LARGE VISION-LANGUAGE MODELS

Datasets and Recipes for Video Temporal Grounding via Reinforcement Learning (2025.emnlp-industry)

Challenge:	LVLMs are known for producing text that is factually inconsistent with visual input . factuality of generated captions for structured visuals has not been studied as much .
Approach:	They propose a typology of factual errors in captions generated by large vision-language models . they propose CHOCOLATE, a visual entailment model that outperforms current models based on this analysis .
Outcome:	The proposed model outperforms current models in evaluating caption factuality.

Copied to clipboard

Ruizhe Chen, Tianze Luo, Zhiting Fan, Heqing Zou, Zhaopeng Feng, Guiyang Xie, Hansheng Zhang, Zhuochen Wang, Zuozhu Liu, Zhang Huaijian

StarFlow: Generating Structured Workflow Outputs From Sketch Images (2026.eacl-long)

Challenge:	Existing methods for video temporal grounding suffer from limited temporal awareness and poor generalization.
Approach:	They propose a two-stage training framework that integrates supervised fine-tuning with reinforcement learning to improve both the accuracy and robustness of VTG models.
Outcome:	The proposed training framework outperforms existing models on multiple benchmarks on open-domain and challenging scenarios.

Copied to clipboard

Patrice Bechard, Chao Wang, Amirhossein Abaskohi, Juan A. Rodriguez, Christopher Pal, David Vazquez, Spandana Gella, Sai Rajeswar, Perouz Taslakian

Generating Vehicular Icon Descriptions and Indications Using Large Vision-Language Models (2024.emnlp-industry)

Challenge:	Despite being widely used, building workflows can be complex, often requiring manual configuration through low-code platforms or visual programming tools.
Approach:	They propose a framework for generating structured workflow outputs from sketches using vision-language models to automate the process.
Outcome:	The proposed framework outperforms large vision-language models in the task of generating structured workflow outputs from sketches and diagrams.

Copied to clipboard

James Fletcher, Nicholas Dehnen, Seyed Nima Tayarani Bathaie, Aijun An, Heidar Davoudi, Ron DiCarlantonio, Gary Farmaner

Learning the Visualness of Text Using Large Vision-Language Models (2023.emnlp-main)

Challenge:	Existing image description systems are trained mainly on natural images, whereas icon images are drawings.
Approach:	They propose to use a dataset to generate both visual and functional icon descriptions based on the icon image and its context information in the car manual.
Outcome:	The proposed model performs well on the dashboard icon description task while the third model perform poorly.

Copied to clipboard

Gaurav Verma, Ryan Rossi, Christopher Tensmeyer, Jiuxiang Gu, Ani Nenkova

Autonomous Aspect-Image Instruction a2II: Q-Former Guided Multimodal Sentiment Classification (2024.lrec-main)

Challenge:	Visual text evokes an image in a person’s mind, while non-visual text fails to do so.
Approach:	They propose a method to automatically detect visualness in text to enable text-to-image retrieval and generation models to augment text with relevant images.
Outcome:	The proposed method performs better than several baseline models and heuristics for the task.

Copied to clipboard

Junjia Feng, Mingqian Lin, Lin Shang, Xiaoying Gao

Information Retrieval

Challenge:	Existing methods to identify sentiment polarities of aspects are limited by the limited multimodal data available.
Approach:	They propose to use instruction tuning paradigm to combine language and vision data to combine text and image modalities.
Outcome:	The proposed model achieves state-of-the-art on benchmark datasets and in few-shot settings.

Mitigating Hallucinations in Multimodal Spatial Relations through Constraint-Aware Prompting (2025.findings-naacl)

Copied to clipboard

Jiarui Wu, Zhuo Liu, Hangfeng He

Responsible & Trustworthy NLP

Challenge:	Existing research has explored methods to enhance the performance of large vision-language models in spatial relations.
Approach:	They propose a constraint-aware prompting framework to reduce spatial relation hallucinations by incorporating two types of constraints into the prompt.
Outcome:	The proposed framework improves on three widely-used spatial relation datasets.

