Proceedings of the 4th Workshop on Advances in Language and Vision Research (ALVR)

Proceedings of the 4th Workshop on Advances in Language and Vision Research (ALVR) Qianqi Yan editor Syrielle Montariol editor Yue Fan editor Jing Gu editor Jiayi Pan editor Manling Li editor Parisa Kordjamshidi editor Alane Suhr editor Xin Eric Wang editor 2026-07 Association for Computational Linguistics San Diego, California, USA text conference publication 979-8-89176-398-2 alvr-2026-main https://aclanthology.org/2026.alvr-main.0/ Thinking in Pictures: A Diagnostic Study of Visual vs. Textual Chain-of-Thought Reasoning in Vision-Language Models Ben Jenkins author 2026-07 text Proceedings of the 4th Workshop on Advances in Language and Vision Research (ALVR) Qianqi Yan editor Syrielle Montariol editor Yue Fan editor Jing Gu editor Jiayi Pan editor Manling Li editor Parisa Kordjamshidi editor Alane Suhr editor Xin Eric Wang editor Association for Computational Linguistics San Diego, California, USA conference publication 979-8-89176-398-2 jenkins-2026-thinking https://aclanthology.org/2026.alvr-main.1/ 2026-07 1 12 A Zipfian Analysis of Visual Token Distributions for AI-Generated Images Andrew Shin author 2026-07 text Proceedings of the 4th Workshop on Advances in Language and Vision Research (ALVR) Qianqi Yan editor Syrielle Montariol editor Yue Fan editor Jing Gu editor Jiayi Pan editor Manling Li editor Parisa Kordjamshidi editor Alane Suhr editor Xin Eric Wang editor Association for Computational Linguistics San Diego, California, USA conference publication 979-8-89176-398-2 shin-2026-zipfian https://aclanthology.org/2026.alvr-main.2/ 2026-07 13 17 Semantically Aware Optimal Transport for Dense Label Transfer Preeti author Kiran Ravish author Ankita Kushwaha author Pawan Kumar author 2026-07 text Proceedings of the 4th Workshop on Advances in Language and Vision Research (ALVR) Qianqi Yan editor Syrielle Montariol editor Yue Fan editor Jing Gu editor Jiayi Pan editor Manling Li editor Parisa Kordjamshidi editor Alane Suhr editor Xin Eric Wang editor Association for Computational Linguistics San Diego, California, USA conference publication 979-8-89176-398-2 preeti-etal-2026-semantically https://aclanthology.org/2026.alvr-main.3/ 2026-07 18 45 CoSMoEs: Compact Sparse Mixture of Experts Patrick Huber author Akshat Shrivastava author Ernie Chang author Chinnadhurai Sankar author Ahmed A Aly author Adithya Sagar author 2026-07 text Proceedings of the 4th Workshop on Advances in Language and Vision Research (ALVR) Qianqi Yan editor Syrielle Montariol editor Yue Fan editor Jing Gu editor Jiayi Pan editor Manling Li editor Parisa Kordjamshidi editor Alane Suhr editor Xin Eric Wang editor Association for Computational Linguistics San Diego, California, USA conference publication 979-8-89176-398-2 huber-etal-2026-cosmoes https://aclanthology.org/2026.alvr-main.4/ 2026-07 46 56 GraphicWeaver: Benchmarking Agentic Planning for Graphic Design Generation Dayeon Ki author Tianyi Zhou author Marine Carpuat author Gang Wu author Puneet Mathur author Viswanathan Swaminathan author 2026-07 text Proceedings of the 4th Workshop on Advances in Language and Vision Research (ALVR) Qianqi Yan editor Syrielle Montariol editor Yue Fan editor Jing Gu editor Jiayi Pan editor Manling Li editor Parisa Kordjamshidi editor Alane Suhr editor Xin Eric Wang editor Association for Computational Linguistics San Diego, California, USA conference publication 979-8-89176-398-2 ki-etal-2026-graphicweaver https://aclanthology.org/2026.alvr-main.5/ 2026-07 57 84 Scaling Vision–Language Models for Pharmaceutical Long-Form Video Reasoning on Industrial GenAI Platform Suyash Mishra author Qiang Li author Srikanth Patil author Satyanarayan Pati author Baddu Narendra