VISION-LANGUAGE MODELS

JEEM: Vision-Language Understanding in Four Arabic Dialects (2026.findings-eacl)

Challenge:	Existing studies have examined whether large language models and vision-language models can harness these sub-character features in Chinese through prompting.
Approach:	They establish a benchmark to evaluate large language models' understanding of visual elements in Chinese characters, including radicals, composition structures, strokes, and stroke counts.
Outcome:	The proposed model exhibits some, but still limited, knowledge of the visual elements in Chinese characters regardless of whether images of characters are provided.

Copied to clipboard

Karima Kadaoui, Hanin Atwany, Hamdan Al-Ali, Abdelrahman Mohamed, Ali Mekky, Sergei Tilga, Natalia Fedorova, Ekaterina Artemova, Hanan Aldarmaki, Yova Kementchedjhieva

HGCLIP: Exploring Vision-Language Models with Graph Representations for Hierarchical Understanding (2025.coling-main)

Challenge:	Existing evaluation datasets feature Western-centric images and English text, while their non-English counterparts are often derived from the latter.
Approach:	They propose to evaluate Vision-Language Models (VLMs) on visual understanding across four Arabic-speaking countries: Jordan, The Emirates, Egypt, and Morocco.
Outcome:	The proposed model underperforms in visual understanding and dialect-specific generation across four Arabic-speaking countries.

Copied to clipboard

Peng Xia, Xingtong Yu, Ming Hu, Lie Ju, Zhiyong Wang, Peibo Duan, Zongyuan Ge

MARCH: Multi-Agent Radiology Clinical Hierarchy for CT Report Generation (2026.acl-short)

Challenge:	Object categories are typically organized into a multi-granularity taxonomic hierarchy . traditional uni-modal approaches focus primarily on image features, revealing limitations in complex scenarios.
Approach:	They propose a framework that combines vision-language models with a deeper exploitation of the hierarchy.
Outcome:	The proposed framework shows significant improvements on 11 diverse visual recognition benchmarks.

Copied to clipboard

Yi Lin, Yihao Ding, Yonghui Wu, Yifan Peng

Text Generation

Challenge:	Automated 3D radiology report generation suffers from clinical hallucinations and lacks the iterative verification characteristic of clinical workflows.
Approach:	They propose a multi-agent framework that emulates the professional hierarchy of radiology departments and assigns specialized roles to distinct agents.
Outcome:	The proposed framework outperforms state-of-the-art models in clinical fidelity and linguistic accuracy on the RadGenome-ChestCT dataset.

Pre-Deployment Advertisement Ranking under Data Scarcity via Context-Aware Criteria Generation with VLMs (2026.acl-industry)

Copied to clipboard

Kyungho Kim, Yeonje Choi, Gyurim Hwang, Sejin Chung, Hongseok Lee, Myeong Ho Song, Yeongho Kim, Sunwoo Kim, Jongha Lee, Juyeon Kim, Kijung Shin

Parameter-free and Accessible Prompt Learning to Enhance Adversarial Robustness for Pre-trained Vision-Language Models (2025.naacl-long)

Challenge:	Existing VLMs perform well on general multimodal tasks, but limited labeled data makes them difficult to apply to real-world business decisions.
Approach:	They propose a new task that aims to rank ads for a target brand prior to deployment . they propose 'brand-specific ad ranking' which uses brand-specific effectiveness .
Outcome:	The proposed task outperforms baselines on 10 brands on real-world advertising data.

Copied to clipboard

Xingran Zhou, Kun Yang, Changtao Miao, Bingyu Hu, Zhuoer Xu, Shiwen Cui, Changhua Meng, Dan Hong

PresentAgent: Multimodal Agent for Presentation Video Generation (2025.emnlp-demos)

Challenge:	Large pre-trained Vision-Language Models (VLMs) have revolutionized downstream vision-language tasks including classification, object detection, and segmentation.
Approach:	They propose to search for text prompts at the word level rather than optimizing continuous textual embeddings to boost adversarial robustness.
Outcome:	Experiments show that the proposed method outperforms hand-engineered prompts with average gains of +4.9% and +5.8%.

Copied to clipboard

Jingwei Shi, Zeyu Zhang, Biao Wu, Yanjie Liang, Meng Fang, Ling Chen, Yang Zhao

GlyphPattern: An Abstract Pattern Recognition for Vision-Language Models (2025.findings-acl)

Challenge:	Existing methods for generating static slides or text summaries are limited to producing narrated presentations.
Approach:	They propose a multimodal agent that transforms long-form documents into narrated presentations.
Outcome:	The present agent produces fully synchronized visual and spoken content that closely mimics human-style presentations.

Copied to clipboard

Zixuan Wu, Yoolim Kim, Carolyn Jane Anderson

VisualWebInstruct: Scaling up Multimodal Instruction Data through Web Search (2025.emnlp-main)

Challenge:	Existing benchmarks for abstract pattern recognition are easier because they do not involve a natural language description of the pattern.
Approach:	They present a dataset that pairs human-written descriptions of visual patterns with three visual presentation styles.
Outcome:	The proposed benchmark pairs human-written and human-verified patterns with three visual presentation styles.

Copied to clipboard

Yiming Jia, Jiachen Li, Xiang Yue, Bo Li, Ping Nie, Kai Zou, Wenhu Chen

Spectra: A Mechanistic Interpretability Library for Vision-Language Models (2026.acl-demo)

Challenge:	Existing vision-language models struggle with reasoning-focused tasks due to the lack of high-quality training data.
Approach:	They propose a new approach that leverages search engines to create a multimodal multimodal dataset . they use a set of 30,000 seed images to extract HTML data from 700K unique URLs .
Outcome:	The proposed model achieves the best known performance on MMMU-Pro (40.7), MathVerse (42.6), and DynaMath (55.7).

Copied to clipboard

Clement Neo, Yongsen Zheng, Kwok-Yan Lam, Luke Ong

Explainability & Interpretability in NLP

Challenge:	Existing interpretability tools for visionlanguage models are limited to activation probing and saving.
Approach:	They propose a library specifically designed for mechanistic interpretability of visionlanguage models that provides unified abstractions for activation patching, attention pattern analysis, and meta-functions across diverse VLM architectures.
Outcome:	The proposed library handles architecture-specific complexities while maintaining a simple, high-level interface.

SCAN: Semantic Document Layout Analysis for Textual and Visual Retrieval-Augmented Generation (2026.findings-eacl)

Copied to clipboard

Nobuhiro Ueda, Yuyang Dong, Krisztián Boros, Daiki Ito, Takuya Sera, Masafumi Oyamada

Can LLMs See Without Pixels? Benchmarking Spatial Intelligence from Textual Descriptions (2026.findings-acl)

Challenge:	Recent research indicates that using VLMs yields better RAG performance, but processing rich documents remains a challenge.
Approach:	They propose a VLM-friendly approach that enhances both textual and visual RAG systems.
Outcome:	The proposed approach outperforms conventional methods and commercial document processing solutions.

Copied to clipboard

Zhongbin Guo, Zhen Yang, Yushan Li, Xinyue Zhang, Wenyu Gao, Jiacheng Wang, Chengzhi Li, Xiangrui Liu, Ping Jian

LLaSA: Large Language and Structured Data Assistant (2025.naacl-long)

Challenge:	Existing advances in Spatial Intelligence rely on vision-Language Models . however, a critical question remains: does spatial understanding originate from visual encoders?
Approach:	They propose to evaluate the SI performance of Large Language Models without pixel-level input.
Outcome:	The proposed benchmark challenges large language models to perform symbolic reasoning rather than visual pattern matching.

Copied to clipboard

Yao Xu, Shizhu He, Jiabei Chen, ZengXiangrong ZengXiangrong, Bingning Wang, Guang Liu, Jun Zhao, Kang Liu

TopViewRS: Vision-Language Models as Top-View Spatial Reasoners (2024.emnlp-main)

Challenge:	Structured knowledge grounding (SKG) tasks are a key part of many NLP applications.
Approach:	They propose a framework for enhancing LLMs' ability to handle structured data . they represent various types of structured data in a unified hypergraph format .
Outcome:	The proposed framework outperforms existing methods on SKG tasks using LoRA finetuning.

Copied to clipboard

Chengzu Li, Caiqi Zhang, Han Zhou, Nigel Collier, Anna Korhonen, Ivan Vulić

EcoDoc: A Cost-Efficient Multimodal Document Processing System for Enterprises Using LLMs (2025.acl-industry)

Challenge:	Top-view perspective is a typical way in which humans read and reason over different types of maps, but spatial reasoning capabilities of modern VLMs in this setup remain unattested and underexplored.
Approach:	They introduce a top-view spatial reasoning dataset and use it to evaluate VLMs across 4 perception and reasoning tasks with different levels of complexity.
Outcome:	The proposed model can understand and reason over spatial relations from the top view and can be controlled at different granularities of spatial reasoning.

Copied to clipboard

Ravi K. Rajendran, Biplob Debnath, Murugan Sankaradass, Srimat Chakradhar

Automating eHMI Action Design with LLMs for Automated Vehicle Communication (2025.findings-emnlp)

Challenge:	Recent advances in Retrieval-Augmented Generation (RAG) frameworks and Vision-Language Models (VLMs) have improved retrieval performance on multimodal documents by processing pages as images.
Approach:	They propose a cost-effective multimodal document processing system that dynamically selects the processing modalities for each page as an image or text based on page characteristics and query intent.
Outcome:	The proposed system reduces average query processing latency by 2.29 and cost by up to 10 . it reduces cost and latency while maintaining high performance on large scale deployments .

Copied to clipboard

Ding Xia, Xinyue Gui, Fan Gao, Dongyuan Li, Mark Colley, Takeo Igarashi

Breach in the Shield: Unveiling the Vulnerabilities of Large Language Models (2026.eacl-long)

Challenge:	Currently, eHMIs employ predefined text messages and manually designed actions to perform these messages . this limits the real-world deployment of ehMIs, where adaptability in dynamic scenarios is essential.
Approach:	They propose a pipeline that integrates large language models and 3D renderers to generate executable actions for controlling eHMIs and rendering action clips.
Outcome:	The proposed pipeline integrates large language models and 3D renderers to generate executable actions for controlling eHMIs and rendering action clips.

