VCU-Bridge: Hierarchical Visual Connotation Understanding via Semantic Bridging

• URL: http://arxiv.org/abs/2511.18121v1
• Date: Sat, 22 Nov 2025 17:01:03 GMT
• Title: VCU-Bridge: Hierarchical Visual Connotation Understanding via Semantic Bridging
• Authors: Ming Zhong, Yuanlei Wang, Liuzhou Zhang, Arctanx An, Renrui Zhang, Hao Liang, Ming Lu, Ying Shen, Wentao Zhang,
• Abstract summary: We present VCU-Bridge, a framework that operationalizes a human-like hierarchy of visual connotation understanding.<n>Building on this framework, we construct HVCU-Bench, a benchmark for hierarchical visual connotation understanding with explicit, level-wise diagnostics.
• Score: 49.55286536996476
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: While Multimodal Large Language Models (MLLMs) excel on benchmarks, their processing paradigm differs from the human ability to integrate visual information. Unlike humans who naturally bridge details and high-level concepts, models tend to treat these elements in isolation. Prevailing evaluation protocols often decouple low-level perception from high-level reasoning, overlooking their semantic and causal dependencies, which yields non-diagnostic results and obscures performance bottlenecks. We present VCU-Bridge, a framework that operationalizes a human-like hierarchy of visual connotation understanding: multi-level reasoning that advances from foundational perception through semantic bridging to abstract connotation, with an explicit evidence-to-inference trace from concrete cues to abstract conclusions. Building on this framework, we construct HVCU-Bench, a benchmark for hierarchical visual connotation understanding with explicit, level-wise diagnostics. Comprehensive experiments demonstrate a consistent decline in performance as reasoning progresses to higher levels. We further develop a data generation pipeline for instruction tuning guided by Monte Carlo Tree Search (MCTS) and show that strengthening low-level capabilities yields measurable gains at higher levels. Interestingly, it not only improves on HVCU-Bench but also brings benefits on general benchmarks (average +2.53%), especially with substantial gains on MMStar (+7.26%), demonstrating the significance of the hierarchical thinking pattern and its effectiveness in enhancing MLLM capabilities. The project page is at https://vcu-bridge.github.io .