FaithScore: Fine-grained Evaluations of Hallucinations in Large Vision-Language Models (2024.findings-emnlp)

Copied to clipboard

Liqiang Jing, Ruosen Li, Yunmo Chen, Xinya Du

MEENA (PersianMMMU): Multimodal-Multilingual Educational Exams for N-level Assessment (2026.findings-eacl)

Challenge:	Large Language Models (LLMs) lack the capacity to handle multimodal inputs effectively.
Approach:	They introduce a reference-free and fine-grained evaluation metric that measures the faithfulness of the generated free-form answers from large vision-language models.
Outcome:	The proposed metric measures the faithfulness of free-form answers from large vision-language models.

Copied to clipboard

Omid Ghahroodi, Arshia Hemmat, Marzia Nouri, Seyed Mohammad Hadi Hosseini, Doratossadat Dastgheib, Mohammad Vali Sanian, Alireza Sahebi, Reihaneh Zohrabi, Mohammad Hossein Rohban, Ehsaneddin Asgari, Mahdieh Soleymani Baghshah

Can We Trust AI Doctors? A Survey of Medical Hallucination in Large Language and Large Vision-Language Models (2025.findings-acl)

Challenge:	Recent advances in large vision-language models have primarily focused on English, with limited attention given to other languages.
Approach:	They propose a dataset to evaluate Persian VLMs across scientific, reasoning, and human-level understanding tasks.
Outcome:	The proposed model performs well across scientific reasoning, reasoning, and human-level understanding tasks in Persian and English.

Copied to clipboard

Zhihong Zhu, Yunyan Zhang, Xianwei Zhuang, Fan Zhang, Zhongwei Wan, Yuyan Chen, QingqingLong QingqingLong, Yefeng Zheng, Xian Wu

Black-Box Tuning of Vision-Language Models with Effective Gradient Approximation (2023.findings-emnlp)

Challenge:	Hallucination is a critical challenge for large language models and large vision-language models (LVLMs) however, dedicated research on medical hallucinations remains unexplored.
Approach:	They provide a unified perspective on medical hallucination for both LLMs and LVLMs, and delve into its causes.
Outcome:	The proposed models have demonstrated impressive performance on a variety of medical benchmarks.

Copied to clipboard

Zixian Guo, Yuxiang Wei, Ming Liu, Zhilong Ji, Jinfeng Bai, Yiwen Guo, Wangmeng Zuo

VLFeedback: A Large-Scale AI Feedback Dataset for Large Vision-Language Models Alignment (2024.emnlp-main)

Challenge:	Large vision-language models are often not open-source due to preventing abuse or commercial factors.
Approach:	They propose a method for parameter-efficient fine-tuning to improve model accessibility . large models are often not open-source due to preventing abuse or commercial factors . they propose implementing a lightweight adapter over the output feature of an inaccessible model .
Outcome:	The proposed methods improve on 11 benchmarks and are made publicly available.

Copied to clipboard

Lei Li, Zhihui Xie, Mukai Li, Shunian Chen, Peiyi Wang, Liang Chen, Yazheng Yang, Benyou Wang, Lingpeng Kong, Qi Liu

Generating Questions, Answers, and Distractors for Videos: Exploring Semantic Uncertainty of Object Motions (2025.findings-acl)

Challenge:	Large vision-language models (LVLMs) are evolving rapidly and require data with human supervision to achieve better alignment.
Approach:	They introduce VLFeedback, the first large-scale vision-language feedback dataset . they train Silkie, an LVLM fine-tuned via direct preference optimization .
Outcome:	The proposed model outperforms its base model in helpfulness, visual faithfulness, and safety metrics and exhibits enhanced resilience against red-teaming attacks.