Copied to clipboard

Runpeng Dai, Run Yang, Fan Zhou, Hongtu Zhu

HiPrune: Hierarchical Attention for Efficient Token Pruning in Vision-Language Models (2026.findings-acl)

Challenge:	Large Language Models and Vision Language Model (LLMs) have impressive performance across a wide range of tasks, yet remain vulnerable to external and internal perturbations.
Approach:	They propose a stability measure called FI, First order local Influence, which quantifies the sensitivity of individual parameters and input dimensions.
Outcome:	The proposed stability measure measures the sensitivity of parameters and input dimensions across LLMs and VLMs.

Copied to clipboard

Jizhihui Liu, Guangdao Zhu, Feiyi Du, Niu Lian, Jun Li, Bin Chen, Weili Guan, Yaowei Wang

PlanGPT-VL: Enhancing Urban Planning with Domain-Specific Vision-Language Models (2025.emnlp-industry)

Challenge:	Existing methods for visual token pruning lack insight into the intrinsic property of the vision encoder . et al., 2017: 99.3% of task accuracy with only 1/3 of the tokens.
Approach:	They propose a model-agnostic token pruning method that trains without training . they propose 'HiPrune' method which prunes visual tokens according to their attention .
Outcome:	The proposed method achieves 99.3% of task accuracy with only 1/3 of the tokens . it reduces inference FLOPs by 58.7% and maintains 99.99% accuracy with 2/9 tokens.

Copied to clipboard

He Zhu, Junyou Su, Minxin Chen, Wen Wang, Yijie Deng, Guanhua Chen, Wenjia Zhang

Distilling Cross-Modal Knowledge into Domain-Specific Retrievers for Enhanced Industrial Document Understanding (2025.emnlp-industry)

Challenge:	Existing Vision-Language Models (VLMs) fail to analyze planning maps . specialized visual representations of land use zones, transportation networks, and development policies are needed to interpret complex planning maps.
Approach:	They propose a domain-specific VLM tailored for urban planning maps that employs three innovations: PlanAnno-V framework for high-quality VQA data synthesis, Critical Point Thinking (CPT) and PlanBench-V benchmark for systematic evaluation.
Outcome:	The new model outperforms general-purpose VLMs on planning map interpretation tasks.

Copied to clipboard

Jinhyeong Lim, Jeongwan Shin, Seeun Lee, Seongdeok Kim, Joungsu Choi, Jongbae Kim, Chun Hwan Jung, Youjin Kang

Unraveling and Mitigating Safety Alignment Degradation of Vision-Language Models (2025.findings-acl)

Challenge:	Retrieval-Augmented Generation (RAG) has shown strong performance in open-domain tasks, but its effectiveness in industrial domains is limited by a lack of domain understanding and document structural elements (DSE) such as tables, figures, charts, and formula.
Approach:	They propose a knowledge distillation framework that transfers complementary knowledge from Large Language Models and Vision-Language Models into a compact domain-specific retriever.
Outcome:	The proposed framework outperforms larger baselines while requiring significantly less computational complexity.

Copied to clipboard

Qin Liu, Chao Shang, Ling Liu, Nikolaos Pappas, Jie Ma, Neha Anna John, Srikanth Doss, Lluis Marquez, Miguel Ballesteros, Yassine Benajiba

Red Teaming Visual Language Models (2024.findings-acl)

Challenge:	LLaVA-7B demonstrated a decline in safety alignment ability on multi-modal inputs compared to its LLM backbone.
Approach:	They propose a method to recover alignment ability from LLM backbone while preserving functional capabilities of VLMs.
Outcome:	The proposed framework recovers alignment ability that is inherent in the LLM backbone with minimal impact on fluency and linguistic capabilities of pre-trained VLMs.

Copied to clipboard

Mukai Li, Lei Li, Yuwei Yin, Masood Ahmed, Zhenguang Liu, Qi Liu

Attribution-Guided Multi-Object Hallucination and Bias Detection in Vision-Language Models (2026.eacl-long)

Challenge:	VLMs (Vision-Language Models) can be induced to generate harmful or inaccurate content through specific test cases.
Approach:	They propose a red teaming dataset which encompasses 12 subtasks under 4 primary aspects (faithfulness, privacy, safety, fairness) this dataset is the first to benchmark current VLMs in terms of these 4 aspects .
Outcome:	The proposed dataset shows that 10 open-source VLMs struggle with red teaming in different degrees and have up to 31% performance gap with GPT-4V.

Copied to clipboard

Sirat Samyoun, Yingtai Xiao, Jian Du

Decompose and Compare Consistency: Measuring VLMs’ Answer Reliability via Task-Decomposition Consistency Comparison (2024.emnlp-main)

Challenge:	Existing methods struggle with multi-object grounding because language priors dominate visual evidence, causing hallucinated or biased objects to produce attention distributions or similarity scores nearly indistinguishable from those of real objects.
Approach:	They propose a Shapley value-based attribution framework that uses Kernel SHAP and multi-layer fusion to detect hallucinated and biased objects.
Outcome:	Evaluated on ADE and COCO datasets, SHAPLENS improves hallucination detection accuracy by 8–12% and F1 by 10–14% over baselines.

Copied to clipboard

Qian Yang, Weixiang Yan, Aishwarya Agrawal

Look Less, Reason More: Rollout-Guided Adaptive Pixel-Space Reasoning (2026.acl-long)

Challenge:	Existing methods for estimating uncertainty using answer likelihoods or prompt-based confidence generation often suffer from overconfidence and confirmation biases.
Approach:	They propose to use Decompose and Compare Consistency (DeCC) to measure the reliability of a VLM's direct answer and indirect answers by decomposing the question into sub-questions and reasoning over the sub-answers.
Outcome:	Experiments on six vision-language tasks with three VLMs show that DeCC achieves better correlation with task accuracy compared to existing methods.

Copied to clipboard

Xuchen Li, Xuzhao Li, Jiahui Gao, Renjie Pi, Shiyu Hu, Wentao Zhang

CIVET: Systematic Evaluation of Understanding in VLMs (2025.findings-emnlp)

Challenge:	Recent work has shown promise by incorporating pixel-level visual information into the reasoning process, enabling VLMs to access high-resolution visual details during their thought process.
Approach:	They propose a framework that dynamically determines necessary pixel-level operations based on the input query.
Outcome:	The proposed model achieves 73.4% accuracy on HR-Bench 4K while maintaining a tool usage ratio of only 20.1%, improving accuracy and reducing tool usage by 66.5% compared to the previous methods.

Copied to clipboard

Massimo Rizzoli, Simone Alghisi, Olha Khomyn, Gabriel Roccabruna, Seyed Mahed Mousavi, Giuseppe Riccardi

Challenge:	Current Vision-Language Models can accurately recognize only a limited set of basic object properties; 3) they struggle to understand basic relations among objects.
Approach:	They propose a framework that evaluates VLMs on exhaustive sets of stimuli, free from annotation noise, dataset-specific biases, and uncontrolled scene complexity.
Outcome:	The proposed framework addresses the lack of standardized systematic evaluation for assessing VLMs’ understanding, enabling researchers to test hypotheses with statistical rigor.

AdaV: Adaptive Text-visual Redirection for Vision-Language Models (2025.findings-acl)

Copied to clipboard

Jiayi Han, Liang Du, Yiwen Wu, Guanming Liang, Xiangguo Zhou, Weibo Zheng, Donghong Han, Zixun Sun

World to Code: Multi-modal Data Generation via Self-Instructed Compositional Captioning and Filtering (2024.emnlp-main)

Challenge:	Vision-language models often generate excessive visual tokens, leading to poor performance . a novel training-free visual token pruning method is proposed to improve performance despite the computational cost associated with VLMs.
Approach:	They propose a training-free visual token pruning method that reduces biased token pruning . they plan to open-source the code upon publication .
Outcome:	The proposed method reduces biased token pruning and enhances model robustness with limited visual token budget.

Copied to clipboard

Jiacong Wang, Bohong Wu, Haiyong Jiang, Zhou Xun, Xin Xiao, Haoyuan Guo, Jun Xiao

WikiSeeker: Rethinking the Role of Vision-Language Models in Knowledge-Based Visual Question Answering (2026.findings-acl)

Challenge:	Recent advances in Vision-Language Models and the scarcity of high-quality multi-modal alignment data have inspired numerous researches on synthetic VLM data generation.
Approach:	They propose a multi-modal data construction pipeline that organizes the final output into a Python code format.
Outcome:	The proposed pipeline improves visual question answering and visual grounding benchmarks across different VLMs.

Copied to clipboard

Yingjian Zhu, Xinming Wang, Kun Ding, Ying Wang, Bin Fan, Shiming Xiang

The Art of Saying "Maybe": A Conformal Lens for Uncertainty Benchmarking in VLMs (2026.findings-eacl)

Challenge:	Existing methods for Knowledge-Based Visual Question Answering rely on images as the retrieval key, and often overlook or misplace the role of Vision-Language Models (VLMs)
Approach:	They propose a multi-modal RAG framework that assigns VLMs two specialized agents: a Refiner and an Inspector.
Outcome:	Experiments on EVQA, InfoSeek, and M2KR show that the proposed framework achieves state-of-the-art performance with significant improvements in both retrieval accuracy and answer quality.

Copied to clipboard

Asif Azad, Mohammad Sadat Hossain, MD Sadik Hossain Shanto, M Saifur Rahman, Md Rizwan Parvez

OS-Genesis: Automating GUI Agent Trajectory Construction via Reverse Task Synthesis (2025.acl-long)

Challenge:	Recent advances in large vision-language models have led to remarkable progress in complex visual understanding across scientific and reasoning tasks.
Approach:	They evaluate 18 state-of-the-art vision-language models across 6 multimodal datasets with 3 distinct scoring functions and develop instruction-guided likelihood proxies for closed-source models lacking token-level logprob access.
Outcome:	The proposed model is able to achieve higher accuracy on multimodal benchmarks while performing poorer on reasoning tasks.

Copied to clipboard

Qiushi Sun, Kanzhi Cheng, Zichen Ding, Chuanyang Jin, Yian Wang, Fangzhi Xu, Zhenyu Wu, Chengyou Jia, Liheng Chen, Zhoumianze Liu, Ben Kao, Guohao Li, Junxian He, Yu Qiao, Zhiyong Wu

POP: Prefill-Only Pruning for Efficient Large Model Inference (2026.findings-acl)

Challenge:	Graphical User Interface (GUI) agents powered by Vision-Language Models (VLMs) have demonstrated human-like computer control capability.
Approach:	They propose a GUI data synthesis pipeline that reverse engineers GUI trajectory construction process by executing pre-defined tasks.
Outcome:	The proposed GUI data synthesis pipeline overcomes the bottlenecks of previous methods that rely on pre-defined tasks and limited data diversity.

