% Key papers for Universal VQA models (scime atlas, https://atlas.scime.ai). Authors are not included: add them from the paper pages.

@inproceedings{cvpr2018_bottom_12877,
  title = {{Bottom-Up and Top-Down Attention for Image Captioning and Visual Question Answering}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2018},
  url = {https://openaccess.thecvf.com/content_cvpr_2018/html/Anderson_Bottom-Up_and_Top-Down_CVPR_2018_paper.html},
}

@inproceedings{cvpr2019_deep_14029,
  title = {{Deep Modular Co-Attention Networks for Visual Question Answering}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2019},
}

@inproceedings{cvpr2019_ok_14586,
  title = {{OK-VQA: A Visual Question Answering Benchmark Requiring External Knowledge}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2019},
}

@inproceedings{cvpr2018_vizwiz_13714,
  title = {{VizWiz Grand Challenge: Answering Visual Questions From Blind People}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2018},
  url = {https://openaccess.thecvf.com/content_cvpr_2018/html/Gurari_VizWiz_Grand_Challenge_CVPR_2018_paper.html},
}

@inproceedings{cvpr2018_tips_13653,
  title = {{Tips and Tricks for Visual Question Answering: Learnings From the 2017 Challenge}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2018},
  url = {https://openaccess.thecvf.com/content_cvpr_2018/html/Teney_Tips_and_Tricks_CVPR_2018_paper.html},
}

@inproceedings{cvpr2020_counterfactual_15297,
  title = {{Counterfactual Samples Synthesizing for Robust Visual Question Answering}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2020},
}

@inproceedings{aaai2022_an_1735,
  title = {{An Empirical Study of GPT-3 for Few-Shot Knowledge-Based VQA}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2022},
  url = {https://aaai.org/papers/03081-an-empirical-study-of-gpt-3-for-few-shot-knowledge-based-vqa/},
}

@inproceedings{cvpr2018_dvqa_12946,
  title = {{DVQA: Understanding Data Visualizations via Question Answering}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2018},
  url = {https://openaccess.thecvf.com/content_cvpr_2018/html/Kafle_DVQA_Understanding_Data_CVPR_2018_paper.html},
}

@inproceedings{cvpr2023_prompting_21936,
  title = {{Prompting Large Language Models With Answer Heuristics for Knowledge-Based Visual Question Answering}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2023},
  url = {https://cvpr.thecvf.com/virtual/2023/poster/22417},
}

@inproceedings{cvpr2018_visual_13711,
  title = {{Visual Question Generation as Dual Task of Visual Question Answering}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2018},
  url = {https://openaccess.thecvf.com/content_cvpr_2018/html/Li_Visual_Question_Generation_CVPR_2018_paper.html},
}

@inproceedings{aaai2019_kvqa_103517,
  title = {{KVQA: Knowledge-Aware Visual Question Answering}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2019},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/4915},
}

@inproceedings{aaai2024_nuscenes_6800,
  title = {{NuScenes-QA: A Multi-Modal Visual Question Answering Benchmark for Autonomous Driving Scenario}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/28253},
}

@inproceedings{cvpr2016_answer_11400,
  title = {{Answer-Type Prediction for Visual Question Answering}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2016},
}

@inproceedings{neurips2019_self_58964,
  title = {{Self-Critical Reasoning for Robust Visual Question Answering}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2019},
  url = {https://nips.cc/virtual/2019/poster/14567},
}

@inproceedings{aaai2022_multi_2436,
  title = {{Multi-Modal Answer Validation for Knowledge-Based VQA}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2022},
  url = {https://aaai.org/papers/02712-multi-modal-answer-validation-for-knowledge-based-vqa/},
}

@inproceedings{cvpr2017_the_12697,
  title = {{The VQA-Machine: Learning How to Use Existing Vision Algorithms to Answer New Questions}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2017},
}

@inproceedings{cvpr2019_explicit_14166,
  title = {{Explicit Bias Discovery in Visual Question Answering Models}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2019},
}