Copied to clipboard

Wenjian Ding, Yao Zhang, Jun Wang, Adam Jatowt, Zhenglu Yang

Logical Closed Loop: Uncovering Object Hallucinations in Large Vision-Language Models (2024.findings-acl)

Challenge:	Existing video QADs are generated using video captions, incurring significant costs and resulting in bias.
Approach:	They propose to use temporal motion to describe video objects to generate diverse QADs focusing on different objects and interactions.
Outcome:	The proposed approach improves consistency and diversity of generated QADs on the NExT-QA and Perception Test benchmarks.

Copied to clipboard

Junfei Wu, Qiang Liu, Ding Wang, Jinghao Zhang, Shu Wu, Liang Wang, Tieniu Tan

Beyond Words: Exploring Cultural Value Sensitivity in Multimodal Models (2025.findings-naacl)

Challenge:	Object hallucination has been an Achilles’ heel which hinders the broader applications of large vision-language models (LVLMs).
Approach:	They propose a logical closed loop-based framework for Object Hallucination Detection and Mitigation that uses logical consistency probing to raise questions with logical correlations to determine hallucinations.
Outcome:	The proposed method can be applied to all existing LVLMs and is effective and general.

Copied to clipboard

Srishti Yadav, Zhi Zhang, Daniel Hershcovich, Ekaterina Shutova

BBA: Bi-Modal Behavioral Alignment for Reasoning with Large Vision-Language Models (2024.findings-acl)

Challenge:	Using large vision-language models to understand cultural contexts is a critical area of research.
Approach:	They conduct a thorough evaluation of multimodal models at different scales, focusing on their alignment with cultural values.
Outcome:	The proposed models show that they exhibit sensitivity to cultural values but their performance is highly context-dependent.

Copied to clipboard

Xueliang Zhao, Xinting Huang, Tingchen Fu, Qintong Li, Shansan Gong, Lemao Liu, Wei Bi, Lingpeng Kong

AdDriftBench: A Benchmark for Detecting Data Drift and Label Drift in Short Video Advertising (2025.findings-emnlp)

Challenge:	Multimodal reasoning is a key capability for large vision-language models . however, the vanilla Chain-of-Thought method fails to address critical steps in multi-step reasoning tasks.
Approach:	They propose a bi-modal Behavioral Alignment method to augment multimodal reasoning . they use domain-specific language to integrate multimodal information into a precise alternative form .
Outcome:	The proposed method significantly improves GPT-4V(ision) on geometry problem solving, chess positional advantage prediction and molecular property prediction.

Copied to clipboard

Yinghao Song, Xiangji Zeng, Shuai Cui, Lu Sun, Zhaowei Liu, Yuan Yuan, Yulu Wang, Hai Zhou, Zhaohan Gong

On the Perception Bottleneck of VLMs for Chart Understanding (2025.findings-emnlp)

Challenge:	Short video advertising scenarios present unique challenges due to data drift (DD) and label drift (LD).
Approach:	They propose to use data drift and label drift to evaluate models under rapidly shifting content distributions and labeling scenarios to assess their generalization capabilities.
Outcome:	The proposed model performs moderately in short video advertising contexts, particularly in handling fine-grained semantics and adapting to shifting instructions.

Copied to clipboard

Junteng Liu, Weihao Zeng, Xiwen Zhang, Yijun Wang, Zifei Shan, Junxian He

Making Every Step Effective: Jailbreaking Large Vision-Language Models Through Hierarchical KV Equalization (2025.findings-emnlp)

Challenge:	a perception bottleneck in large vision-language models is critical for chart understanding . instruction tuning improves the extraction capability of LVLMs, but the vision encoder remains a bottleneck .
Approach:	They propose to decompose the perception bottleneck into two components . the vision encoder bottleneck is where visual representation fails to encapsulate the correct information .
Outcome:	The proposed approach significantly mitigates the vision encoder bottleneck and improves the ability of LVLMs to comprehend charts.