Copied to clipboard

Junhui He, Zhihui Fu, Jun Wang, Qingan Li

Green & Sustainable NLP

Challenge:	Existing structured pruning methods suffer from significant accuracy degradation . Existing pruning methods are expensive and require specialized hardware and kernels to perform .
Approach:	They propose a stage-agnostic pruning approach that overlooks asymmetric roles between prefill and decode stages.
Outcome:	The proposed pruning approach achieves 1.37 speedup in prefill latency with minimal performance loss.

RoD-TAL: A Benchmark for Answering Questions in Romanian Driving License Exams (2026.findings-eacl)

Copied to clipboard

Andrei Vlad Man, Răzvan-Alexandru Smădu, Cristian-George Craciun, Dumitru-Clementin Cercel, Florin Pop, Mihaela-Claudia Cercel

Iterative Self-Correction for Text-Driven Person Re-Identification with Large Vision-Language Models (2026.findings-acl)

Challenge:	a growing need for tools that support legal education, especially in under-resourced languages such as Romanian . we evaluate the capabilities of large language models and vision-language models in legal education .
Approach:	They evaluate the capabilities of Large Language Models and Vision-Language Models in Romanian driving law through textual and visual question-answering tasks.
Outcome:	The proposed model improves retrieval performance and QA accuracy in Romanian driving tests.

Copied to clipboard

Guijin Luo, Zequn Xie, Sihang Cai, Chuxin Wang, Zhou Zhao, Yixuan Tang

Do Images Speak Louder than Words? Investigating the Effect of Textual Misinformation in VLMs (2026.eacl-long)

Challenge:	Existing methods for Person Re-Identification (ReID) adopt a static "one-pass" paradigm, converting images to text once for retrieval.
Approach:	They propose a framework that reformulates ReID as an iterative "Think-and-Refine" process.
Outcome:	The proposed framework outperforms state-of-the-art methods in complex occlusion scenarios.

Copied to clipboard

Chi Zhang, Wenxuan Ding, Jiale Liu, Mingrui Wu, Qingyun Wu, Ray Mooney

Self-Correction is More than Refinement: A Learning Framework for Visual and Language Reasoning Tasks (2025.findings-acl)

Challenge:	Existing studies have shown that Vision-Language Models have robust multimodal reasoning capabilities, but their robustness against textual misinformation remains under-explored.
Approach:	They propose to use visual-question-answering (VQA) prompts to generate persuasive prompts that deliberately conflict with visual evidence to test their models.
Outcome:	The proposed framework shows that models are vulnerable to misleading prompts, and show an average performance drop of over 48.2% after only one round of persuasive conversation.

Copied to clipboard

Jiayi He, Hehai Lin, Qingyun Wang, Yi R. Fung, Heng Ji

FlightGPT: Towards Generalizable and Interpretable UAV Vision-and-Language Navigation with Vision-Language Models (2025.emnlp-main)

Challenge:	Large Language Models (LLMs) have shown remarkable abilities, but they invariably generate flawed responses.
Approach:	They propose a self-correction approach that instructs VLMs to refine their outputs by allowing them to learn from their self-generated self-reference data without external feedback.
Outcome:	The proposed approach enables VLMs to learn from their self-generated self-correction data without relying on external feedback, facilitating self-improvement.

Copied to clipboard

Hengxing Cai, Jinhan Dong, Jingjun Tan, Jingcheng Deng, Sihang Li, Zhifeng Gao, Haidong Wang, Zicheng Su, Agachai Sumalee, Renxin Zhong

Grounding Visual Illusions in Language: Do Vision-Language Models Perceive Illusions Like Humans? (2023.emnlp-main)

Challenge:	Existing methods for vision-and-language navigation struggle with insufficient multimodal fusion, weak generalization, and poor interpretability.
Approach:	They propose a framework for UAV vision-and-language navigation that integrates natural language instructions with visual observations to improve multimodal fusion and interpretability.
Outcome:	The proposed framework achieves state-of-the-art performance across all scenarios, with a 9.22% higher success rate than the strongest baseline in unseen environments.

Copied to clipboard

Yichi Zhang, Jiayi Pan, Yuchen Zhou, Rui Pan, Joyce Chai

DiscoSG: Towards Discourse-Level Text Scene Graph Parsing through Iterative Graph Refinement (2025.emnlp-main)

Challenge:	Visual illusions are a phenomenon that is often seen in human perception but are not always faithful to the physical world.
Approach:	They build a dataset containing five types of visual illusions and formulate four tasks to examine visual illusion in state-of-the-art VLMs.
Outcome:	The proposed dataset reveals that larger models are closer to human perception and more susceptible to visual illusions.

Copied to clipboard

Shaoqing Lin, Chong Teng, Fei Li, Donghong Ji, Lizhen Qu, Zhuang Li

Advancement in Graph Understanding: A Multimodal Benchmark and Fine-Tuning of Vision-Language Models (2024.acl-long)

Challenge:	Current approaches typically merge sentence-level parsing outputs for discourse input, resulting in fragmented graphs and degraded downstream performance.
Approach:	They propose a task for discourse-level text scene graph parsing that merges sentence-level outputs for discourse input and propose 'DiscoSG' a dataset of 400 expert-annotated and 8,430 synthesised multi-sentence caption-graph pairs is used to test the new task.
Outcome:	The proposed task improves SPICE by 30% over the baseline while achieving 86 faster inference than existing models.

Copied to clipboard

Qihang Ai, Jiafan Li, Jincheng Dai, Jianwu Zhou, Lemao Liu, Haiyun Jiang, Shuming Shi

Lang2Act: Fine-Grained Visual Reasoning through Self-Emergent Linguistic Toolchains (2026.findings-acl)

Challenge:	Graph data organizes complex relationships and interactions between objects . Graph neural networks (GNNs) are becoming more popular in graph learning .
Approach:	They propose a new paradigm for interactive and instructional graph data understanding and reasoning . they first evaluate the capabilities of public VLMs in graph learning from multiple aspects .
Outcome:	The proposed model achieves an accuracy increase of 5%-15% compared to baseline models . the best-performing model achieve scores comparable to Gemini in GPT-asissted Evaluation .

Copied to clipboard

Yuqi Xiong, Chunyi Peng, Zhipeng Xu, Zhenghao Liu, Zulong Chen, Yukun Yan, Shuo Wang, Yu Gu, Ge Yu

AbsVis – Benchmarking How Humans and Vision-Language Models “See” Abstract Concepts in Images (2025.emnlp-main)

Challenge:	Existing frameworks depend on rigid, pre-defined external tools to extend perceptual capabilities of VLMs.
Approach:	They propose a framework that leverages self-emergent linguistic toolchains to enhance visual perception and reasoning.
Outcome:	The proposed framework improves the visual perception capabilities of large language models by incorporating external visual documents to address a given query.

Copied to clipboard

Tarun Tater, Diego Frassinelli, Sabine Schulte im Walde

Explainability & Interpretability in NLP

Challenge:	Abstract concepts like mercy and peace lack clear visual grounding, and therefore challenge humans and models to provide suitable image representations.
Approach:	They propose a dataset of 675 images annotated with 14,175 concept–explanation attributions from humans and two Vision-Language Models where each concept is accompanied by a textual explanation.
Outcome:	The proposed dataset compares human and VLM attributions in terms of diversity, abstractness, and alignment, and shows that overlapping concepts are most preferred.

Does Acceleration Cause Hidden Instability in Vision Language Models? Uncovering Instance-Level Divergence Through a Large-Scale Empirical Study (2025.emnlp-main)

Copied to clipboard

Yizheng Sun, Hao Li, Chang Xu, Hongpeng Zhou, Chenghua Lin, Riza Batista-Navarro, Jingyuan Sun

OS-Sentinel: Towards Safety-Enhanced Mobile GUI Agents via Hybrid Validation in Realistic Workflows (2026.acl-long)

Challenge:	Current acceleration evaluations focus on minimal overall performance degradation . however, accelerated models can exhibit significant changes in instance-level predictions .
Approach:	They investigate whether accelerated vision-Language Models can still give the same answers as before . they found that accelerated models changed original answers up to 20% of the time .
Outcome:	The results show that accelerated models changed their original answers up to 20% of the time.

Copied to clipboard

Qiushi Sun, Mukai Li, Zhoumianze Liu, Zhihui Xie, Fangzhi Xu, Zhangyue Yin, Kanzhi Cheng, Zehao Li, Zichen Ding, Qi Liu, Zhiyong Wu, Zhuosheng Zhang, Ben Kao, Lingpeng Kong

Challenge:	Existing methods for detecting unsafe mobile GUI agents are underexplored.
Approach:	They propose a mobile agent safety detection framework that integrates a formal verifier and a VLM-based contextual judge to detect system-level violations.
Outcome:	The proposed framework achieves 10%–30% improvements over existing approaches across multiple metrics.

“I See What You Did There”: Can Large Vision-Language Models Understand Multimodal Puns? (2026.acl-long)

Copied to clipboard

Naen Xu, Jiayi Sheng, Changjiang Li, Chunyi Zhou, Yuyuan Li, Tianyu Du, Jun Wang, Zhihui Fu, Jinbao Li, Shouling Ji

Sparrow: Text-Anchored Window Attention with Visual-Semantic Glimpsing for Speculative Decoding in Video LLMs (2026.acl-long)

Challenge:	Puns are a common form of rhetorical wordplay that exploits polysemy and phonetic similarity to create humor.
Approach:	They propose a multimodal pun generation pipeline and a model to evaluate their understanding of puns.
Outcome:	The proposed benchmark improves the understanding of multimodal puns by 16.5% in the F1 test.

Copied to clipboard

Libo Zhang, Zhaoning Zhang, null Hongwanyang, Peng Qiao, Dongsheng Li

Value-Spectrum: Quantifying Preferences of Vision-Language Models via Value Decomposition in Social Media Contexts (2025.acl-long)

Challenge:	Existing speculative decoding models face performance collapse due to key-value cache explosion and context window mismatches.
Approach:	They propose a framework that offloads visual computation to the target model by using hidden state reuse.
Outcome:	The proposed framework achieves an average speedup of 2.82x even with 25k visual tokens .

