VISION-LANGUAGE TASKS

Query-aware Multi-modal based Ranking Relevance in Video Search (2023.emnlp-industry)

Challenge:	InfiMM is a multimodal large language model that adapts to complex vision-language tasks.
Approach:	They present a Multimodal Large Language Model that adapts to intricate vision-language tasks using large-scale training data and comprehensive training strategies.
Outcome:	Empirical evaluations across a variety of benchmarks underscore InfiMM’s remarkable capability in multimodal understanding.

Copied to clipboard

Chengcan Ye, Ting Peng, Tim Chang, Zhiyi Zhou, Feng Wang

Stop Pre-Training: Adapt Visual-Language Models to Unseen Languages (2023.acl-short)

Challenge:	Existing relevance ranking methods focus on text modality, incapable of fully exploiting cross-modal cues present in video.
Approach:	They propose a QUery-Aware pre-training model with multi-modality that integrates video tag information as alignment targets and enhances ranking optimization method based on ordinal regression.
Outcome:	The proposed model significantly improves video search performance.

Copied to clipboard

Yasmine Karoui, Rémi Lebret, Negar Foroutan Eghlidi, Karl Aberer

Think Before You Act: A Two-Stage Framework for Mitigating Gender Bias Towards Vision-Language Tasks (2024.naacl-long)

Challenge:	Existing studies have shown that the pre-training in English does not transfer well to other languages in a zero-shot setting.
Approach:	They propose a simple yet efficient approach to adapt VLP to unseen languages using MPLM.
Outcome:	The proposed approach outperforms state-of-the-art models without large parallel corpora across three tasks.

Copied to clipboard

Yunqi Zhang, Songda Li, Chunyuan Deng, Luyi Wang, Hui Zhao

UniFine: A Unified and Fine-grained Approach for Zero-shot Vision-Language Understanding (2023.findings-acl)

Challenge:	Existing vision-language models focus on salient attributes but ignore contextualized nuances, resulting in gender bias.
Approach:	They propose a task-agnostic generation framework to mitigate gender bias in vision-language models.
Outcome:	The proposed framework can mitigate gender bias in vision-language models . it yields all-sided but gender-obfuscated narratives, which prevents concentration on localized image features, especially gender attributes.

Copied to clipboard

Rui Sun, Zhecan Wang, Haoxuan You, Noel Codella, Kai-Wei Chang, Shih-Fu Chang

UniFashion: A Unified Vision-Language Model for Multimodal Fashion Retrieval and Generation (2024.emnlp-main)

Challenge:	supervised methods for vision-language tasks have been well-studied, but they lack the fine-grained information needed for semantics understanding.
Approach:	They propose a framework to take advantage of fine-grained information for zero-shot vision-language learning, covering multiple tasks such as VQA, SNLI-VE, and VCR.
Outcome:	The proposed framework outperforms previous zero-shot methods on VQA and achieves substantial improvement on SNLI-VE and VCR.

Copied to clipboard

Xiangyu Zhao, Yuehan Zhang, Wenlong Zhang, Xiao-Ming Wu

KD-VLP: Improving End-to-End Vision-and-Language Pretraining with Object Knowledge Distillation (2022.findings-naacl)

Challenge:	e-commerce tasks such as multimodal retrieval and multimodal generation are largely ignored due to the diversity of the multimodal fashion domain.
Approach:	They propose a framework that integrates image generation with retrieval and text generation tasks.
Outcome:	The proposed framework outperforms state-of-the-art models across fashion tasks.

Copied to clipboard

Yongfei Liu, Chenfei Wu, Shao-Yen Tseng, Vasudev Lal, Xuming He, Nan Duan

SPARTA: Evaluating Reasoning Segmentation Robustness through Black-Box Adversarial Paraphrasing in Text Autoencoder Latent Space (2026.eacl-long)

Challenge:	Existing vision-and-language pretraining approaches rely on external object detectors to encode images in a multi-modal transformer framework.
Approach:	They propose an object-aware end-to-end VLP framework which feeds image grid features from CNNs into the Transformer and learns the multi-modal representations jointly.
Outcome:	The proposed framework achieves competitive or superior performances on vision-language tasks.