Copied to clipboard

Shuyang Hao, Yiwei Wang, Bryan Hooi, Jun Liu, Muhao Chen, Zi Huang, Yujun Cai

Robustness in NLP

Challenge:	HKVE selectively accepts gradient optimization results based on the distribution of attention scores across different layers, ensuring that every optimization step positively contributes to the attack.
Approach:	They propose a framework that selectively accepts gradient optimization results based on the distribution of attention scores across different layers and selectively takes them into account when calculating the attack success rate.
Outcome:	The proposed framework outperforms existing methods by achieving success rates of 75.08% on MiniGPT4, 85.84% on LLaVA and 81.00% on Qwen-VL.

VisDiaHalBench: A Visual Dialogue Benchmark For Diagnosing Hallucination in Large Vision-Language Models (2024.acl-long)

Copied to clipboard

Qingxing Cao, Junhao Cheng, Xiaodan Liang, Liang Lin

A Closer Look at Bias and Chain-of-Thought Faithfulness of Large (Vision) Language Models (2025.findings-emnlp)

Challenge:	Despite the significant success of large vision-language models, some studies have revealed that LVLMs suffer from the hallucination problem when given long-term misleading textual history.
Approach:	They propose a visual dialogue hallucination evaluation benchmark VisDiaHalBench to investigate the halluciation problem of large vision-language models when given long-term misleading textual history.
Outcome:	The proposed benchmark consists of samples with five-turn questions about an edited image and its original version.

Copied to clipboard

Sriram Balasubramanian, Samyadeep Basu, Soheil Feizi

HiddenDetect: Detecting Jailbreak Attacks against Multimodal Large Language Models via Monitoring Hidden States (2025.acl-long)

Challenge:	Chain-of-thought reasoning improves performance of large language models, but is it faithfully reflecting internal processes?
Approach:	They propose a new evaluation pipeline for categorizing bias articulation patterns and a novel evaluation pipeline to examine CoT faithfulness in large vision-language models.
Outcome:	The proposed evaluation pipeline enables significantly more precise analysis of CoT reasoning than previous methods.

Copied to clipboard

Yilei Jiang, Xinyan Gao, Tianshuo Peng, Yingshui Tan, Xiaoyong Zhu, Bo Zheng, Xiangyu Yue

Semantic Text Processing

Challenge:	Existing studies focus on posthoc alignment techniques, but the underlying safety mechanisms within LVLMs remain unexplored.
Approach:	They propose a tuning-free framework that leverages internal activations to enhance safety.
Outcome:	The proposed framework outperforms state-of-the-art methods in detecting jailbreak attacks against large vision-language models.

SHARP: Steering Hallucination in LVLMs via Representation Engineering (2025.emnlp-main)

Copied to clipboard

Junfei Wu, Yue Ding, Guofan Liu, Tianze Xia, Ziyue Huang, Dianbo Sui, Qiang Liu, Shu Wu, Liang Wang, Tieniu Tan

Semantic Text Processing

Challenge:	Large Vision-Language Models (LVLMs) generate responses that are plausible but incorrect or unsupported—commonly referred to as hallucinations.
Approach:	They propose a representation-level intervention framework that modulates hallucination-related features during inference by probing their encoded features.
Outcome:	The proposed framework reduces hallucinations while maintaining the performance and generalization capabilities of Large Vision-Language Models (LVLMs).

Evaluating Model Alignment with Human Perception: A Study on Shitsukan in LLMs and LVLMs (2025.coling-main)

Copied to clipboard

Daiki Shiono, Ana Brassard, Yukiko Ishizuki, Jun Suzuki

Semantic Text Processing

Challenge:	This work examines the alignment of large language models and large vision-language models with human perception.
Approach:	They use a dataset of shitsukan terms elicited from individuals in response to object images to evaluate their understanding of the Japanese concept of shitukan.
Outcome:	The proposed models demonstrated mixed accuracy across benchmark tasks, with limited overlap between model- and human-generated terms.