Copied to clipboard

Jingxuan Li, Yuning Yang, Shengqi Yang, Linfan Zhang, Ying Nian Wu

MuSe: Multi-Stage Graph Reasoning via Vision-Language Models (2026.acl-long)

Challenge:	Recent advances in Vision-Language Models (VLMs) have broadened the scope of multimodal applications, but evaluations often neglect abstract dimensions such as personality traits and human values.
Approach:	They propose a Visual Question Answering (VQA) benchmark based on Schwartz’s value dimensions that capture core human values guiding people’s preferences and actions.
Outcome:	The proposed model can be used to evaluate visual question answering (VQA) tasks and to simulate diverse personas.

Copied to clipboard

Guanyu Wang, Xu Chu, Zhijie Tan, Xinrong Chen, Tong Mo, Weiping Li

Is GPT-4V (ision) All You Need for Automating Academic Data Visualization? Exploring Vision-Language Models’ Capability in Reproducing Academic Charts (2024.findings-emnlp)

Challenge:	Graph Neural Networks (GNNs) and graph transformers are inadequate for tasks with limited generalization.
Approach:	They propose a multi-stage graph reasoning framework based on vision-language models that incrementally samples and visualizes task-relevant subgraphs.
Outcome:	The proposed framework outperforms existing benchmarks in Graph-related tasks.

Copied to clipboard

Zhehao Zhang, Weicheng Ma, Soroush Vosoughi

EchoVLM: Dynamic Mixture-of-Experts Vision-Language Model for Universal Ultrasound Intelligence (2026.acl-long)

Challenge:	Using Vision-Language Models (VLMs) for data visualizations requires significant time and expertise in both data management and graphic design.
Approach:	They propose a dataset comprising 2525 high-resolution data visualization figures with captions from AI conferences, extracted directly from source codes.
Outcome:	The proposed model outperforms open-source models in reproducing complex charts while using Chain-of-Thought prompting.

Copied to clipboard

Chaoyin She, Ruifang Lu, Lida Chen, Wei Wang, Qinghua Huang

Exploring How Generative MLLMs Perceive More Than CLIP with the Same Vision Encoder (2025.acl-long)

Challenge:	Ultrasound is the preferred early cancer screening modality due to non-ionizing radiation, cost-effectiveness, and real-time imaging.
Approach:	They propose to use ultrasound-tailored vision-language models with a mixture-of-experts architecture to train ultrasound-specific knowledge across seven anatomical systems.
Outcome:	The proposed model outperforms Qwen2-VL by 7.58 BLEU-1 and 3.45 ROUGE-1 points in report generation.

Copied to clipboard

Siting Li, Pang Wei Koh, Simon Shaolei Du

Vision-Language Models Mistake Head Orientation for Gaze Direction: Nonverbal Conversation Cues (2026.findings-acl)

Challenge:	Recent studies show that CLIP models struggle with visual reasoning tasks . despite the success of Contrastive Language-Image Pretraining, there are still limitations .
Approach:	They propose to use a visual encoder to train CLIP-like models for fine-grained visual reasoning tasks.
Outcome:	The proposed models outperform CLIP-like encoders in visual reasoning tasks . the study highlights the importance of VLM architectural choices .

Copied to clipboard

Zory Zhang, Pinyuan Feng, Bingyang Wang, Tianwei Zhao, Suyang Yu, Qingying Gao, Hokin Deng, Ziqiao Ma, Yijiang Li, Dezhi Luo

Natural Language Interfaces

Challenge:	Where someone looks is a nonverbal communication cue that children and adults readily use.
Approach:	They used 1,360 real-world photos to construct evaluation stimuli for Vision-Language Models (VLMs) they found a substantial performance gap between VLMs and humans .
Outcome:	The proposed model outperforms existing models in predicting gaze direction using head orientation rather than eye appearance.

ProgressLM: Towards Progress Reasoning in Vision-Language Models (2026.acl-long)

Copied to clipboard

Jianshu Zhang, Chengxuan Qian, Haosen Sun, Haoran Lu, Dingcheng Wang, Letian Xue, Han Liu

Can Vision-Language Models Solve Visual Math Equations? (2025.emnlp-main)

Challenge:	Existing models for task progress estimation lack long-horizon and dynamic reasoning . estimating how much of a task has been completed requires long-term reasoning based on partial information.
Approach:	They propose a benchmark for evaluating progress reasoning from a single observation . they instantiate a two-stage paradigm that combines episodic retrieval with mental simulation .
Outcome:	The proposed benchmark improves on 14 VLMs on a small scale and shows common failure patterns.

Copied to clipboard

Monjoy Narayan Choudhury, Junling Wang, Yifan Hou, Mrinmaya Sachan

3D-Aware Vision-Language Models Fine-Tuning with Geometric Distillation (2025.findings-emnlp)

Challenge:	Vision-Language Models (VLMs) perform well on textual equations, but fail on visually grounded counterparts.
Approach:	They propose to decompose visual equation solving into symbolic equation solving and visual recognition into two core components to understand this gap.
Outcome:	The proposed models perform well on textual equations, but fail on visual grounded ones.

Copied to clipboard

Seonho Lee, Jiho Choi, Inha Kang, Jiwook Kim, Junsung Park, Hyunjung Shim

AgentThink: A Unified Framework for Tool-Augmented Chain-of-Thought Reasoning in Vision-Language Models for Autonomous Driving (2025.findings-emnlp)

Challenge:	Vision-Language Models (VLMs) have shown remarkable performance on diverse visual and linguistic tasks, yet they remain limited in their understanding of 3D spatial structures.
Approach:	They propose a framework that injects human-inspired geometric cues into pretrained VLMs . they use sparse correspondences, relative depth relations and dense cost volumes .
Outcome:	The proposed framework outperforms existing methods on vision-language reasoning and 3D perception benchmarks.

Copied to clipboard

Kangan Qian, Sicong Jiang, Yang Zhong, Ziang Luo, Zilin Huang, Tianze Zhu, Kun Jiang, Mengmeng Yang, Zheng Fu, Jinyu Miao, Yining Shi, He Zhe Lim, Li Liu, Tianbao Zhou, Hongyi Wang, Huang Yu, Yifei Hu, Guang Li, Guang Chen, Hao Ye, Lijun Sun, Diange Yang

What Do VLMs NOTICE? A Mechanistic Interpretability Pipeline for Gaussian-Noise-free Text-Image Corruption and Evaluation (2025.naacl-long)

Challenge:	Vision-Language Models struggle with hallucinations, inefficient reasoning, and limited real-world validation hinders accurate perception and robust step-by-step reasoning.
Approach:	AgentThink integrates Chain-of-Thought reasoning with dynamic, agent-style tool invocation for autonomous driving tasks.
Outcome:	Experiments on the DriveLMM-o1 benchmark show AgentThink significantly boosts overall reasoning scores by 53.91% and enhances answer accuracy by 33.54% .

Copied to clipboard

Michal Golovanevsky, William Rudman, Vedant Palit, Carsten Eickhoff, Ritambhara Singh

Investigating Cross-Modal Skill Injection: Scenarios, Methods, and Hyperparameters (2026.acl-long)

Challenge:	Vision-Language Models (VLMs) have gained prominence due to their success in solving complex cross-modal tasks.
Approach:	They propose a Gaussian-Noise-free pipeline for mechanistic interpretability in VLMs that introduces Semantic Image Pairs corruption, the first visual counterpart to Symmetric Token Replacement for text.
Outcome:	The proposed pipeline identifies a set of “universal attention heads” in BLIP and LLaVA that consistently contribute across different tasks and modalities.

Copied to clipboard

Zhiyu Xu, Lean Wang, Yuanxin Liu, Lei Li, Hao Zhou, Fandong Meng, Jie Zhou, Xu Sun

Large Language Models Are Natural Video Popularity Predictors (2025.findings-acl)

Challenge:	Existing research lacks systematic analysis of the applicability and methodology of cross-modal skill injection.
Approach:	They investigate the applicability and methodology of cross-modal skill injection by integrating a domain-expert LLM into a VLM.
Outcome:	The proposed method enables transfer of domain-specific expertise from Large Language Models (LLMs) to VLMs without incurring additional training data requirements or significant computational overhead.

Copied to clipboard

Pratik Kayal, Pascal Mettes, Nima Dehmamy, Minsu Park

Prompting Scientific Names for Zero-Shot Species Recognition (2023.emnlp-main)

Challenge:	Large Language Models (LLMs) can better capture cultural and social factors such as viewing intensity and geographic spread of video content.
Approach:	They propose to use Large Language Models to capture cultural and social factors that influence video popularity and generate interpretable, attribute-based explanations.
Outcome:	The proposed model captures both engagement intensity and geographic spread on 13,639 popular videos, while the neural network's predictions reach 82% without fine-tuning.

Copied to clipboard

Shubham Parashar, Zhiqiu Lin, Yanan Li, Shu Kong

BiasDora: Exploring Hidden Biased Associations in Vision-Language Models (2024.findings-emnlp)

Challenge:	We use visionlanguage models (VLMs) to recognize images of common objects in a zero-shot fashion, but it is underexplored how to use CLIP for zero- shot species recognition of highly specialized concepts.
Approach:	They propose a method to translate scientific names to common English names and use them in prompts to improve their performance.
Outcome:	The proposed method performs poorly for species recognition with prompts that use scientific names, e.g., “a photo of Lepus Timidus” (which is a scientific name in Latin) and additionally use them in the prompts.

Copied to clipboard

Chahat Raj, Anjishnu Mukherjee, Aylin Caliskan, Antonios Anastasopoulos, Ziwei Zhu

AlanaVLM: A Multimodal Embodied AI Foundation Model for Egocentric Video Understanding (2024.findings-emnlp)

Challenge:	Existing studies on social biases focus on a limited set of documented associations, such as gender-profession or race-crime.
Approach:	They propose to examine hidden, implicit bias associations across 9 bias dimensions by probing VLMs to uncover hidden, unexamined associations.
Outcome:	The proposed methods reveal that biases vary in negativity, toxicity, and extremity.