author 2026-07 text Proceedings of the 4th Workshop on Advances in Language and Vision Research (ALVR) Qianqi Yan editor Syrielle Montariol editor Yue Fan editor Jing Gu editor Jiayi Pan editor Manling Li editor Parisa Kordjamshidi editor Alane Suhr editor Xin Eric Wang editor Association for Computational Linguistics San Diego, California, USA conference publication 979-8-89176-398-2 mishra-etal-2026-scaling https://aclanthology.org/2026.alvr-main.7/ 2026-07 85 104 PGGA: A Plan-Grounded GUI Agent for Automated Device Support Lei Hsiung author Zhiyu Chen author Seonhoon Kim author Qun Liu author 2026-07 text Proceedings of the 4th Workshop on Advances in Language and Vision Research (ALVR) Qianqi Yan editor Syrielle Montariol editor Yue Fan editor Jing Gu editor Jiayi Pan editor Manling Li editor Parisa Kordjamshidi editor Alane Suhr editor Xin Eric Wang editor Association for Computational Linguistics San Diego, California, USA conference publication 979-8-89176-398-2 hsiung-etal-2026-pgga https://aclanthology.org/2026.alvr-main.9/ 2026-07 105 114 CAFES: A Collaborative Multi-Agent Framework for Multi-Granular Multimodal Essay Scoring Jiamin Su author Yibo Yan author Zhuoran Gao author Han Zhang author Xiang Liu author Huiyu Zhou author Xuming Hu author 2026-07 text Proceedings of the 4th Workshop on Advances in Language and Vision Research (ALVR) Qianqi Yan editor Syrielle Montariol editor Yue Fan editor Jing Gu editor Jiayi Pan editor Manling Li editor Parisa Kordjamshidi editor Alane Suhr editor Xin Eric Wang editor Association for Computational Linguistics San Diego, California, USA conference publication 979-8-89176-398-2 su-etal-2026-cafes https://aclanthology.org/2026.alvr-main.10/ 2026-07 115 138 GM-PRM: A Generative Multimodal Process Reward Model for Multimodal Mathematical Reasoning Jianghangfan Zhang author Yibo Yan author Kening Zheng author Xin Zou author Song Dai author Xuming Hu author 2026-07 text Proceedings of the 4th Workshop on Advances in Language and Vision Research (ALVR) Qianqi Yan editor Syrielle Montariol editor Yue Fan editor Jing Gu editor Jiayi Pan editor Manling Li editor Parisa Kordjamshidi editor Alane Suhr editor Xin Eric Wang editor Association for Computational Linguistics San Diego, California, USA conference publication 979-8-89176-398-2 zhang-etal-2026-gm https://aclanthology.org/2026.alvr-main.11/ 2026-07 139 154 Look Where You’re Told: Instruction-Consistent Attention for GUI Grounding Seonhoon Kim author Zhiyu Chen author Xin Li author Qun Liu author 2026-07 text Proceedings of the 4th Workshop on Advances in Language and Vision Research (ALVR) Qianqi Yan editor Syrielle Montariol editor Yue Fan editor Jing Gu editor Jiayi Pan editor Manling Li editor Parisa Kordjamshidi editor Alane Suhr editor Xin Eric Wang editor Association for Computational Linguistics San Diego, California, USA conference publication 979-8-89176-398-2 kim-etal-2026-look https://aclanthology.org/2026.alvr-main.12/ 2026-07 155 163 From Pixels to BFS: High Maze Accuracy Does Not Imply Visual Planning Alberto Gonzalo Rodriguez Salgado author 2026-07 text Proceedings of the 4th Workshop on Advances in Language and Vision Research (ALVR) Qianqi Yan editor Syrielle Montariol editor Yue Fan editor Jing Gu editor Jiayi Pan editor Manling Li editor Parisa Kordjamshidi editor Alane Suhr editor Xin Eric Wang editor Association for Computational Linguistics San Diego, California, USA conference publication 979-8-89176-398-2 rodriguez-salgado-2026-pixels https://aclanthology.org/2026.alvr-main.13/ 2026-07 164 179 When Relations Break: Analyzing Relation Hallucination in Vision-Language Model Under Rotation and Noise Philip Wootaek Shin author Ajay Narayanan Sridhar author Lakshmi Sivani Devarapalli author Rui