Movie101v2: Improved Movie Narration Benchmark (2025.acl-long)

Copied to clipboard

Zihao Yue, Yepeng Zhang, Ziheng Wang, Qin Jin

MVL-SIB: A Massively Multilingual Vision-Language Benchmark for Cross-Modal Topical Matching (2025.findings-acl)

Challenge:	Automatic movie narration aims to generate video-aligned plot descriptions to assist visually impaired audiences.
Approach:	They propose to break down the ultimate goal of automatic movie narration into three stages . they propose a large-scale, bilingual dataset with enhanced data quality .
Outcome:	The proposed dataset breaks down the goal of automatic movie narration into three stages . achieving applicable movie narration is a fascinating goal that requires significant research .

Copied to clipboard

Fabian David Schmidt, Florian Schneider, Chris Biemann, Goran Glavaš

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

Challenge:	Existing multilingual vision-language (VL) benchmarks typically only cover a handful of languages, underscoring the need for evaluation data for low-resource languages.
Approach:	They propose a multilingual vision-language benchmark that evaluates cross-modal and text-only topical matching across 205 languages.
Outcome:	The proposed model performs better in cross-modal and text-only topical matching in lower-resource languages than the most multilingual benchmarks.

Copied to clipboard

Tiannan Wang, Wangchunshu Zhou, Yan Zeng, Xinsong Zhang

BloomVQA: Assessing Hierarchical Multi-modal Comprehension (2024.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

Yunye Gong, Robik Shrestha, Jared Claypoole, Michael Cogswell, Arijit Ray, Christopher Kanan, Ajay Divakaran

GeoArena: Evaluating Open-World Geographic Reasoning in Large Vision-Language Models (2026.acl-long)

Challenge:	Recent advances of machine intelligence solutions have demonstrated tremendous success in a wide range of language and multi-modal tasks over diverse domains.
Approach:	They propose a VQA dataset to facilitate comprehensive evaluation of large vision-language models on comprehension tasks.
Outcome:	The proposed dataset shows improved accuracy over all comprehension levels and a tendency to bypass visual inputs especially for higher-level tasks.

Copied to clipboard

Pengyue Jia, Yingyi Zhang, Xiangyu Zhao, Sharon Li

ChartQAPro: A More Diverse and Challenging Benchmark for Chart Question Answering (2025.findings-acl)

Challenge:	Existing evaluation paradigms for geographic reasoning are outcome-centric and focus on label matching, leaving the underlying linguistic reasoning chains as unexamined black boxes.
Approach:	They propose a dynamic, human-preference-based evaluation framework for benchmarking open-world geographic reasoning.
Outcome:	The proposed framework reframes evaluation as a pairwise reasoning alignment task on in-the-wild images, where human judges compare model-generated explanations based on reasoning quality, evidence synthesis, and plausibility.

Copied to clipboard

Ahmed Masry, Mohammed Saidul Islam, Mahir Ahmed, Aayush Bajaj, Firoz Kabir, Aaryaman Kartha, Md Tahmid Rahman Laskar, Mizanur Rahman, Shadikur Rahman, Mehrad Shahmohammadi, Megh Thakkar, Md Rizwan Parvez, Enamul Hoque, Shafiq Joty

Natural Language Interfaces

Challenge:	Chart Question Answering systems are limited in their ability to interpret data visually and reason with visual representations.
Approach:	They propose a chart-based chart question-answering system that includes 1,341 charts from 99 diverse sources and 1,948 questions in various types.
Outcome:	The new benchmark includes 1,341 charts from 99 diverse sources and 1,948 questions in various types.

From Observation to Understanding: Front-Door Adjustments with Uncertainty Calibration for Enhancing Egocentric Reasoning in LVLMs (2025.findings-acl)

Copied to clipboard

Shenshen Li, Wenxin Meng, Lei Wang, Hao Yang, Chong Peng, Peng Yan, Fumin Shen, Jingkuan Song, Heng Tao Shen, Xing Xu

Low-Resource NLP

Challenge:	Existing methods that adapt LVLMs to egocentric tasks overlook critical agent-environment interactions, limiting their ability to perform egoic reasoning.
Approach:	They propose a zero-shot paradigm to enhance egocentric reasoning by simulating human causal reasoning by formalizing ego-centric reasoning using a structural causal model.
Outcome:	The proposed method improves egocentric reasoning abilities on six tasks.