Copied to clipboard

Viktoriia Zinkovich, Anton Antonov, Andrei Spiridonov, Denis Shepelev, Andrey Moskalenko, Daria Pugacheva, Elena Tutubalina, Andrey Kuznetsov, Vlad Shakhuro

Robustness in NLP

Challenge:	Existing work on semantically equivalent textual paraphrases has focused on perturbing image inputs.
Approach:	They propose a novel adversarial paraphrasing task that generates grammatically correct paraphrases that sighed the original query meaning while degrading segmentation performance.
Outcome:	The proposed task outperforms previous methods by up to 2x on ReasonSeg and LLMSeg-40k datasets.

Fine-tuning CLIP Text Encoders with Two-step Paraphrasing (2024.findings-eacl)

Copied to clipboard

Hyunjae Kim, Seunghyun Yoon, Trung Bui, Handong Zhao, Quan Tran, Franck Dernoncourt, Jaewoo Kang

Compressing then Matching: An Efficient Pre-training Paradigm for Multimodal Embedding (2026.acl-long)

Challenge:	Contrastive language-image pre-training models have demonstrated considerable success across various vision-language tasks, such as text-to-image retrieval.
Approach:	They propose a fine-tuning approach to enhance the representations of CLIP models for paraphrases by leveraging large language models.
Outcome:	The proposed model improves on baseline models across paraphrased retrieval, visual genome relation and attribution, and seven semantic textual similarity tasks.

Copied to clipboard

Da Li, Yuxiao Luo, Keping Bi, Jiafeng Guo, Wei Yuan, Biao Yang, Yan Wang, Fan Yang, Tingting Gao, Guorui Zhou

Filling the Image Information Gap for VQA: Prompting Large Language Models to Proactively Ask Questions (2023.findings-emnlp)

Challenge:	Recent approaches demonstrate that MLLMs can be adapted into competitive embedding models via large-scale contrastive learning.
Approach:	They propose a compressed pre-training phase which serves as a warm-up stage for contrastive learning.
Outcome:	The proposed model achieves state-of-the-art among MLLMs of comparable size on the MMEB, realizing optimization in both efficiency and effectiveness.

Copied to clipboard

Ziyue Wang, Chi Chen, Peng Li, Yang Liu

Scaffolding Coordinates to Promote Vision-Language Coordination in Large Multi-Modal Models (2025.coling-main)

Challenge:	Large Language Models (LLMs) demonstrate impressive reasoning ability and the maintenance of world knowledge in natural language tasks.
Approach:	They propose a framework that enables LLMs to ask relevant questions to uncover more details in the image, along with filters for refining the generated information.
Outcome:	The proposed framework boosts the performance of baseline methods by 2.15% on OK-VQA and achieves consistent improvements across different LLMs.

Copied to clipboard

Xuanyu Lei, Zonghan Yang, Xinrui Chen, Peng Li, Yang Liu

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

Challenge:	Existing prompting techniques for Large Multi-Modal Models (LMMs) focus on improving textual reasoning or leveraging tools for image preprocessing, lacking a simple and general visual prompting scheme to promote vision-language coordination.
Approach:	They propose a prompting scheme that scaffolds coordinates to promote vision-language coordination in Large Multi-Modal Models (LMMs) they overlay a dot matrix within the image as visual information anchors and leverage multi-dimensional coordinates as textual positional references.
Outcome:	Experiments on a wide range of vision-language tasks show the superiority of SCAFFOLD prompting over the textual Chain-of-Thought prompting.

Copied to clipboard

Qian Yang, Weixiang Yan, Aishwarya Agrawal

Simple-VGC: Enhancing Visual Grounding in Multimodal Reasoning via Adaptive Tool Composition (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

Ye Wang, Qianglong Chen, Siyuan Wang, Zejun Li, Shijie Guo, Zhirui Zhang, Zhongyu Wei

Pruning the Paradox: How CLIP’s Most Informative Heads Enhance Performance While Amplifying Bias (2025.emnlp-main)

Challenge:	Existing multimodal large language models suffer from systematic failures in basic visual understanding.
Approach:	They propose a tool-augmented reasoning framework with three targeted compensation strategies to address these problems.
Outcome:	The proposed framework improves visual grounding by re-injecting the original image to mitigate visual forgetting, the authors show . the proposed framework also improves the accuracy of the visual inputs, the researchers show - and the results are promising .

