# VLM2-Bench: A Closer Look at How Well VLMs Implicitly Link Explicit Matching Visual Cues

arXiv: https://arxiv.org/abs/2502.12084 · HTML: https://mlsanity.com/paper/2502.12084/

## Key facts

- Cited by 33 papers in the map (data through 14 Oct 2026).
- Builds on 36 of its 67 references that are in the map.
- First posted on arXiv 17 Feb 2025.

## Builds on (most cited first, 30 of 36)

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Large Language Models are Zero-Shot Reasoners](https://mlsanity.com/paper/2205.11916/) (2022)
- [Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution](https://mlsanity.com/paper/2409.12191/) (2024)
- [LLaVA-OneVision: Easy Visual Task Transfer](https://mlsanity.com/paper/2408.03326/) (2024)
- [InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks](https://mlsanity.com/paper/2312.14238/) (2023)
- [Making the V in VQA Matter: Elevating the Role of Image Understanding in Visual Question Answering](https://mlsanity.com/paper/1612.00837/) (2016)
- [CLIPScore: A Reference-free Evaluation Metric for Image Captioning](https://mlsanity.com/paper/2104.08718/) (2021)
- [MMMU: A Massive Multi-discipline Multimodal Understanding and Reasoning Benchmark for Expert AGI](https://mlsanity.com/paper/2311.16502/) (2023)
- [Learn to Explain: Multimodal Reasoning via Thought Chains for Science Question Answering](https://mlsanity.com/paper/2209.09513/) (2022)
- [FEVER: a large-scale dataset for Fact Extraction and VERification](https://mlsanity.com/paper/1803.05355/) (2018)
- [MM-Vet: Evaluating Large Multimodal Models for Integrated Capabilities](https://mlsanity.com/paper/2308.02490/) (2023)
- [ShareGPT4V: Improving Large Multi-Modal Models with Better Captions](https://mlsanity.com/paper/2311.12793/) (2023)
- [Grounded SAM: Assembling Open-World Models for Diverse Visual Tasks](https://mlsanity.com/paper/2401.14159/) (2024)
- [LLaVA-Video: Video Instruction Tuning With Synthetic Data](https://mlsanity.com/paper/2410.02713/) (2024)
- [ActivityNet-QA: A Dataset for Understanding Complex Web Videos via Question Answering](https://mlsanity.com/paper/1906.02467/) (2019)
- [Long Context Transfer from Language to Vision](https://mlsanity.com/paper/2406.16852/) (2024)
- [Justice or Prejudice? Quantifying Biases in LLM-as-a-Judge](https://mlsanity.com/paper/2410.02736/) (2024)
- [TempCompass: Do Video LLMs Really Understand Videos?](https://mlsanity.com/paper/2403.00476/) (2024)
- [MuirBench: A Comprehensive Benchmark for Robust Multi-image Understanding](https://mlsanity.com/paper/2406.09411/) (2024)
- [OmniEdit: Building Image Editing Generalist Models Through Specialist Supervision](https://mlsanity.com/paper/2411.07199/) (2024)
- [MLLM-Protector: Ensuring MLLM's Safety without Hurting Performance](https://mlsanity.com/paper/2401.02906/) (2024)
- [NaturalBench: Evaluating Vision-Language Models on Natural Adversarial Samples](https://mlsanity.com/paper/2410.14669/) (2024)
- [MMDU: A Multi-Turn Multi-Image Dialog Understanding Benchmark and Instruction-Tuning Dataset for LVLMs](https://mlsanity.com/paper/2406.11833/) (2024)
- [Towards Open-ended Visual Quality Comparison](https://mlsanity.com/paper/2402.16641/) (2024)
- [ImagenHub: Standardizing the evaluation of conditional image generation models](https://mlsanity.com/paper/2310.01596/) (2023)
- [A Survey of Safety on Large Vision-Language Models: Attacks, Defenses and Evaluations](https://mlsanity.com/paper/2502.14881/) (2025)
- [Scaffolding Coordinates to Promote Vision-Language Coordination in Large Multi-Modal Models](https://mlsanity.com/paper/2402.12058/) (2024)
- [Benchmarking Multi-Image Understanding in Vision and Language Models: Perception, Knowledge, Reasoning, and Multi-Hop Reasoning](https://mlsanity.com/paper/2406.12742/) (2024)
- [From Pixels to Insights: A Survey on Automatic Chart Understanding in the Era of Large Foundation Models](https://mlsanity.com/paper/2403.12027/) (2024)
- [Image Textualization: An Automatic Framework for Creating Accurate and Detailed Image Descriptions](https://mlsanity.com/paper/2406.07502/) (2024)