In-Context Compositional Generalization for Large Vision-Language Models (2024.emnlp-main)

Copied to clipboard

Chuanhao Li, Chenchen Jing, Zhen Li, Mingliang Zhai, Yuwei Wu, Yunde Jia

World Modeling Makes a Better Planner: Dual Preference Optimization for Embodied Task Planning (2025.acl-long)

Challenge:	Recent work shows that in-context learning for large language models exhibits compositional generalization capacity.
Approach:	They propose a method to exhibit in-context compositional generalization in large vision-language models by combining visual and linguistic modalities.
Outcome:	The proposed method reduces redundancy and complexity in in-context learning with LVLMs.

Copied to clipboard

Siyin Wang, Zhaoye Fei, Qinyuan Cheng, Shiduo Zhang, Panpan Cai, Jinlan Fu, Xipeng Qiu

Green & Sustainable NLP

Challenge:	Existing approaches focus on action selection or use pre-trained models as world models to enhance planning capabilities.
Approach:	They propose a new learning framework that optimizes state prediction and action selection through preference learning.
Outcome:	The proposed method outperforms existing methods and GPT-4o on VoTa-Bench and Qwen2-VL (7B), LLaVA-1.6 (7B) and LLama-3.2 (11B).

CELLO: Causal Evaluation of Large Vision-Language Models (2024.emnlp-main)

Copied to clipboard

Meiqi Chen, Bo Peng, Yan Zhang, Chaochao Lu

Pearl: A Multimodal Culturally-Aware Arabic Instruction Dataset (2025.findings-emnlp)

Challenge:	Recent advances in large vision-language models have improved causal reasoning abilities . however, current models struggle with tasks like causal reasoning .
Approach:	They propose a fine-grained and unified definition of causality involving interactions between humans and objects.
Outcome:	The proposed model surpasses traditional commonsense causality by including explicit causal graphs . it also shows that current LVLMs can benefit from a causally inspired prompting strategy .

Copied to clipboard

Fakhraddin Alwajih, Samar M. Magdy, Abdellah El Mekki, Omer Nacar, Youssef Nafea, Safaa Taher Abdelfadil, Abdulfattah Mohammed Yahya, Hamzah Luqman, Nada Almarwani, Samah Aloufi, Baraah Qawasmeh, Houdaifa Atou, Serry Sibaee, Hamzah A. Alsayadi, Walid Al-Dhabyani, Maged S. Al-shaibani, Aya El aatar, Nour Qandos, Rahaf Alhamouri, Samar Ahmad, Mohammed Anwar AL-Ghrawi, Aminetou Yacoub, Ruwa AbuHweidi, Vatimetou Mohamed Lemin, Reem Abdel-Salam, Ahlam Bashiti, Adel Ammar, Aisha Alansari, Ahmed Ashraf, Nora Alturayeif, Alcides Alcoba Inciarte, AbdelRahim A. Elmadany, Mohamedou Cheikh Tourad, Ismail Berrada, Mustafa Jarrar, Shady Shehata, Muhammad Abdul-Mageed

GLIMPSE: Do Large Vision-Language Models Truly Think With Videos or Just Glimpse at Them? (2025.emnlp-main)

Challenge:	Mainstream large vision-language models (LVLMs) inherently encode cultural biases, highlighting the need for diverse multimodal datasets.
Approach:	They propose to construct a large-scale Arabic multimodal dataset and benchmark explicitly designed for cultural understanding.
Outcome:	The proposed dataset covers ten culturally significant domains covering all Arab countries and includes two evaluation benchmarks (PEARL and PEARL-LITE) and a specialized subset (PearL-X).

