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