Copied to clipboard

Avinash Madasu, Vasudev Lal, Phillip Howard

Responsible & Trustworthy NLP

Challenge:	Large-scale vision-language models such as CLIP have advanced state-of-the-art performance in vision tasks . however, as they gain prominence in real-world applications, their embedded social biases can be harmful . et al., 2021: 103-104.
Approach:	They propose an interpretability metric that measures how consistently attention heads align with specific concepts in CLIP-like models.
Outcome:	The proposed interpretability metric measures how consistently attention heads align with specific concepts.

M5 – A Diverse Benchmark to Assess the Performance of Large Multimodal Models Across Multilingual and Multicultural Vision-Language Tasks (2024.findings-emnlp)

Copied to clipboard

Florian Schneider, Sunayana Sitaram

RWKV-CLIP: A Robust Vision-Language Representation Learner (2024.emnlp-main)

Challenge:	Recent advances in Large Language Models and their multimodal counterparts have shown significant performance disparities across different languages and cultural contexts.
Approach:	They propose to evaluate LLMs on diverse vision-language tasks within a multilingual and multicultural context using M5 benchmark.
Outcome:	The proposed benchmarks highlight task-agnostic performance disparities between languages and cultural contexts.

Copied to clipboard

Tiancheng Gu, Kaicheng Yang, Xiang An, Ziyong Feng, Dongnan Liu, Weidong Cai, Jiankang Deng

MSD: Saliency-aware Knowledge Distillation for Multimodal Understanding (2021.findings-emnlp)

Challenge:	Using large image-text datasets, large-scale image-data sets have been used for visionlanguage pre-training.
Approach:	They propose a framework that leverages Large Language Models to combine and refine information from web-based image-text pairs, synthetic captions, and detection tags.
Outcome:	The proposed framework can combine and refine information from web-based image-text pairs, synthetic captions, and detection tags.

Copied to clipboard

Woojeong Jin, Maziar Sanjabi, Shaoliang Nie, Liang Tan, Xiang Ren, Hamed Firooz

ProMedTS: A Self-Supervised, Prompt-Guided Multimodal Approach for Integrating Medical Text and Time Series (2025.findings-acl)

Challenge:	Current knowledge distillation models are limited and lack performance on multimodal datasets.
Approach:	They propose a multimodal knowledge distillation framework to transfer knowledge from a teacher on multimodal tasks by learning the teacher's behavior within each modality.
Outcome:	The proposed framework achieves better performance than KD on four multimodal datasets.

Copied to clipboard

Shuai Niu, Jing Ma, Hongzhan Lin, Liang Bai, Zhihua Wang, V. W., Richard Yi Da Xu, Guo Li, Xian Yang

Evaluating and Mitigating Object Hallucination in Large Vision-Language Models: Can They Still See Removed Objects? (2025.naacl-long)

Challenge:	Large language models excel at processing unstructured data, but integrating time series data with text remains a challenge.
Approach:	They propose a self-supervised multimodal framework that uses prompt-guided learning to unify heterogeneous data types.
Outcome:	The proposed framework outperforms state-of-the-art approaches on disease diagnosis tasks using real-world datasets.

Copied to clipboard

Yixiao He, Haifeng Sun, Pengfei Ren, Jingyu Wang, Huazheng Wang, Qi Qi, Zirui Zhuang, Jing Wang

TAMP: Token-Adaptive Layerwise Pruning in Multimodal Large Language Models (2025.findings-acl)

Challenge:	LVLMs often mistakenly determine objects as present in images where they do not exist . authors propose a new benchmark to evaluate object hallucinations by removing objects from images and asking the model whether it can still see the removed objects.
Approach:	They propose a benchmark to evaluate object hallucinations by removing objects from images . they propose oDPO, a direct preference optimization objective based on visual objects .
Outcome:	The proposed benchmark reduces the likelihood of object hallucinations by removing objects from images and asking the model whether it can still see the removed objects.

Copied to clipboard

Jaewoo Lee, Keyang Xuan, Chanakya Ekbote, Sandeep Polisetty, Yi R. Fung, Paul Pu Liang

LEO-MINI: An Efficient Multimodal Large Language Model using Conditional Token Reduction and Mixture of Multi-Modal Experts (2025.emnlp-main)

Challenge:	Existing pruning methods fail to account for unique token attributes across layers and modalities inherent to MLLMs.
Approach:	They propose a pruning framework that takes into account unique token attributes across layers and modalities inherent to MLLMs.
Outcome:	The proposed pruning framework outperforms existing pruning techniques on two state-of-the-art MLLMs.