Copied to clipboard

Alessandro Suglia, Claudio Greco, Katie Baker, Jose Part, Ioannis Papaioannou, Arash Eshghi, Ioannis Konstas, Oliver Lemon

AICA-Bench: Holistically Examining the Capabilities of VLMs in Affective Image Content Analysis (2026.findings-acl)

Challenge:	Current Vision-Language Models (VLMs) focus on third-person view videos, neglecting the richness of egocentric perceptual experience.
Approach:	They propose to use the Egocentric Video Understanding Dataset (EVUD) to train VLMs on video captioning and question answering tasks specific to egocentric videos.
Outcome:	The proposed model outperforms open-source models including strong Socratic models using GPT-4 as a planner by 3.6% and outperformed Claude 3 and Gemini Pro Vision 1.0.

Copied to clipboard

Dong She, Xianrong Yao, Liqun Chen, Jinghe Yu, Yang Gao, Zhanpeng Jin

Sentiment Analysis

Challenge:	Recent studies have focused on factual correctness, semantic grounding, visual reasoning, or multimodal large language models.
Approach:	They propose a benchmark to assess AICA, which integrates perception, reasoning, and generation into a unified framework.
Outcome:	The proposed framework corrects intensity errors and significantly enhances descriptive depth.

Prometheus-Vision: Vision-Language Model as a Judge for Fine-Grained Evaluation (2024.findings-acl)

Copied to clipboard

Seongyun Lee, Seungone Kim, Sue Park, Geewook Kim, Minjoon Seo

Efficient Architectures for High Resolution Vision-Language Models (2025.coling-main)

Challenge:	Existing metrics for long-form text outputs are prone to biases and scaling up is expensive.
Approach:	They propose to evaluate VLMs with VLM feedback dataset . they use 15K customized score rubrics to train Prometheus-Vision .
Outcome:	The proposed model shows highest correlation with human evaluators and GPT-4V among open-source models.

Copied to clipboard

Miguel Carvalho, Bruno Martins

Vision-Free Retrieval: Rethinking Multimodal Search with Textual Scene Descriptions (2025.emnlp-main)

Challenge:	Recent advances in vision-Language Models (VLMs) have limited accuracy of fine details within high resolution images, which limits performance in multiple tasks.
Approach:	They propose a new architecture that efficiently processes high-resolution images while training fewer parameters than similarly sized VLMs.
Outcome:	The proposed architecture achieves high efficiency while maintaining strong performance in tasks that require fine-grained image understanding and/or handling of scene-text.

Copied to clipboard

Ioanna Ntinou, Alexandros Xenos, Yassine Ouali, Adrian Bulat, Georgios Tzimiropoulos

More Than Meets the Eye: Measuring the Semiotic Gap in Vision-Language Models via Semantic Anchorage (2026.acl-long)

Challenge:	Contrastively trained Vision-Language Models exhibit shallow language understanding, manifesting bag-of-words behaviour.
Approach:	They propose a vision-free, single-encoder retrieval pipeline to replace traditional text-to-image retrieval paradigm with structured image descriptions.
Outcome:	The proposed approach reduces the modality gap and improves compositionality and performance on short and long caption queries.

Copied to clipboard

Wei He

Can Vision-Language Models Evaluate Handwritten Math? (2025.acl-long)

Challenge:	Vision-Language Models excel at photorealistic generation, but struggle to represent abstract meanings.
Approach:	They propose a benchmark that replaces high-fidelity visual detail with schematic iconicity by generating paired, sense-anchored visualizations for literal and idiomatic readings.
Outcome:	The proposed benchmark replaces high-fidelity visual detail with schematic iconicity by generating paired, sense-anchored visualizations for literal and idiomatic readings.

Copied to clipboard

Oikantik Nath, Hanani Bathina, Mohammed Safi Ur Rahman Khan, Mitesh M Khapra

CapArena: Benchmarking and Analyzing Detailed Image Captioning in the LLM Era (2025.findings-acl)

Challenge:	Recent advances in Vision-Language Models (VLMs) have significantly enhanced the ability to interpret both textual and visual data.
Approach:	They propose a benchmark to assess VLMs’ ability to detect, localize and correct errors in handwritten mathematical content.
Outcome:	The proposed benchmark covers over 2,200 handwritten math solutions from 609 manually curated problems from grades 7-12 with intentionally introduced perturbations.

Copied to clipboard

Kanzhi Cheng, Wenpo Song, Jiaxin Fan, Zheng Ma, Qiushi Sun, Fangzhi Xu, Chenyang Yan, Nuo Chen, Jianbing Zhang, Jiajun Chen

VLMInferSlow: Evaluating the Efficiency Robustness of Large Vision-Language Models as a Service (2025.acl-long)

Challenge:	Image captioning has been a challenge for vision-language researchers for decades . current VLMs focus on tasks like visual question answering (YA) but image captioning is not as advanced as expected.
Approach:	They evaluate VLMs' performance on image captioning using human annotations . they find that some metrics show high caption-level agreement with humans .
Outcome:	The proposed model outperforms open-source models on image captioning . it achieves 93.4% correlation with human rankings at $4 per test .

Copied to clipboard

Xiasi Wang, Tianliang Yao, Simin Chen, Runqi Wang, Lei Ye, Kuofeng Gao, Yi Huang, Yuan Yao

IntelliCockpitBench: A Comprehensive Benchmark to Evaluate VLMs for Intelligent Cockpit (2025.findings-acl)

Challenge:	Existing studies evaluate efficiency robustness of vision-language models under unrealistic assumptions, requiring access to model architecture and parameters.
Approach:	They propose a novel approach to evaluate VLM efficiency robustness in a realistic black-box setting.
Outcome:	The proposed approach generates adversarial images with imperceptible perturbations, increasing the computational cost by up to 128.47%.

Copied to clipboard

Liang Lin, Siyuan Chai, Jiahao Wu, Hongbing Hu, Xiaotao Gu, Hao Hu, Fan Zhang, Wei Wang, Dan Zhang

Semantic Token Reweighting for Interpretable and Controllable Text Embeddings in CLIP (2024.findings-emnlp)

Challenge:	Visual Question Answering (VQA) is a key task in vehicular systems.
Approach:	They propose a benchmark that encompasses diverse automotive scenarios . they use images from front, side, and rear cameras, various road types, weather conditions, and interior views .
Outcome:	The proposed benchmark includes images from front, side, and rear cameras, various road types, weather conditions, and interior views.

Copied to clipboard

Eunji Kim, Kyuhong Shim, Simyung Chang, Sungroh Yoon

VisualEDU: A Benchmark for Assessing Coding and Visual Comprehension through Educational Problem-Solving Video Generation (2025.findings-emnlp)

Challenge:	Despite the varying significance of textual elements within a sentence depending on the context, efforts to account for variation of importance in constructing text embeddings have been lacking.
Approach:	They propose a framework for Semantic Token Reweighting to build Interpretable text embeddings which incorporates controllability as well.
Outcome:	The proposed framework improves the text encoding process in CLIP by differentially weighting semantic elements based on contextual importance, enabling finer control over emphasis responsive to data-driven insights and user preferences.

Copied to clipboard

Hao Chen, Tianyu Shi, Pengran Huang, Zeyuan Li, Jiahui Pan, Qianglong Chen, Lewei He

VisBias: Measuring Explicit and Implicit Social Biases in Vision Language Models (2025.emnlp-main)

Challenge:	VisualEDU is a benchmark to evaluate VLMs' ability to produce coherent video from text . advanced proprietary models show promise, but struggle with increasing task complexity .
Approach:	VisualEDU is a benchmark to evaluate VLMs' ability to produce coherent video from text . it integrates meta-prompt learning, visual and code feedback, and a drawing toolkit to enhance output quality.
Outcome:	VisualEDU is a benchmark to evaluate VLMs' ability to produce coherent video from text . it integrates meta-prompt learning, visual and code feedback, and a drawing toolkit to improve output quality.

Copied to clipboard

Jen-tse Huang, Jiantong Qin, Jianping Zhang, Youliang Yuan, Wenxuan Wang, Jieyu Zhao

***YesBut***: A High-Quality Annotated Multimodal Dataset for evaluating Satire Comprehension capability of Vision-Language Models (2024.emnlp-main)

Challenge:	Identifying and addressing potential social biases is essential to prevent harm to users.
Approach:	They examine explicit and implicit biases exhibited by Vision-Language Models . they pose questions related to gender and racial differences to test their models .
Outcome:	The proposed models are used in image description tasks, form completion tasks and medical applications.

Copied to clipboard

Abhilash Nandy, Yash Agarwal, Ashish Patwa, Millon Das, Aman Bansal, Ankit Raj, Pawan Goyal, Niloy Ganguly

PunMemeCN: A Benchmark to Explore Vision-Language Models’ Understanding of Chinese Pun Memes (2025.emnlp-main)

Challenge:	Existing Vision-Language models perform poorly on satirical image detecting tasks . satire and humor are powerful tools to highlight issues, provoke thought, and encourage critical perspective .
Approach:	They propose to use a dataset to evaluate satirical images and satire images to detect satiric images . they also propose to generate the reason behind the image being satiral by generating one half of the image to be satisfying .
Outcome:	The proposed dataset contains 2547 images, 1084 satirical and 1463 non-satirically, with different artistic styles.

Copied to clipboard

Zhijun Xu, Siyu Yuan, Yiqiao Zhang, Jingyu Sun, Tong Zheng, Deqing Yang

MVTamperBench: Evaluating Robustness of Vision-Language Models (2025.findings-acl)

Challenge:	Pun memes combine wordplay with visual elements to create humor, irony, or other rhetorical effects.
Approach:	They propose a benchmark to assess Chinese pun memes' processing capabilities across three progressive tasks: pun meme detection, sentiment analysis, and chat-driven meme response.
Outcome:	The proposed model can detect pun memes, analyze sentiments, and respond to chats, while ignoring homophone wordplay.

Copied to clipboard

Amit Agarwal, Srikant Panda, Angeline Charles, Hitesh Laxmichand Patel, Bhargava Kumar, Priyaranjan Pattnayak, Taki Hasan Rafi, Tejaswini Kumar, Hansa Meghwani, Karan Gupta, Dong-Kyu Chae

Vision-Language Models Struggle to Align Entities across Modalities (2025.findings-acl)

Challenge:	Multimodal Large Language Models (MLLMs) have been a key advance in video understanding but their vulnerability to adversarial tampering remains underexplored.
Approach:	They evaluate MLLMs against five prevalent tampering techniques to assess their robustness . they use a tampered video format to examine the vulnerability of ML models .
Outcome:	The benchmark evaluates MLLMs against five prevalent tampering techniques based on 19 video manipulation tasks.