Zhang author Jack Sampson author Vijaykrishnan Narayanan author 2026-07 text Proceedings of the 4th Workshop on Advances in Language and Vision Research (ALVR) Qianqi Yan editor Syrielle Montariol editor Yue Fan editor Jing Gu editor Jiayi Pan editor Manling Li editor Parisa Kordjamshidi editor Alane Suhr editor Xin Eric Wang editor Association for Computational Linguistics San Diego, California, USA conference publication 979-8-89176-398-2 shin-etal-2026-relations https://aclanthology.org/2026.alvr-main.14/ 2026-07 180 185 VLCE: A Knowledge-Enhanced Framework for Image Description in Disaster Assessment Md. Mahfuzur Rahman author Marufa Kamal author Fahad Rahman author Sunzida Siddique author Ahmed Rafi Hasan author Mohd Ariful Haque author Kishor Datta Gupta author Roy George author 2026-07 text Proceedings of the 4th Workshop on Advances in Language and Vision Research (ALVR) Qianqi Yan editor Syrielle Montariol editor Yue Fan editor Jing Gu editor Jiayi Pan editor Manling Li editor Parisa Kordjamshidi editor Alane Suhr editor Xin Eric Wang editor Association for Computational Linguistics San Diego, California, USA conference publication 979-8-89176-398-2 rahman-etal-2026-vlce https://aclanthology.org/2026.alvr-main.15/ 2026-07 186 198 Beyond Visual Similarity: Rule-Guided Multimodal Clustering with explicit domain rules Kishor Datta Gupta author Mohd Ariful Haque author Marufa Kamal author Ahmed Rafi Hasan author Md. Mahfuzur Rahman author Roy George author 2026-07 text Proceedings of the 4th Workshop on Advances in Language and Vision Research (ALVR) Qianqi Yan editor Syrielle Montariol editor Yue Fan editor Jing Gu editor Jiayi Pan editor Manling Li editor Parisa Kordjamshidi editor Alane Suhr editor Xin Eric Wang editor Association for Computational Linguistics San Diego, California, USA conference publication 979-8-89176-398-2 gupta-etal-2026-beyond https://aclanthology.org/2026.alvr-main.16/ 2026-07 199 208 ChartDiff: A Large-Scale Benchmark for Comprehending Pairs of Charts Rongtian Ye author 2026-07 text Proceedings of the 4th Workshop on Advances in Language and Vision Research (ALVR) Qianqi Yan editor Syrielle Montariol editor Yue Fan editor Jing Gu editor Jiayi Pan editor Manling Li editor Parisa Kordjamshidi editor Alane Suhr editor Xin Eric Wang editor Association for Computational Linguistics San Diego, California, USA conference publication 979-8-89176-398-2 ye-2026-chartdiff https://aclanthology.org/2026.alvr-main.19/ 2026-07 209 229 Formal Machine Interpretation for the Semasiographic Mixtec Codices of Precolonial and Early Colonial Mesoamerica Christopher Driggers-Ellis author Gabriel Ayoubi author Girish.Salunke811@Gmail.Com Girish.Salunke811@Gmail.Com author Christan Grant author 2026-07 text Proceedings of the 4th Workshop on Advances in Language and Vision Research (ALVR) Qianqi Yan editor Syrielle Montariol editor Yue Fan editor Jing Gu editor Jiayi Pan editor Manling Li editor Parisa Kordjamshidi editor Alane Suhr editor Xin Eric Wang editor Association for Computational Linguistics San Diego, California, USA conference publication 979-8-89176-398-2 driggers-ellis-etal-2026-formal https://aclanthology.org/2026.alvr-main.20/ 2026-07 230 238 Temporal-Linguistic Adaptive Streaming for Continuous Sign Language Translation Arshia Kermani author Habib Irani author Deautaun Ross author Vangelis Metsis author 2026-07 text Proceedings of the 4th Workshop on Advances in Language and Vision Research (ALVR) Qianqi Yan editor Syrielle Montariol editor Yue Fan editor Jing Gu editor Jiayi Pan editor Manling Li editor Parisa Kordjamshidi editor Alane Suhr editor Xin Eric Wang editor Association for Computational Linguistics San Diego, California, USA conference publication 979-8-89176-398-2 