Copied to clipboard

Yimu Wang, Mozhgan Nasr Azadani, Sean Sedwards, Krzysztof Czarnecki

AesBiasBench: Evaluating Bias and Alignment in Multimodal Language Models for Personalized Image Aesthetic Assessment (2025.emnlp-main)

Challenge:	Recent approaches to reduce visual tokens have been criticized for their computational efficiency and lack of visual reasoning capabilities.
Approach:	They propose a novel multi-modal large language model that reduces the number of visual tokens and simultaneously boosts visual reasoning capabilities.
Outcome:	The proposed model significantly reduces the number of visual tokens and boosts visual reasoning capabilities.

Copied to clipboard

Kun Li, Lai Man Po, Hongzheng Yang, Xuyuan Xu, Kangcheng Liu, Yuzhi Zhao

CLIP Models are Few-Shot Learners: Empirical Studies on VQA and Visual Entailment (2022.acl-long)

Challenge:	Multimodal Large Language Models are increasingly used in Personalized Image Aesthetic Assessment (PIAA) however, their predictions may reflect subtle biases influenced by demographic factors such as gender, age, and education.
Approach:	They propose to evaluate MLLMs along two complementary dimensions: (1) stereotype bias and (2) alignment between model outputs and genuine human aesthetic preferences.
Outcome:	The proposed benchmark covers three subtasks: aesthetic perception, assessment, empathy and alignment between outputs and genuine human aesthetic preferences.

Copied to clipboard

Haoyu Song, Li Dong, Weinan Zhang, Ting Liu, Furu Wei

AHEAD: Attention Head Energy-Aware Dynamics for Hallucination Mitigation in MLLMs (2026.findings-acl)

Challenge:	Previously, CLIP was only regarded as a powerful visual encoder.
Approach:	They propose a parameter-efficient fine-tuning strategy to boost CLIP's few-shot performance on a visual entailment task without introducing any additional pre-training procedure.
Outcome:	The proposed strategy achieves competitive zero/few-shot results on visual question answering and visual entailment tasks without introducing any additional pre-training procedure.

Copied to clipboard

Jiale Chang, Ying Li, Siliang Tang, Yueting Zhuang

Vision-Language Models Can Self-Improve Reasoning via Reflection (2025.naacl-long)

Challenge:	Existing approaches to hallucination mitigation ignore heterogeneous behaviors of attention heads . hallucinosity is a critical barrier to multimodal large language models' reliability, authors say .
Approach:	They propose a framework that quantifies the energetic properties of each attention head during object generation through two potential networks and dynamically adjusts their contributions at inference time.
Outcome:	The proposed framework reduces hallucination rates without fine-tuning the base model while maintaining generation quality.

Copied to clipboard

Kanzhi Cheng, Li YanTao, Fangzhi Xu, Jianbing Zhang, Hao Zhou, Yang Liu

Position Really Matters: Towards a Holistic Approach for Prompt Tuning (2025.findings-naacl)

Challenge:	Chain-of-thought (CoT) has been shown to improve the reasoning capability of large language models (LLMs).
Approach:	They propose a framework which iteratively enhances the model’s Vision-language Reasoning by Reflecting on CoT Rationales.
Outcome:	The proposed framework improves multimodal reasoning on vision-language tasks by 23% to 60% over baselines.

Copied to clipboard

Xianjun Yang, Wei Cheng, Xujiang Zhao, Wenchao Yu, Linda Ruth Petzold, Haifeng Chen

Browse and Concentrate: Comprehending Multimodal Content via Prior-LLM Context Fusion (2024.acl-long)

Challenge:	Prompt tuning is effective in extracting knowledge from foundation models, but its effectiveness is uncertain.
Approach:	They propose a parametric prompt tuning strategy that dynamically determines different factors of prompts based on specific tasks or instances.
Outcome:	The proposed approach improves performance across a wide range of tasks including NLP, vision recognition, and vision-language tasks.