Copied to clipboard

Iñigo Alonso, Gorka Azkune, Ander Salaberria, Jeremy Barnes, Oier Lopez De Lacalle

Improving Adversarial Robustness in Vision-Language Models with Architecture and Prompt Design (2024.findings-emnlp)

Challenge:	Several real-world applications require the ability to perform cross-modal entity linking . cross-functional entity linking is a skill needed for multimodal code generation and scene understanding .
Approach:	They propose a task and benchmark to evaluate cross-modal entity linking performance . they use visual scenes aligned with their textual representations to evaluate performance a question-answering task .
Outcome:	The proposed task and benchmark aims to improve cross-modal entity linking performance . it evaluates state-of-the-art vision-language models and humans on the task .

Copied to clipboard

Rishika Bhagwatkar, Shravan Nayak, Pouya Bashivan, Irina Rish

Treble Counterfactual VLMs: A Causal Approach to Hallucination (2025.findings-emnlp)

Challenge:	Vision-Language Models (VLMs) have seen a significant increase in research interest and real-world applications, including healthcare, autonomous systems, and security.
Approach:	They propose novel approaches to enhance model robustness through prompt engineering by suggesting adversarial perturbations or rephrasing questions.
Outcome:	The proposed approaches improve model robustness against strong image-based attacks such as Auto-PGD.

Copied to clipboard

Li Li, Jiashu Qu, Linxin Song, Yuxiao Zhou, Yuehan Qin, Tiankai Yang, Yue Zhao

OS-Symphony: A Holistic Framework for Robust and Generalist Computer-Using Agents (2026.acl-long)

Challenge:	Existing studies link hallucination to data or representation biases, but their causal origins remain unclear.
Approach:	They propose a causal framework to analyze and mitigate hallucination in vision-language models by using counterfactual analysis to estimate the Natural Direct Effect (NDE) of each modality and their interaction.
Outcome:	The proposed framework significantly reduces hallucination while preserving task performance while retaining reliability.

Copied to clipboard

Bowen Yang, Kaiming Jin, Zhenyu Wu, Zhaoyang Liu, Qiushi Sun, Zehao Li, JingJing Xie, Zhoumianze Liu, Fangzhi Xu, Kanzhi Cheng, Yian Wang, Qingyun Li, Yu Qiao, Zun Wang, Zichen Ding

PALM: Few-Shot Prompt Learning for Audio Language Models (2024.emnlp-main)

Challenge:	Vision-Language Models (VLMs) lack visual-aware tutorial retrieval and historical visual context curation and pruning.
Approach:	They propose a framework that integrates an orchestrator and a Reflection-Memory Agent for robust automation.
Outcome:	Experimental results show that OS-Symphony delivers substantial performance gains across model scales.

Copied to clipboard

Asif Hanif, Maha Agro, Mohammad Qazi, Hanan Aldarmaki

VIB-Probe: Detecting and Mitigating Hallucinations in Vision-Language Models via Variational Information Bottleneck (2026.acl-long)

Challenge:	Audio-Language Models (ALMs) have recently achieved remarkable success in zero-shot audio recognition tasks, which match features of audio waveforms with class-specific text prompt features.
Approach:	They propose a method which optimizes the feature space of the text encoder branch and optimizes audio waveform features with text prompt features.
Outcome:	The proposed method outperforms existing methods while being less demanding.

Copied to clipboard

Feiran Zhang, Yixin Wu, Zhenghua Wang, Xiaohua Wang, Changze Lv, Xuanjing Huang, Xiaoqing Zheng

MTabVQA: Evaluating Multi-Tabular Reasoning of Language Models in Visual Space (2025.findings-emnlp)

Challenge:	Existing hallucination detection methods rely on external verification tools . however, entanglement of visual-linguistic syntax and noise makes it difficult to detect hallucis .
Approach:	They propose a hallucination detection framework that leverages the Variational Information Bottleneck theory to detect hallucinic heads and to infer hallucication mitigation strategies.
Outcome:	The proposed framework outperforms baselines in hallucinations and noise detection environments.

Copied to clipboard

Anshul Singh, Chris Biemann, Jan Strich

INDOTABVQA: A Benchmark for Cross-Lingual Table Understanding in Bahasa Indonesia Documents (2026.findings-acl)

Challenge:	Existing benchmarks address single tables or non-visual data, leaving a critical gap . MTabVQA comprises 3,745 complex question-answer pairs .
Approach:	They propose a benchmark specifically designed for multi-tabular visual question answering that measures the ability to parse diverse table images and correlate information across them.
Outcome:	The proposed benchmarks show that fine-tuning VLMs with MTabVQA-Instruct significantly improves their reasoning abilities.

Copied to clipboard

Somraj Gautam, Anathapindika Dravichi, Gaurav Harit

Ascending the Infinite Ladder: Benchmarking Spatial Deformation Reasoning in Vision-Language Models (2026.acl-long)

Challenge:	INDOTABVQA provides a benchmark for evaluating cross-lingual Table Visual Question Answering (VQA) on real-world document images in Bahasa Indonesia.
Approach:	They propose a benchmark for evaluating cross-lingual Table Visual Question Answering on real-world document images in Bahasa Indonesia.
Outcome:	The proposed model improves on a 3B model and a LoRA- finetuned 7B model on Bahasa Indonesian document images by 11.6% and 17.8% respectively.

Copied to clipboard

Jiahuan Zhang, Shunwen Bai, Tianheng Wang, KaiWen Guo, Zijia Song, Hanqing WU, Guozheng Rao, Kai Han, Kaicheng Yu

CharTide: Data-Centric Chart-to-Code Generation via Tri-Perspective Tuning and Inquiry-Driven Evolution (2026.acl-long)

Challenge:	Existing benchmarks explore aspects of threedimensional spatial reasoning and visual-language reasoning in dynamic environments, but they are unable to perform well on 3D spatial deformation reasoning.
Approach:	They propose to use a ladder competition format to assess the model's spatial deformation reasoning abilities to determine its performance.
Outcome:	The proposed framework assesses the performance of Vision-Language Models in spatial deformation reasoning tasks.

Copied to clipboard

Xiangxi Zheng, Kuang He, Jiayi Hu, Ping Yu, Rui Yan, Yuan Yao, Peng Hou, Anxiang Zeng, Alex Jinpeng Wang

InstructPart: Task-Oriented Part Segmentation with Instruction Reasoning (2025.acl-long)

Challenge:	Existing approaches to chart-to-code generation are constrained by data-centric limitations . authors present a new framework that redesigns both training and alignment data .
Approach:	They propose a data-centric framework that redesigns both training and alignment data for chart-to-code generation.
Outcome:	The proposed framework outperforms open-source baselines and is competitive with GPT-5.

Copied to clipboard

Zifu Wan, Yaqi Xie, Ce Zhang, Zhiqiu Lin, Zihan Wang, Simon Stepputtis, Deva Ramanan, Katia P. Sycara

Retrieval-enriched zero-shot image classification in low-resource domains (2024.emnlp-main)

Challenge:	Large multimodal foundation models perceive objects as indivisible, overlooking the components that constitute them.
Approach:	They propose a novel benchmark for large multimodal foundation models comprising hand-labeled part segmentation annotations and task-oriented instructions to evaluate their performance.
Outcome:	The proposed benchmark improves performance of current models in understanding and executing part-level tasks within everyday contexts.

Copied to clipboard

Nicola Dall’Asen, Yiming Wang, Enrico Fini, Elisa Ricci

Information Retrieval

Challenge:	Low-resource domains are those where data or annotations are scarce.
Approach:	They propose a retrieval-based method for low-resource domains that trains without training . they use web-crawled databases to retrieve relevant textual information from query images .
Outcome:	The proposed method outperforms existing training-based methods in low-resource domains . it retrieves relevant textual information from large web-crawled databases .

ChemVLR: Prioritizing Reasoning in Perception for Chemical Vision-Language Understanding (2026.findings-acl)

Copied to clipboard

Xuanle Zhao, Xinyuan Cai, Xiang Cheng, Xiuyi Chen, Bo XU

FREE: Fast and Robust Vision Language Models with Early Exits (2025.findings-acl)

Challenge:	Currently, vision-Language Models are optimized for direct visual question-answering tasks.
Approach:	They propose a visual-language-based VLM that prioritizes reasoning within the perception process.
Outcome:	The proposed model outperforms existing models and domain-specific open-source models in the chemical domain.

Copied to clipboard

Divya Jyoti Bajpai, Manjesh Kumar Hanawal

Preserving Language Capabilities in Vision-Language Models via Representation Regulation (2026.findings-acl)

Challenge:	Vision-Language Models (VLMs) have shown remarkable performance improvements in Vision-language tasks, but their large size poses challenges for real-world applications.
Approach:	They propose an adversarial approach to train exit classifiers in Vision-Language Models that uses a transformer layer and a classifier to perform input-adaptive inference.
Outcome:	The proposed approach speeds up inference speed with minimal drop in performance by 1.51 while retaining comparable performance.

Copied to clipboard

ZiXuan Chen, Juncheng Tao, Ziqian Zeng

AIM-CoT: Active Information-driven Multimodal Chain-of-Thought for Vision-Language Reasoning (2026.acl-long)

Challenge:	Vision-Language Models (VLMs) provide a unified framework to process both text-only and vision-language tasks.
Approach:	They propose a method to reduce the distance between visual and textual representations by introducing a Representation Distribution Difference (RDD) loss.
Outcome:	Empirical evidence shows that finetuning VLMs on vision-language data has degraded language capabilities.

Copied to clipboard

Xiping Li, Jianghong Ma

DocLens: A Tool-Augmented Multi-Agent Framework for Long Visual Document Understanding (2026.acl-long)

Challenge:	Existing methods for I-MCoT fail to capture dynamic needs of vision-language models . existing methods rely on attention signals, which are unreliable under severe granularity imbalance between brief textual query and informative image.
Approach:	They propose a framework that integrates specially selected visual evidence into the context of Vision-Language Models (VLMs) they propose 'AIM-CoT' to improve evidence selection and insertion triggering .
Outcome:	Experiments across three benchmarks and four backbones demonstrate the proposed framework’s consistent superiority.

