understanding converges quickly as the training data increases.<n>From the architectural perspective, we find that spatial understanding relies more heavily on the positional encoding within the visual encoder than within the language model.
  arXiv  Detail & Related papers  (2025-09-02T14:22:43Z)
• Enhancing Spatial Reasoning in Multimodal Large Language Models through Reasoning-based Segmentation [50.81551581148339]
  We introduce Relevant Reasoning (R$2$S), a reasoning-based segmentation framework.<n>We also introduce 3D ReasonSeg, a reasoning-based segmentation dataset.<n>Both experiments demonstrate that the R$2$S and 3D ReasonSeg effectively endow 3D point cloud perception with stronger spatial reasoning capabilities.
  arXiv  Detail & Related papers  (2025-06-29T06:58:08Z)
• ViewSpatial-Bench: Evaluating Multi-perspective Spatial Localization in Vision-Language Models [68.46716645478661]
  Vision-language models (VLMs) have demonstrated remarkable capabilities in understanding and reasoning about visual content.<n>Current VLMs excel primarily at egocentric spatial reasoning (from the camera's perspective) but fail to generalize to allocentric viewpoints.<n>We introduce ViewSpatial-Bench, the first comprehensive benchmark designed specifically for multi-viewpoint spatial localization recognition evaluation.
  arXiv  Detail & Related papers  (2025-05-27T17:59:26Z)
• SpatialScore: Towards Unified Evaluation for Multimodal Spatial Understanding [64.15606979785355]
  Multimodal large language models (MLLMs) have achieved impressive success in question-answering tasks, yet their capabilities for spatial understanding are less explored.<n>This work investigates a critical question: do existing MLLMs possess 3D spatial perception and understanding abilities?
  arXiv  Detail & Related papers  (2025-05-22T17:59:03Z)
• Beyond Semantics: Rediscovering Spatial Awareness in Vision-Language Models [13.768090541138571]
  Vision Language Models (VLMs) excel at identifying and describing objects but often fail at spatial reasoning.<n>Our analysis reveals a key imbalance: vision token embeddings have much larger norms than text tokens.<n>Tools uncover that vision tokens and system prompts dominate attention.
  arXiv  Detail & Related papers  (2025-03-21T17:51:14Z)

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.