Copied to clipboard

Ziyue Wang, Chi Chen, Yiqi Zhu, Fuwen Luo, Peng Li, Ming Yan, Ji Zhang, Fei Huang, Maosong Sun, Yang Liu

Forgotten Polygons: Multimodal Large Language Models are Shape-Blind (2025.findings-acl)

Challenge:	Multimodal Large Language Models (MLLMs) lack understanding of multi-image and interleaved inputs due to the visual features encoded by frozen encoders before being fed into the LLM backbone.
Approach:	They propose a two phase paradigm to enable in-depth multimodal context fusion prior to feeding the features into LLMs.
Outcome:	The proposed paradigm boosts the performance on 7 multi-image scenarios, contributing to increments on average accuracy by 2.13% and 7.60% against strong MLLMs baselines with 3B and 11B LLMs, respectively.

Copied to clipboard

William Rudman, Michal Golovanevsky, Amir Bar, Vedant Palit, Yann LeCun, Carsten Eickhoff, Ritambhara Singh

MUCAR: Benchmarking Multilingual Cross-Modal Ambiguity Resolution for Multimodal Large Language Models (2025.emnlp-main)

Challenge:	Multimodal Large Language Models struggle with visual reasoning, despite strong performance on vision-language tasks.
Approach:	They propose a visually cued chain-of-thought prompting that enhances multi-step mathematical reasoning by explicitly referencing visual annotations in diagrams.
Outcome:	The proposed model improves GPT-4o's accuracy on an irregular polygon side-counting task from 7% to 93%.

Copied to clipboard

Xiaolong Wang, Zhaolu Kang, Wangyuxuan Zhai, Xinyue Lou, Yunghwei Lai, Ziyue Wang, Yawen Wang, Kaiyu Huang, Yile Wang, Peng Li, Yang Liu

Task-Aware Resolution Optimization for Visual Large Language Models (2025.emnlp-main)

Challenge:	Existing multimodal benchmarks overlook linguistic and visual ambiguities, authors say . ambiguity resolution between modalities is lacking in multimodal large language models .
Approach:	They propose a benchmark to evaluate multimodal ambiguity resolution across multilingual and cross-modal scenarios.
Outcome:	a new benchmark evaluates multimodal ambiguity resolution across multilingual and cross-modal scenarios . the benchmark shows that MLLMs can resolve ambiguities in image-text alignment . however, existing benchmarks often overlook linguistic and visual ambiguties .

Copied to clipboard

Weiqing Luo, Zhen Tan, Yifan Li, Xinyu Zhao, Kwonjoon Lee, Behzad Dariush, Tianlong Chen

WildScore: Benchmarking MLLMs in-the-Wild Symbolic Music Reasoning (2025.emnlp-main)

Challenge:	Existing visual large language models pre-assume a fixed resolution for downstream tasks, leading to sub-optimal performance.
Approach:	They propose a formula to determine the optimal resolution for a given vision-language task . they then propose 'parameter-efficient' fine-tuning technique to extend the visual input resolution .
Outcome:	The proposed method is based on rigorous experiments on vision-language tasks.

Copied to clipboard

Gagan Mundada, Yash Vishe, Amit Namburi, Xin Xu, Zachary Novack, Julian McAuley, Junda Wu

EfficientVLM: Fast and Accurate Vision-Language Models via Knowledge Distillation and Modal-adaptive Pruning (2023.findings-acl)

Challenge:	Recent advances in Multimodal Large Language Models (MLLMs) have demonstrated impressive capabilities across various vision-language tasks.
Approach:	They propose a systematic taxonomy to evaluate MLLMs' ability to interpret real-world music scores and answer complex musicological queries.
Outcome:	The proposed model is based on real-world music scores and user-generated questions and discussions, and is scalable and controlled.

Copied to clipboard

Tiannan Wang, Wangchunshu Zhou, Yan Zeng, Xinsong Zhang

Images in Language Space: Exploring the Suitability of Large Language Models for Vision & Language Tasks (2023.findings-acl)

Challenge:	Pre-trained vision-language models have achieved impressive results in a range of vision-linguistic tasks.
Approach:	They propose a distilling then pruning framework to compress large vision-language models into smaller, faster ones.
Outcome:	The proposed framework reduces the size of a pre-trained large vision-language model and improves its performance on vision-linguistic tasks.