Copied to clipboard

Dawei Zhu, Rui Meng, Jiefeng Chen, Sujian Li, Tomas Pfister, Jinsung Yoon

Perceptual Hallucination in Vision–Language Models: Definition, Analysis and Verification (2026.findings-acl)

Challenge:	Existing approaches to localizing evidence from long visual documents fail on a fundamental challenge: evidence localization.
Approach:	They propose a tool-augmented multi-agent framework that “zooms in” on evidence like a lens.
Outcome:	The proposed framework achieves state-of-the-art performance on MMLongBench-Doc and FinRAGBench-V, surpassing even human experts.

Copied to clipboard

Taewook Hwang, Inbum Heo, Sung Jun Lee, Sangkeun Jung

Token-level Inference-Time Alignment for Vision-Language Models (2026.findings-acl)

Challenge:	Recent advances in large language models (LLMs) have dramatically improved text understanding and generation capabilities.
Approach:	They define perceptual hallucination as the phenomenon where VLMs generate information as if perceived, despite absent or damaged visual evidence.
Outcome:	The proposed model reduces hallucination exposure by 36% on average, with reductions of up to 88%.

Copied to clipboard

Kejia Chen, Junjun Zheng, Jiawen Zhang, Manxi Lin, Xiao Pan, Jiacong Hu, Jian Lou, Zunlei Feng, Mingli Song

ProcVQA: Benchmarking the Effects of Structural Properties in Mined Process Visualizations on Vision–Language Model Performance (2025.findings-emnlp)

Challenge:	Vision-Language Models (VLMs) often prioritize linguistic fluency over visual fidelity . despite widespread adoption, VLMs often exhibit a critical failure mode: hallucination .
Approach:	They propose a framework for Token-level Inference-Time Alignment that steers the decoding process without updating the base model parameters.
Outcome:	The proposed framework improves performance on 13 benchmarks across architectures . it boosts LLaVA-1.5-7B by 8.6% on MMVet and achieves a 74.0 MMStar score .

Copied to clipboard

Kazi Tasnim Zinat, Saad Mohammad Abrar, Shoumik Saha, Sharmila Duppala, Saimadhav Naga Sakhamuri, Zhicheng Liu

HomoGraphAdapter: A Homogeneous Graph Neural Network as an Effective Adapter for Vision-Language Models (2025.findings-emnlp)

Challenge:	Vision-Language Models have shown impressive capabilities and notable failures in data visualization understanding tasks.
Approach:	They propose a benchmark to analyze how specific properties within a visualization type affect VLM performance.
Outcome:	The proposed benchmark examines how specific properties affect VLM performance . it shows that models exhibit steep drops on multi-hop reasoning and extraction errors increase with edge density .

Copied to clipboard

Chuan He, Zhuozhao Li, Song Guo, Xiaocheng Lu, Jinxiang Lai

Jianzhu Bao, Haozhen Zhang, Kuicai Dong, Bozhi Wu, Sarthak Ketanbhai Modi, Zi Pong Lim, Yon Shin Teo, Wenya Wang

Challenge:	Existing adaptation methods overlook structural knowledge between text and image modalities or create overly complex graphs containing redundant information for alignment.
Approach:	They propose a method to adapt visual models to downstream tasks using text and image modalities.
Outcome:	The proposed method improves classification accuracy by 1.51% for 1-shot and 0.74% for 16-shot on 11 datasets.

Copied to clipboard

SteerVLM: Robust Model Control through Lightweight Activation Steering for Vision Language Models (2025.findings-emnlp)

Challenge:	Chart understanding is a critical capability for vision-language models, serving as a cornerstone for automated data analysis, document understanding, and scientific research.
Approach:	They propose a chart-efficient training framework to enhance counterfactual sensitivity by code modification and a similarity-based data selection strategy.
Outcome:	The proposed framework achieves superior or comparable performance to strong chart-specific VLMs while using significantly less training data.

Copied to clipboard

Anushka Sivakumar, Andrew Zhang, Zaber Ibn Abdul Hakim, Chris Thomas

From Perception to Reasoning: Enhancing Vision-Language Models for Mobile UI Understanding (2025.findings-acl)

Challenge:	SteerVLM is a lightweight steering module designed to guide Vision-Language Models (VLMs) towards outputs that better adhere to desired instructions.
Approach:	They propose a lightweight steering module that learns from latent embeddings of paired prompts encoding target and converse behaviors to dynamically adjust activations connecting the language modality with image context.
Outcome:	The proposed steering module outperforms existing intervention techniques on steering and hallucination mitigation benchmarks for VLMs.

Copied to clipboard

Settaluri Lakshmi Sravanthi, Ankit Mishra, Debjyoti Mondal, Subhadarshi Panda, Rituraj Singh, Pushpak Bhattacharyya

iVISPAR — An Interactive Visual-Spatial Reasoning Benchmark for VLMs (2025.emnlp-main)

Challenge:	Accurately grounding visual and textual elements within mobile user interfaces remains a challenge for Vision-Language Models (VLMs).
Approach:	They propose a mobile UI understanding model trained on a dataset specifically tailored for mobile screen understanding and grounding.
Outcome:	The proposed model achieves significant gains in accuracy across all perception tasks and on reasoning benchmarks.

Copied to clipboard

Julius Mayer, Mohamad Ballout, Serwan Jassim, Farbod Nosrat Nezami, Elia Bruni

VLURes: Benchmarking Long-Text Grounding and Cross-Lingual Robustness in Vision Language Models (2026.findings-acl)

Challenge:	Vision-Language Models (VLMs) struggle with spatial reasoning and visual alignment, despite their performance on 2D tasks.
Approach:	They propose a multimodal benchmark to evaluate VLMs' spatial reasoning capabilities based on the sliding tile puzzle .
Outcome:	The proposed model performs better on 2D tasks compared to 3D or text-based settings, but struggles with complex spatial configurations and consistently falls short of human performance.

Copied to clipboard

Jesse Atuhurra, Iqra Ali, Tomoya Iwakura, Hidetaka Kamigaito, Tatsuya Hiraoka

Multilinguality

Challenge:	*VLURes provides a practical testbed for long-text grounding and multilingual robustness in web-realistic agent settings.
Approach:	They propose a multilingual benchmark for evaluating vision-language models under long-text grounding.
Outcome:	*VLURes provides a testbed for long-text grounding and multilingual robustness in web-realistic agent settings.

CAVE : Detecting and Explaining Commonsense Anomalies in Visual Environments (2025.emnlp-main)

Copied to clipboard

Rishika Bhagwatkar, Syrielle Montariol, Angelika Romanou, Beatriz Borges, Irina Rish, Antoine Bosselut

Explainability & Interpretability in NLP

Challenge:	a new benchmark for computer vision fails to capture richness and unpredictability of real-world anomalies . state-of-the-art VLMs struggle with visual anomaly perception and commonsense reasoning . elucidating the nature of anomalies is a fundamental human trait .
Approach:	They propose a benchmark for visual anomalies that includes annotations for visual grounding and categorizing anomalies based on their visual manifestations, their complexity, severity, and commonness.
Outcome:	The proposed benchmark improves on existing vision models by incorporating visual annotations.

On the Fine-Grained Planning Abilities of VLM Web Agents (2025.findings-emnlp)

Copied to clipboard

Surgan Jandial, Yinong Oliver Wang, Andrea Bajcsy, Fernando De la Torre

Challenge:	Vision-Language Models (VLMs) have shown promise as web agents, yet their planning has been overlooked.
Approach:	They propose to examine VLMs’ ability to understand temporal relationships within web contexts and assess plans of actions across diverse scenarios.
Outcome:	The proposed models exhibit limited performance in the above skills and are not reliable to function as web agents.

Almieyar-Oryx-BloomBench: A Bilingual Multimodal Benchmark for Cognitively Informed Evaluation of Vision-Language Models (2026.findings-acl)

Copied to clipboard

Mohammad Mahdi Abootorabi, Omid Ghahroodi, Anas Madkoor, Marzia Nouri, Doratossadat Dastgheib, Ehsaneddin Asgari

Benchmarking Vision-Language Models on Chinese Ancient Documents: From OCR to Knowledge Reasoning (2026.findings-acl)

Challenge:	Existing evaluations focus on piecemeal or disconnected tasks, obscuring critical cognitive weaknesses and providing little insight for targeted improvement.
Approach:	They propose a bilingual, cognitively human-grounded multimodal benchmark for VLMs that evaluates six levels of cognition through carefully designed image–question–answer tasks.
Outcome:	The proposed framework ensures scalability, cultural inclusivity, and linguistic fidelity.

Copied to clipboard

Haiyang Yu, Yuchuan Wu, Fan Shi, Jinghui Lu, Ke Niu, Xiaodong Ge, Minghan Zhuo, Jingqun Tang, Bin Li

InquireMobile: Teaching VLM-based Mobile Agent to Request Human Assistance via Reinforcement Fine-Tuning (2026.acl-long)

Challenge:	Existing document benchmarks focus on English printed texts or simplified Chinese . current vision-language models struggle with visual complexity and poor adaptability .
Approach:	They propose a benchmark to evaluate Chinese ancient documents' visual/linguistic complexity . ancient documents are valuable cultural heritage, but they face challenges in digitization and understanding .
Outcome:	the first benchmark for Chinese ancient documents evaluates VLMs from OCR to knowledge reasoning . ancient documents carry thousands of years of Chinese history and culture . traditional methods only scan images, while current models struggle with visual complexity .

Copied to clipboard

Qihang Ai, Pi Bu, Yue Cao, Yingyao Wang, Jihao Gu, Jingxuan Xing, Zekun Zhu, Wei Jiang, Zhicheng Zheng, Jun Song, Yuning Jiang

On the Cultural Anachronism and Temporal Reasoning in Vision Language Models (2026.findings-acl)

Challenge:	Recent advances in Vision-Language Models (VLMs) have enabled mobile agents to perceive and interact with real-world mobile environments based on human instructions.
Approach:	They propose a vision-language model that actively seeks human confirmation at critical decision points and a model inspired by reinforcement learning.
Outcome:	The proposed model achieves an improvement of 46.8% in inquiry success rate and the best overall success rate among existing baselines on InquireBench.