Related papers

• Reconstructing Content via Collaborative Attention to Improve Multimodal Embedding Quality [59.651410243721045]
  CoCoA is a Content reconstruction pre-training paradigm based on Collaborative Attention for multimodal embedding optimization.<n>We introduce an EOS-based reconstruction task, encouraging the model to reconstruct input from the corresponding EOS> embeddings.<n>Experiments on MMEB-V1 demonstrate that CoCoA built upon Qwen2-VL and Qwen2.5-VL significantly improves embedding quality.
  arXiv  Detail & Related papers  (2026-03-02T05:34:45Z)
• Understanding the Fine-Grained Knowledge Capabilities of Vision-Language Models [42.79282247484499]
  Vision-language models (VLMs) have made substantial progress across a wide range of visual question answering benchmarks, spanning visual reasoning, document understanding, and multimodal dialogue.<n>Recent works show that these models trail behind in traditional image classification benchmarks, which test fine-grained visual knowledge.<n>We test a large number of recent VLMs on fine-grained classification benchmarks and identify potential factors in the disconnect between fine-grained knowledge and other vision benchmarks.
  arXiv  Detail & Related papers  (2026-02-19T22:07:29Z)
• Prompt the Unseen: Evaluating Visual-Language Alignment Beyond Supervision [22.712690974750007]
  Vision-Language Models (VLMs) combine a vision encoder and a large language model (LLM) through alignment training.<n>Despite its importance, the projection layer's ability to generalize to unseen visual concepts has not been systematically evaluated.<n>This study introduces a new evaluation framework for alignment generalization.
  arXiv  Detail & Related papers  (2025-08-31T05:00:51Z)
• Re-ranking Reasoning Context with Tree Search Makes Large Vision-Language Models Stronger [51.01841635655944]
  Recent advancements in Large Vision Language Models (LVLMs) have significantly improved performance in Visual Question Answering (VQA) tasks.<n>Existing methods still face challenges, such as the scarcity of knowledge with reasoning examples and erratic responses from retrieved knowledge.<n>We propose a multimodal RAG framework, termed RCTS, which enhances LVLMs by constructing a Reasoning Context-enriched knowledge base and a Tree Search re-ranking method.
  arXiv  Detail & Related papers  (2025-06-09T14:00:57Z)
• Reasoning is All You Need for Video Generalization: A Counterfactual Benchmark with Sub-question Evaluation [19.46864730994867]
  We introduce textbfCOVER (textbfunderlineCOunterfactual textbfunderlineEo textbfunderlineReasoning), a multidimensional multimodal benchmark.<n>It decomposes complex queries into structured sub-questions, enabling fine-grained reasoning analysis.
  arXiv  Detail & Related papers  (2025-03-12T03:25:51Z)
• Painting with Words: Elevating Detailed Image Captioning with Benchmark and Alignment Learning [56.31096024472269]
  We introduce DeCapBench along with a novel metric, DCScore, specifically designed for detailed captioning tasks.<n>DCScore evaluates hallucinations and fine-grained comprehensiveness by deconstructing responses into the smallest self-sufficient units.<n>DeCapBench exhibits a high correlation with VLM arena results on descriptive tasks, surpassing existing benchmarks for vision-language models.
  arXiv  Detail & Related papers  (2025-03-10T22:53:56Z)
• Human Cognitive Benchmarks Reveal Foundational Visual Gaps in MLLMs [65.93003087656754]
  VisFactor is a benchmark that digitizes 20 vision-centric subtests from a well-established cognitive psychology assessment.<n>We evaluate 20 frontier Multimodal Large Language Models (MLLMs) from GPT, Gemini, Claude, LLaMA, Qwen, and SEED families.<n>The best-performing model achieves a score of only 25.19 out of 100, with consistent failures on tasks such as mental rotation, spatial relation inference, and figure-ground discrimination.
  arXiv  Detail & Related papers  (2025-02-23T04:21:32Z)
• Instruction-Guided Fusion of Multi-Layer Visual Features in Large Vision-Language Models [50.98559225639266]
  We investigate the contributions of visual features from different encoder layers using 18 benchmarks spanning 6 task categories.<n>Our findings reveal that multilayer features provide complementary strengths with varying task dependencies, and uniform fusion leads to suboptimal performance.<n>We propose the instruction-guided vision aggregator, a module that dynamically integrates multi-layer visual features based on textual instructions.
  arXiv  Detail & Related papers  (2024-12-26T05:41:31Z)
• Inst-IT: Boosting Multimodal Instance Understanding via Explicit Visual Prompt Instruction Tuning [125.79428219851289]
  Inst-IT is a solution to enhance LMMs in Instance understanding via explicit visual prompt Instruction Tuning.<n>Inst-IT consists of a benchmark to diagnose multimodal instance-level understanding, a large-scale instruction-tuning dataset, and a continuous instruction-tuning training paradigm.
  arXiv  Detail & Related papers  (2024-12-04T18:58:10Z)
• DEAL: Disentangle and Localize Concept-level Explanations for VLMs [10.397502254316645]
  Large pre-trained Vision-Language Models might not be able to identify fine-grained concepts. We propose to DisEnt and Localize (Angle) concept-level explanations for concepts without human annotations. Our empirical results demonstrate that the proposed method significantly improves the concept-level explanations of the model in terms of disentanglability and localizability.
  arXiv  Detail & Related papers  (2024-07-19T15:39:19Z)
• NPHardEval4V: Dynamic Evaluation of Large Vision-Language Models with Effects of Vision [64.83085920775316]
  We introduce NPHardEval4V, a multimodal benchmark suite grounded in four classical NP-hard problems.<n>Each task is presented through a combination of structured visual layouts and textual prompts, designed to assess the ability of LVLMs to perform reasoning under visual-linguistic constraints.<n>Our results show that while these models perform reasonably well on perception-based inputs, they struggle with global optimization, abstraction, and constraint satisfaction.
  arXiv  Detail & Related papers  (2024-03-04T07:10:31Z)

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.