Copied to clipboard

Sherzod Hakimov, David Schlangen

VisiPruner: Decoding Discontinuous Cross-Modal Dynamics for Efficient Multimodal LLMs (2025.emnlp-main)

Challenge:	Large language models have demonstrated robust performance on various language tasks using zero-shot or few-shot learning paradigms.
Approach:	They propose to use open-source, open-access language models to make visual input accessible to the model using separate verbalisation models.
Outcome:	The proposed model can handle visual input but also require strong reasoning component.

Copied to clipboard

Yingqi Fan, Anhao Zhao, Jinlan Fu, Junlong Tong, Hui Su, Yijie Pan, Wei Zhang, Xiaoyu Shen

Looking Beyond Text: Reducing Language Bias in Large Vision-Language Models via Multimodal Dual-Attention and Soft-Image Guidance (2025.emnlp-main)

Challenge:	Multimodal Large Language Models (MLLMs) suffer from significant computational overhead due to the quadratic growth of attention computations with the number of multimodal tokens.
Approach:	They propose a training-free pruning framework that prunes multimodal tokens without a trained pruning method.
Outcome:	The proposed pruning framework outperforms existing token pruning methods and generalizes across diverse MLLMs.

Copied to clipboard

Haozhe Zhao, Shuzheng Si, Liang Chen, Yichi Zhang, Maosong Sun, Baobao Chang, Minjia Zhang

MMEvol: Empowering Multimodal Large Language Models with Evol-Instruct (2025.findings-acl)

Challenge:	Large vision-language models (LVLMs) have been criticized for their language bias.
Approach:	They propose to use a dual-attention mechanism to construct separate attention for visual and text inputs to enhance integration of visual inputs across models.
Outcome:	Experiments show that the proposed model debiases LVLMs from their language bias, enhancing visual comprehension and reducing hallucinations without additional resources.

Copied to clipboard

Run Luo, Haonan Zhang, Longze Chen, Ting-En Lin, Xiong Liu, Yuchuan Wu, Min Yang, Yongbin Li, Minzheng Wang, Pengpeng Zeng, Lianli Gao, Heng Tao Shen, Yunshui Li, Hamid Alinejad-Rokny, Xiaobo Xia, Jingkuan Song, Fei Huang

Mitigating Coordinate Prediction Bias from Positional Encoding Failures (2026.findings-acl)

Challenge:	a new framework for image-text instruction data evolution improves MLLM performance . lack of high-quality instruction data remains a major bottleneck in ML modeling .
Approach:	They propose a multimodal instruction data evolution framework that iteratively enhances data quality through fine-grained perception, cognitive reasoning, and interaction evolution.
Outcome:	The proposed approach improves MLLM performance in nine vision-language tasks while using significantly less data.

Copied to clipboard

Xingjian Tao, Yiwei Wang, Yujun Cai, Yihong Luo, Kai Han, Jing Tang

Unveiling the Lack of LVLM Robustness to Fundamental Visual Variations: Why and Path Forward (2025.findings-acl)

Challenge:	Multimodal Large Language Models (MLLMs) excel at general vision-language tasks, but precise coordinate prediction remains a challenge.
Approach:	They propose a training-free, inference-time correction method to correct VPEs . they isolate position-unconditioned tendencies by shuffling VPE and use it to steer digit decoding .
Outcome:	The proposed method is training-free, inference-time correction method . it effectively rectifies coordinate drift, yielding consistent improvements without retraining .

Copied to clipboard

Zhiyuan Fan, Yumeng Wang, Sandeep Polisetty, Yi R. Fung

Robustness in NLP

Challenge:	Large Vision Language Models (LVLMs) have shown impressive performance on various vision-language tasks.
Approach:	They propose a benchmark framework for evaluating Visual Variation Robustness of Large Vision Language Models that incorporates automated evaluation dataset generation and principled metrics for thorough robustness assessment.
Outcome:	The proposed framework identifies a vulnerability to visual variations affecting even advanced models that excel at complex vision-language tasks but significantly underperform on simple tasks like object recognition.