## Built on by (most cited first, 30 of 33)

- [Thinking with Images for Multimodal Reasoning: Foundations, Methods, and Future Frontiers](https://mlsanity.com/paper/2506.23918/) (2025)
- [MetaSpatial: Reinforcing 3D Spatial Reasoning in VLMs for the Metaverse](https://mlsanity.com/paper/2503.18470/) (2025)
- [VScan: Rethinking Visual Token Reduction for Efficient Large Vision-Language Models](https://mlsanity.com/paper/2505.22654/) (2025)
- [Backdoor Cleaning without External Guidance in MLLM Fine-tuning](https://mlsanity.com/paper/2505.16916/) (2025)
- [Beyond Seeing: Evaluating Multimodal LLMs on Tool-Enabled Image Perception, Transformation, and Reasoning](https://mlsanity.com/paper/2510.12712/) (2025)
- [A Personalized Conversational Benchmark: Towards Simulating Personalized Conversations](https://mlsanity.com/paper/2505.14106/) (2025)
- [Seeing from Another Perspective: Evaluating Multi-View Understanding in MLLMs](https://mlsanity.com/paper/2504.15280/) (2025)
- [PROGRESSLM: Towards Progress Reasoning in Vision-Language Models](https://mlsanity.com/paper/2601.15224/) (2026)
- [GEditBench v2: A Human-Aligned Benchmark for General Image Editing](https://mlsanity.com/paper/2603.28547/) (2026)
- [ApET: Approximation-Error Guided Token Compression for Efficient VLMs](https://mlsanity.com/paper/2602.19870/) (2026)
- [MMBoundary: Advancing MLLM Knowledge Boundary Awareness through Reasoning Step Confidence Calibration](https://mlsanity.com/paper/2505.23224/) (2025)
- [MultiVerse: A Multi-Turn Conversation Benchmark for Evaluating Large Vision and Language Models](https://mlsanity.com/paper/2510.16641/) (2025)
- [TAMP: Token-Adaptive Layerwise Pruning in Multimodal Large Language Models](https://mlsanity.com/paper/2504.09897/) (2025)
- [MiCo: Multi-image Contrast for Reinforcement Visual Reasoning](https://mlsanity.com/paper/2506.22434/) (2025)
- [Unveiling the Lack of LVLM Robustness to Fundamental Visual Variations: Why and Path Forward](https://mlsanity.com/paper/2504.16727/) (2025)
- [MR. Judge: Multimodal Reasoner as a Judge](https://mlsanity.com/paper/2505.13403/) (2025)
- [Rethinking Explainability in the Era of Multimodal AI](https://mlsanity.com/paper/2506.13060/) (2025)
- [A Review of 3D Object Detection with Vision-Language Models](https://mlsanity.com/paper/2504.18738/) (2025)
- [CultureCLIP: Empowering CLIP with Cultural Awareness through Synthetic Images and Contextualized Captions](https://mlsanity.com/paper/2507.06210/) (2025)
- [MEENA (PersianMMMU): Multimodal-Multilingual Educational Exams for N-level Assessment](https://mlsanity.com/paper/2508.17290/) (2025)
- [CrossCheck-Bench: Diagnosing Compositional Failures in Multimodal Conflict Resolution](https://mlsanity.com/paper/2511.21717/) (2025)
- [TCAP: Tri-Component Attention Profiling for Unsupervised Backdoor Detection in MLLM Fine-Tuning](https://mlsanity.com/paper/2601.21692/) (2026)
- [ReMoT: Reinforcement Learning with Motion Contrast Triplets](https://mlsanity.com/paper/2603.00461/) (2026)
- [Self-Purification Mitigates Backdoors in Multimodal Diffusion Language Models](https://mlsanity.com/paper/2602.22246/) (2026)
- [Looking Back and Forth: Cross-Image Attention Calibration and Attentive Preference Learning for Multi-Image Hallucination Mitigation](https://mlsanity.com/paper/2603.07048/) (2026)
- [Anatomy of a Lie: A Multi-Stage Diagnostic Framework for Tracing Hallucinations in Vision-Language Models](https://mlsanity.com/paper/2603.15557/) (2026)
- [Seek-and-Solve: Benchmarking MLLMs for Visual Clue-Driven Reasoning in Daily Scenarios](https://mlsanity.com/paper/2604.14041/) (2026)
- [LENS: Adaptive Spatio-Temporal Zooming for Keyframe Sampling in Long-Form Videos](https://mlsanity.com/paper/2607.25125/) (2026)
- [DiffSpot: Can VLMs Spot Fine-Grained Visual Differences in Web Interfaces?](https://mlsanity.com/paper/2605.29615/) (2026)
- [MiSCHiEF: A Benchmark in Minimal-Pairs of Safety and Culture for Holistic Evaluation of Fine-Grained Image-Caption Alignment](https://mlsanity.com/paper/2602.18729/) (2026)

## Abstract (arXiv)

Visually linking matching cues is a crucial ability in daily life, such as identifying the same person in multiple photos based on their cues, even without knowing who they are. Despite the extensive knowledge that vision-language models (VLMs) possess, it remains largely unexplored whether they are capable of performing this fundamental task. To address this, we introduce VLM2-Bench, a benchmark designed to assess whether VLMs can Visually Link Matching cues, with 9 subtasks and over 3,000 test cases. Comprehensive evaluation across twelve VLMs, along with further analysis of various language-side and vision-side prompting methods, leads to a total of eight key findings. We identify critical challenges in models' ability to link visual cues, highlighting a significant performance gap. Based on these insights, we advocate for (i) enhancing core visual capabilities to improve adaptability and reduce reliance on prior knowledge, (ii) establishing clearer principles for integrating language-based reasoning in vision-centric tasks to prevent unnecessary biases, and (iii) shifting vision-text training paradigms toward fostering models' ability to independently structure and infer relationships among visual cues.