kermani-etal-2026-temporal https://aclanthology.org/2026.alvr-main.21/ 2026-07 239 248 FADE: Probing the Limits of VLMs on fine-grained OCR Deep Shah author Nehal Kathrotia author Sanket Badhe author 2026-07 text Proceedings of the 4th Workshop on Advances in Language and Vision Research (ALVR) Qianqi Yan editor Syrielle Montariol editor Yue Fan editor Jing Gu editor Jiayi Pan editor Manling Li editor Parisa Kordjamshidi editor Alane Suhr editor Xin Eric Wang editor Association for Computational Linguistics San Diego, California, USA conference publication 979-8-89176-398-2 shah-etal-2026-fade https://aclanthology.org/2026.alvr-main.23/ 2026-07 249 259 Efficient Visual Grounding in VQA via Question-Guided Sparse Attention Prasanth author 2026-07 text Proceedings of the 4th Workshop on Advances in Language and Vision Research (ALVR) Qianqi Yan editor Syrielle Montariol editor Yue Fan editor Jing Gu editor Jiayi Pan editor Manling Li editor Parisa Kordjamshidi editor Alane Suhr editor Xin Eric Wang editor Association for Computational Linguistics San Diego, California, USA conference publication 979-8-89176-398-2 prasanth-2026-efficient https://aclanthology.org/2026.alvr-main.24/ 2026-07 260 271 Systematic Performance Degradation in Indic Vision-Language Models: Evidence from Hindi and Telugu Rishikant Chigrupaatii author Ponnada Sai Tulasi Kanishka author Lalit Chandra Routhu author Martin Patel author Sama Supratheek Reddy author Divyam Gupta author Rajiv Misra author Rohun Tripathi author 2026-07 text Proceedings of the 4th Workshop on Advances in Language and Vision Research (ALVR) Qianqi Yan editor Syrielle Montariol editor Yue Fan editor Jing Gu editor Jiayi Pan editor Manling Li editor Parisa Kordjamshidi editor Alane Suhr editor Xin Eric Wang editor Association for Computational Linguistics San Diego, California, USA conference publication 979-8-89176-398-2 chigrupaatii-etal-2026-systematic https://aclanthology.org/2026.alvr-main.26/ 2026-07 272 277 How Fragile Is Vision-Language Alignment? Mapping Concept Disruption Under Text-to-Image Personalization Mujtaba Hasan author 2026-07 text Proceedings of the 4th Workshop on Advances in Language and Vision Research (ALVR) Qianqi Yan editor Syrielle Montariol editor Yue Fan editor Jing Gu editor Jiayi Pan editor Manling Li editor Parisa Kordjamshidi editor Alane Suhr editor Xin Eric Wang editor Association for Computational Linguistics San Diego, California, USA conference publication 979-8-89176-398-2 hasan-2026-fragile https://aclanthology.org/2026.alvr-main.27/ 2026-07 278 286 The Compositional Grounding Gap: Why Vision-Language Models Fail at Relational Reasoning and How to Fix It Kaustubh S Bukkapatnam author 2026-07 text Proceedings of the 4th Workshop on Advances in Language and Vision Research (ALVR) Qianqi Yan editor Syrielle Montariol editor Yue Fan editor Jing Gu editor Jiayi Pan editor Manling Li editor Parisa Kordjamshidi editor Alane Suhr editor Xin Eric Wang editor Association for Computational Linguistics San Diego, California, USA conference publication 979-8-89176-398-2 bukkapatnam-2026-compositional https://aclanthology.org/2026.alvr-main.28/ 2026-07 287 293 HalluTrace: Causal Attribution and Source-Targeted Decoding for Hallucination in Large Vision-Language Models Kaustubh S Bukkapatnam author 2026-07 text Proceedings of the 4th Workshop on Advances in Language and Vision Research (ALVR) Qianqi Yan editor Syrielle Montariol editor Yue Fan editor Jing Gu editor Jiayi Pan editor Manling Li editor Parisa Kordjamshidi editor Alane Suhr editor Xin Eric Wang editor Association for Computational Linguistics San Diego, California, USA conference publication 979-8-89176-398-2 bukkapatnam-2026-hallutrace https://aclanthology.org/2026.alvr-main.29/ 2026-07 294 300