Copied to clipboard

Mukul Ranjan, Prince Jha, Khushboo Kumari, Zhiqiang Shen

MemeIntel: Explainable Detection of Propagandistic and Hateful Memes (2025.emnlp-main)

Challenge:	Vision-Language Models (VLMs) are increasingly applied to cultural heritage materials.
Approach:	They propose a temporal anachronism benchmark to evaluate temporal reasoning on 1,600 Indian cultural artifacts.
Outcome:	The proposed model achieves only 58.7% accuracy on the best model, which is a significant performance gap across architectures and scales.

Copied to clipboard

Mohamed Bayan Kmainasi, Abul Hasnat, Md Arid Hasan, Ali Ezzat Shahroor, Firoj Alam

Can Small Vision–Language Models Perform Sign Language Translation? (2026.findings-acl)

Challenge:	Existing methods for label detection and explanation generation have been limited in understanding complex issues . identifying propaganda and hate in memes is essential for combating misinformation and minimizing harm .
Approach:	They propose an explanation-enhanced dataset for propaganda memes in Arabic and hateful memes on English to solve these tasks.
Outcome:	The proposed model outperforms the current state-of-the-art in label detection and explanation generation.

Copied to clipboard

Anal Roy Chowdhury, Debarshi Kumar Sanyal

Multilinguality

Challenge:	Vision-Language Models (VLMs) have shown strong generalization across multimodal tasks, but their capacity to handle sign language translation (SLT) remains unclear.
Approach:	They propose entity- and semantics-aware metrics tailored for SLT to evaluate their performance.
Outcome:	The proposed metrics highlight the limitations of general-purpose VLMs to SLT, unlike their applicability in other tasks.

DiningBench: A Hierarchical Multi-view Benchmark for Perception and Reasoning in the Dietary Domain (2026.acl-long)

Copied to clipboard

Song Jin, Juntian Zhang, Xun Zhang, Zeying Tian, Fei Jiang, Guojun Yin, Wei Lin, Yong Liu, Rui Yan

LLaTiSA: Towards Difficulty-Stratified Time Series Reasoning from Visual Perception to Semantics (2026.findings-acl)

Challenge:	Existing vision-language models lack fine-grained classification, single-view imagery, and inaccurate metadata.
Approach:	They propose a hierarchical, multi-view benchmark to evaluate VLMs across three levels of cognitive complexity.
Outcome:	The proposed benchmark evaluates vision-language models across three levels of complexity . it systematically identifies five primary failure modes . the proposed benchmarks are available on https://github.com/meituan/DiningBench.

Copied to clipboard

Yueyang Ding, HaoPeng Zhang, Rui Dai, Yi Wang, Tianyu Zong, Kaikui Liu, Xiangxiang Chu

VIDA: A Visual Intent-driven Design Assistant for Proactive Multimodal Clarification (2026.findings-acl)

Challenge:	Current research hinders the development of unified Time Series Reasoning Models (TSRMs) time series data are a fundamental modality for capturing the temporal dynamics of complex systems.
Approach:	They propose a time series reasoning model that integrates visualized patterns with precision-calibrated numerical tables to enhance the temporal perception of Vision-Language Models.
Outcome:	The proposed model outperforms existing models and exhibits robust out-of-distribution generalization across diverse tasks and real-world scenarios.

Copied to clipboard

Yanshan Liu, Hongbo Zhang, Zhen Sun, Jiaheng Wei, Kaishun Wu

KRETA: A Benchmark for Korean Reading and Reasoning in Text-Rich VQA Attuned to Diverse Visual Contexts (2025.emnlp-main)

Challenge:	Existing vision-language models fail to provide accurate and complete answers to user requests . a new strategy-aware design assistant is developed to help designers create proactive, visually grounded, and strategically prioritized clarification questions.
Approach:	They propose a visual intent-driven design assistant to generate proactive, visually grounded, and strategically prioritized clarification questions.
Outcome:	The proposed assistant improves the strategic alignment score by 20.59% over baselines and restores visual grounding capabilities lost during fine-tuning.

Copied to clipboard

Taebaek Hwang, Minseo Kim, Gisang Lee, Seonuk Kim, Hyunjun Eun

CaTS-Bench: Can Language Models Describe Time Series? (2026.findings-acl)

Challenge:	Understanding and reasoning over text within visual contexts poses a significant challenge for Vision-Language Models.
Approach:	They propose a benchmark for Korean Reading and rEasoning in Text-rich VQA Attuned to diverse visual contexts to address this challenge.
Outcome:	The proposed benchmark is tailored for Korean reading and rEasoning in text-rich VQA attuned to diverse visual contexts.

Copied to clipboard

Luca Zhou, Pratham Yashwante, Marshall Fisher, Alessio Sampieri, Zihao Zhou, Fabio Galasso, Rose Yu

Text Generation

Challenge:	Existing time series captioning benchmarks rely on fully synthetic or generic captions . authors propose a pipeline for generating high-fidelity synthetic captions, which is validated .
Approach:	They propose a benchmark for Context-aware Time Series reasoning across 11 diverse domains . they evaluate leading Vision-Language Models on their benchmark .
Outcome:	The proposed benchmark evaluates 1746 human-rewritten captions and shows they perform better than open-source models.

S2H-DPO: Hardness-Aware Preference Optimization for Vision–Language Models (2026.findings-acl)

Copied to clipboard

Nitish Shukla, Surgan Jandial, Arun Ross

VisTW: Benchmarking Vision-Language Models for Taiwanese Mandarin in Taiwan (2026.findings-acl)

Challenge:	Existing methods focus on localized reasoning with pre-specified image indices, bypassing the skills of global visual search and autonomous cross-image comparison.
Approach:	They propose a learning framework that constructs multi-image preference data across three hierarchical reasoning levels requiring an increasing level of capabilities.
Outcome:	The proposed approach maintains strong single-image reasoning performance while strengthening multi-image understanding capabilities.

Copied to clipboard

Zhi Rui Tam, Yung-Yu Shih, Yen-Wei Lee, Ya-Ting Pai, Wen Yu Chang, Yun-Nung Chen

Measuring Social Bias in Vision-Language Models with Face-Only Counterfactuals from Real Photos (2026.acl-long)

Challenge:	Vision-Language Models (VLMs) struggle in Taiwanese Mandarin environments due to region-specific orthographic and cultural context.
Approach:	They propose a human-grounded purity penalty for character mixing under Taiwanese-Mandarin-style prompts.
Outcome:	The proposed model outperforms the strongest open-weight baseline by 22 percentage points on dialogue tasks.

Copied to clipboard

Haodong Chen, Qiang Huang, Jiaqi Zhao, Qiuping Jiang, Xiaojun Chang, Jun Yu

E-ViC: Reasoning Beyond Text via Embodied Visual Chain for Spatial Intelligence (2026.acl-long)

Challenge:	Vision-Language Models (VLMs) are increasingly deployed in socially consequential settings . attribution under visual confounding is a central challenge in measuring social bias .
Approach:	They propose a face-only counterfactual evaluation paradigm that isolates demographic effects while preserving real-image realism.
Outcome:	The proposed paradigm isolates demographic effects while preserving real-image realism.

Copied to clipboard

Junbo Qi, Yi Zhang, Hanchu Ni, Che Liu, Zhimin Yao, Ruilin Yang, Xiancong Ren, Liangjian Wen, Wei Ge, Yuya Ieiri, Osamu Yoshie, Yong Dai, Xiaozhu Ju

RealChart2Code: Bridging the Gap in Real-World Chart-to-Code Generation via Multi-Task Evaluation (2026.acl-long)

Challenge:	Existing Vision-Language Models (VLMs) lack spatial reasoning, despite text-based CoTs . e-ViC reframes spatial intelligence as a verifiable, tool-using capability, argues a new study.
Approach:	They propose a framework that moves reasoning beyond text into the visual domain . they ground reasoning in pixel-level interactions to enable human-like "look-and-confirm" strategies .
Outcome:	The proposed framework outperforms existing Vision-Language Models with an average gain of 10.1%.

Copied to clipboard

Jiajun Zhang, Yuying Li, Zhixun Li, Xingyu Guo, Jingzhuo Wu, Leqi Zheng, Yiran Yang, Jianke Zhang, Qingbin Li, Shannan Yan, Changguo Jia, Junfei Wu, Zilei Wang, Qiang Liu, Liang Wang

Text Generation

Challenge:	Vision-Language Models (VLMs) have demonstrated impressive capabilities in code generation across various domains, but their ability to replicate complex, multi-panel visualizations remains largely unassessed.
Approach:	They propose a large-scale benchmark to evaluate chart generation from large- scale raw data and assess iterative code refinement in a multi-turn conversational setting.
Outcome:	The new benchmark evaluates 14 leading VLMs on real-world data and shows they struggle with complex plot structures and authentic data.

MMErroR: A Benchmark for Erroneous Reasoning in Vision-Language Models (2026.acl-long)

Copied to clipboard

Yang Shi, Yifeng Xie, Minzhe Guo, Liangsi Lu, Mingxuan Huang, Jingchao Wang, Zhihong Zhu, Boyan Xu, Zhiqi Huang

Does RLVR Extend Reasoning Boundaries? Investigating Capability Expansion in Vision-Language Models (2026.acl-long)

Challenge:	Recent advances in vision-language models have improved performance in multi-modal learning.
Approach:	They propose a multi-modal benchmark that embeds a single coherent reasoning error in 1997 samples.
Outcome:	The proposed benchmark is based on a set of 1997 samples embedding a single coherent reasoning error.

Copied to clipboard

Minghe Shen, Zhuo Zhi, Chonghan Liu, Shuo Xing, Zhengzhong Tu, Che Liu

MathSight: A Benchmark Exploring Have Vision-Language Models Really Seen in University-Level Mathematical Reasoning? (2026.acl-long)

Challenge:	Recent studies suggest that RLVR amplifies behaviors inherent to the pre-training distribution rather than inducing new capabilities.
Approach:	They propose a framework for RLVR that extends the spatial reasoning boundary . they use a mapping framework where the difficulty is precisely regulated by path length and number of turns .
Outcome:	The proposed framework extends the spatial reasoning boundary on two real-world navigation benchmarks.

Copied to clipboard

Yuandong Wang, Yao Cui, Yuxin Zhao, Zhen Yang, Yangfu Zhu, Zhenzhou Shao