Mitigating Action-Relation Hallucinations in LVLMs via Relation-aware Visual Enhancement (2026.acl-long)

Copied to clipboard

Zhenxin Qin, Qiang Li, Qingzhuo Wang, Ruiyang Qin, Zhihua Wei, Wen Shen

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

Challenge:	Existing research has focused on mitigating object hallucinations but often overlooks more complex relation hallucines, especially action relations involving interactions between objects.
Approach:	They propose a framework to locate action-relevant image regions and enhance the LVLM’s attention to those regions by using a Relation-aware Visual Enhancement method.
Outcome:	The proposed method achieves superior performance in mitigating action-relation hallucinations with negligible additional inference cost.

Copied to clipboard

ZiXuan Chen, Juncheng Tao, Ziqian Zeng

NUMINA: A Natural Understanding Benchmark for Multi-dimensional Intelligence and Numerical Reasoning Abilities (2025.findings-emnlp)

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

Changyu Zeng, Yifan Wang, Zimu Wang, Wei Wang, Zhengni Yang, Muyi Bao, Jimin Xiao, Anh Nguyen, Yutao Yue

Reasoning

Challenge:	Existing 3D benchmarks lack fine-grained numerical reasoning task annotations, limiting MLLMs’ ability to perform precise spatial measurements and complex numerical reasoning.
Approach:	They propose a 3D-based benchmark to enhance indoor perceptual understanding by using multi-scale annotations and question-answer pairs.
Outcome:	The proposed benchmark improves indoor perceptual understanding by incorporating multi-scale annotations and question-answer pairs.

MIBench: Evaluating Multimodal Large Language Models over Multiple Images (2024.emnlp-main)

Copied to clipboard

Haowei Liu, Xi Zhang, Haiyang Xu, Yaya Shi, Chaoya Jiang, Ming Yan, Ji Zhang, Fei Huang, Chunfeng Yuan, Bing Li, Weiming Hu

VLN-MME: Diagnosing MLLMs as Language-guided Visual Navigation Agents (2026.acl-long)

Challenge:	Existing benchmarks and MLLMs focus on single-image input scenarios, leaving performance of ML models when handling multiple images underexplored.
Approach:	They propose a benchmark to evaluate fine-grained abilities of multimodal large language models in multi-image scenarios.
Outcome:	The proposed benchmark categorizes the multi-image abilities into three scenarios: MII, MKS and MIC.

Copied to clipboard

Xunyi Zhao, Gengze Zhou, Qi Wu

SmartTrim: Adaptive Tokens and Attention Pruning for Efficient Vision-Language Models (2024.lrec-main)

Challenge:	Multimodal Large Language Models have demonstrated remarkable capabilities across vision-language tasks, but their performance as embodied agents needs further exploration.
Approach:	They propose a framework to evaluate multimodal large language models as zero-shot agents . they find that enhancing prevalent agents with Chain-of-Thought reasoning and self-reflection leads to an unexpected performance decrease.
Outcome:	The proposed framework enables comparisons and component-level ablations across diverse MLLM architectures, agent designs, and navigation tasks.

Copied to clipboard

Zekun Wang, Jingchang Chen, Wangchunshu Zhou, Haichao Zhu, Jiafeng Liang, Liping Shan, Ming Liu, Dongliang Xu, Qing Yang, Bing Qin

Seeing but Not Thinking: Routing Distraction in Multimodal Mixture-of-Experts (2026.acl-long)

Challenge:	Experimental results show that SmartTrim accelerates the original model by 2-3 times with minimal performance degradation.
Approach:	They propose an adaptive acceleration framework which prunes redundant token representations and attention heads within each layer of the original model.
Outcome:	The proposed framework accelerates the original model by 2-3 times with minimal performance degradation across vision-language tasks.

Copied to clipboard

Haolei Xu, Haiwen Hong, Hongxing Li, Rui Zhou, Yang Zhang, Longtao Huang, Hui Xue, Yongliang Shen, Weiming Lu, Yueting Zhuang

Benchmarking and Mitigating MCQA Selection Bias of Large Vision-Language Models (2025.emnlp-main)

Challenge:	Existing multimodal Mixture-of-Experts models accurately perceive image content yet fail in subsequent reasoning . Seeing but not thinking phenomenon is a puzzling phenomenon .
Approach:	They propose a routing-guided intervention method that enhances domain expert activation.
Outcome:	The proposed method achieves consistent improvements on visual reasoning tasks.

Copied to clipboard

Md. Atabuzzaman, Ali Asgarov, Chris Thomas