Copied to clipboard

Yiyang Zhou, Linjie Li, Shi Qiu, Zhengyuan Yang, Yuyang Zhao, Siwei Han, Yangfan He, Kangqi Li, Haonian Ji, Zihao Zhao, Haibo Tong, Lijuan Wang, Huaxiu Yao

VISA: Retrieval Augmented Generation with Visual Source Attribution (2025.acl-long)

Challenge:	Existing video benchmarks often resemble image-based questions with scans of only a few key frames, without deep temporal reasoning.
Approach:	They propose a video benchmark to assess whether large vision-language models can genuinely think with videos rather than perform superficial frame-level analysis.
Outcome:	The proposed benchmark consists of 3,269 videos and over 4,342 highly visual-centric questions across 11 categories, including Trajectory Analysis, Temporal Reasoning, and Forensics Detection.

Copied to clipboard

Xueguang Ma, Shengyao Zhuang, Bevan Koopman, Guido Zuccon, Wenhu Chen, Jimmy Lin

CausalVLBench: Benchmarking Visual Causal Reasoning in Large Vision-Language Models (2025.emnlp-main)

Challenge:	Existing approaches to retrieval-augmented generation primarily link generated content to document-level references, making it difficult for users to locate evidence among multiple content-rich retrieved documents.
Approach:	They propose a novel approach that combines answer generation with visual source attribution by leveraging large vision-language models to identify evidence and highlight exact regions that support the generated answers with bounding boxes in the retrieved document screenshots.
Outcome:	The proposed approach identifies evidence and highlights exact regions that support the generated answers with bounding boxes in the retrieved document screenshots.

Copied to clipboard

Aneesh Komanduri, Karuna Bhaila, Xintao Wu

Autoregressive Semantic Visual Reconstruction Helps VLMs Understand Better (2026.findings-acl)

Challenge:	Large vision-language models have shown impressive ability in various language tasks, especially with their emergent in-context learning capability.
Approach:	They propose a causal reasoning benchmark for multi-modal in-context learning from large vision-language models that incorporates visual inputs.
Outcome:	The proposed model outperforms existing models on three visual causal reasoning tasks and demonstrates their strengths and weaknesses.

Copied to clipboard

Dianyi Wang, Wei Song, Yikun Wang, Siyuan Wang, Kaicheng Yu, Zhongyu Wei, Jiaqi Wang

Multimodal Dual-Path Decoding for Medical Report Generation (2026.findings-acl)

Challenge:	Typical large vision-language models emphasize vision-to-language alignment while overlooking fine-grained visual information.
Approach:	They introduce autoregressive semantic visual reconstruction (ASVR) that enables joint learning of visual and textual modalities within a unified autoregression framework.
Outcome:	The proposed model improves baselines and multimodal understanding benchmarks by 2-3%.

Copied to clipboard

Jinghan Sun, Dong Wei, Zhihong Zhu, Yuyang Xue, Steven McDonagh, Xian Wu

Inject to Heal: Alleviating hallucination in LVLMs via Context Embedding Injection (2026.findings-acl)

Challenge:	Current methods for radiology report generation rely on encoder-decoder based frameworks that fail to integrate multimodal clinical evidence with domain-specific knowledge.
Approach:	They propose a multimodal dual-path framework that synergistically integrates large vision-language models and large language models for radiology report generation.
Outcome:	The proposed framework improves on the public MIMIC-CXR benchmark and shows that it is superior to state-of-the-art models.

Copied to clipboard

Mehrdad Fazli, Bowen Wei, Ziwei Zhu

FineState-Bench: Benchmarking State-Conditioned Grounding for Fine-grained GUI State Setting (2026.findings-acl)

Challenge:	a large vision-language model can generate hallucinations inconsistent with visual input . a lightweight method that embeds the last input token as a grounding signal reduces the likelihood of hallucinosity.
Approach:	They propose a training-free mitigation strategy that harnesses the hidden state of the last input token as a grounding signal to maintain visual fidelity throughout decoding and curb hallucinations.
Outcome:	The proposed method outperforms state-of-the-art methods on CHAIR, AMBER, and MMHal benchmarks.

Copied to clipboard

Fengxian Ji, Jingpu Yang, Zirui Song, Yuanxi Wang, Zhexuan Cui, Yuke Li, Qian Jiang, Xiuying Chen