VLM$^2$-Bench: A Closer Look at How Well VLMs Implicitly Link Explicit Matching Visual Cues
- URL: http://arxiv.org/abs/2502.12084v1
- Date: Mon, 17 Feb 2025 17:57:50 GMT
- Title: VLM$^2$-Bench: A Closer Look at How Well VLMs Implicitly Link Explicit Matching Visual Cues
- Authors: Jianshu Zhang, Dongyu Yao, Renjie Pi, Paul Pu Liang, Yi R., Fung,
- Abstract summary: VLM$2$-Bench is a benchmark designed to assess whether vision-language models can Visually Link Matching cues.
We identify critical challenges in models' ability to link visual cues, highlighting a significant performance gap where even GPT-4o lags 34.80% behind humans.
- Score: 32.00120712945976
- License:
- Abstract: 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 VLM$^2$-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 eight open-source VLMs and GPT-4o, 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 where even GPT-4o lags 34.80% behind humans. 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.
Related papers
- ChineseSimpleVQA -- "See the World, Discover Knowledge": A Chinese Factuality Evaluation for Large Vision Language Models [38.921977141721605]
We introduce the first factuality-based visual question-answering benchmark in Chinese, named ChineseSimpleVQA.
Key features of this benchmark include a focus on the Chinese language, diverse knowledge types, a multi-hop question construction, high-quality data, static consistency, and easy-to-evaluate through short answers.
arXiv Detail & Related papers (2025-02-17T12:02:23Z) - Why Vision Language Models Struggle with Visual Arithmetic? Towards Enhanced Chart and Geometry Understanding [94.64781599202882]
Vision Language Models (VLMs) have achieved remarkable progress in multimodal tasks.
They often struggle with visual arithmetic, seemingly simple capabilities like object counting or length comparison.
We propose CogAlign, a novel post-training strategy inspired by Piaget's theory of cognitive development.
arXiv Detail & Related papers (2025-02-17T06:54:49Z) - LlamaV-o1: Rethinking Step-by-step Visual Reasoning in LLMs [103.0226977561914]
We propose a comprehensive framework for advancing step-by-step visual reasoning in large language models.
We introduce a visual reasoning benchmark specifically designed to evaluate multi-step reasoning tasks.
Second, we propose a novel metric that assesses visual reasoning quality at the granularity of individual steps.
Third, we present a new multimodal visual reasoning model, named LlamaV-o1, trained using a multi-step curriculum learning approach.
arXiv Detail & Related papers (2025-01-10T18:59:51Z) - Beyond Visual Understanding: Introducing PARROT-360V for Vision Language Model Benchmarking [0.12369742273401668]
We introduce the PARROT-360V Benchmark, a novel and comprehensive benchmark featuring 2487 challenging visual puzzles.
We evaluate leading models: GPT-4o, Claude-3.5-Sonnet, and Gemini-1.5-Pro.
State-of-the-art models scored between 28 to 56 percentage on our benchmark, significantly lower than their performance on popular benchmarks.
arXiv Detail & Related papers (2024-11-20T01:09:21Z) - Prism: A Framework for Decoupling and Assessing the Capabilities of VLMs [83.24033574914425]
We present Prism, an innovative framework designed to disentangle the perception and reasoning processes involved in visual question solving.
Prism comprises two distinct stages: a perception stage that utilizes a VLM to extract and articulate visual information in textual form, and a reasoning stage that formulates responses based on the extracted visual information.
Our analytical framework provides several valuable insights, underscoring Prism's potential as a cost-effective solution for vision-language tasks.
arXiv Detail & Related papers (2024-06-20T17:54:03Z) - Finer: Investigating and Enhancing Fine-Grained Visual Concept Recognition in Large Vision Language Models [57.95366341738857]
In-depth analyses show that instruction-tuned LVLMs exhibit modality gap, showing discrepancy when given textual and visual inputs that correspond to the same concept.
We propose a multiple attribute-centric evaluation benchmark, Finer, to evaluate LVLMs' fine-grained visual comprehension ability and provide significantly improved explainability.
arXiv Detail & Related papers (2024-02-26T05:43:51Z) - Prismatic VLMs: Investigating the Design Space of Visually-Conditioned Language Models [73.40350756742231]
Visually-conditioned language models (VLMs) have seen growing adoption in applications such as visual dialogue, scene understanding, and robotic task planning.
Despite the volume of new releases, key design decisions around image preprocessing, architecture, and optimization are under-explored.
arXiv Detail & Related papers (2024-02-12T18:21:14Z) - Lost in Translation: When GPT-4V(ision) Can't See Eye to Eye with Text.
A Vision-Language-Consistency Analysis of VLLMs and Beyond [7.760124498553333]
We study whether vision-language models execute vision and language tasks consistently or independently.
We introduce a systematic framework that quantifies the capability disparities between different modalities in the multi-modal setting.
We introduce "Vision Description Prompting," a method that effectively improves performance in challenging vision-related tasks.
arXiv Detail & Related papers (2023-10-19T06:45:11Z) - See, Think, Confirm: Interactive Prompting Between Vision and Language
Models for Knowledge-based Visual Reasoning [60.43585179885355]
We propose a novel framework named Interactive Prompting Visual Reasoner (IPVR) for few-shot knowledge-based visual reasoning.
IPVR contains three stages, see, think and confirm.
We conduct experiments on a range of knowledge-based visual reasoning datasets.
arXiv Detail & Related papers (2023-01-12T18:59:50Z)
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.