@inproceedings{aaai2020_re_99737,
  title = {{Re-Attention for Visual Question Answering}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2020},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/5338},
}

@inproceedings{cvpr2022_transform_20090,
  title = {{Transform-Retrieve-Generate: Natural Language-Centric Outside-Knowledge Visual Question Answering}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2022},
}

@inproceedings{aaai2016_community_104729,
  title = {{Community-Based Question Answering via Heterogeneous Social Network Learning}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2016},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/9972},
}

@inproceedings{aaai2024_earthvqa_5790,
  title = {{EarthVQA: Towards Queryable Earth via Relational Reasoning-Based Remote Sensing Visual Question Answering}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/28357},
}

@inproceedings{aaai2024_bridging_5315,
  title = {{Bridging the Gap between 2D and 3D Visual Question Answering: A Fusion Approach for 3D VQA}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/28222},
}

@inproceedings{aaai2024_object_6810,
  title = {{Object Attribute Matters in Visual Question Answering}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/29816},
}

@inproceedings{aaai2024_towards_7609,
  title = {{Towards More Faithful Natural Language Explanation Using Multi-Level Contrastive Learning in VQA}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/28065},
}

@inproceedings{aaai2024_cross_5529,
  title = {{Cross-Modal Feature Distribution Calibration for Few-Shot Visual Question Answering}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/28543},
}

@inproceedings{aaai2025_vqa4cir_11221,
  title = {{VQA4CIR: Boosting Composed Image Retrieval with Visual Question Answering}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/32301},
}

@inproceedings{cvpr2025_notes_27086,
  title = {{Notes-guided MLLM Reasoning: Enhancing MLLM with Knowledge and Visual Notes for Visual Question Answering}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/33913},
}

@inproceedings{aaai2025_fine_9199,
  title = {{Fine-grained Adaptive Visual Prompt for Generative Medical Visual Question Answering}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/33047},
}

@inproceedings{cvpr2025_alignment_25470,
  title = {{Alignment, Mining and Fusion: Representation Alignment with Hard Negative Mining and Selective Knowledge Fusion for Medical Visual Question Answering}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/32389},
}

@inproceedings{neurips2025_knowledge_78662,
  title = {{Knowledge-based Visual Question Answer with Multimodal Processing, Retrieval and Filtering}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2025},
  url = {https://openreview.net/forum?id=h0LzGQq6uO},
}

@inproceedings{aaai2026_cross_108271,
  title = {{Cross-Granularity Hypergraph Retrieval-Augmented Generation for Multi-hop Question Answering}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2026},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/40623},
}

@inproceedings{aaai2025_core_8542,
  title = {{Core-to-Global Reasoning for Compositional Visual Question Answering}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/33170},
}

@inproceedings{neurips2024_cvqa_71163,
  title = {{CVQA: Culturally-diverse Multilingual Visual Question Answering Benchmark}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/97798},
}

@inproceedings{aaai2026_macvqa_108106,
  title = {{MacVQA: Adaptive Memory Allocation and Global Noise Filtering for Continual Visual Question Answering}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2026},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/40458},
}

@inproceedings{cvpr2025_frames_26222,
  title = {{FRAMES-VQA: Benchmarking Fine-Tuning Robustness across Multi-Modal Shifts in Visual Question Answering}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/33655},
}

@inproceedings{neurips2024_lova3_74350,
  title = {{LOVA3: Learning to Visual Question Answering, Asking and Assessment}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/93210},
}

@inproceedings{neurips2025_coralvqa_78795,
  title = {{CoralVQA: A Large-Scale Visual Question Answering Dataset for Coral Reef Image Understanding}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2025},
  url = {https://openreview.net/forum?id=iRsZHAMNHL},
}

@inproceedings{iclr2025_answer_80877,
  title = {{Answer, Assemble, Ace: Understanding How LMs Answer Multiple Choice Questions}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2025},
  url = {https://iclr.cc/virtual/2025/poster/30890},
}

@inproceedings{aaai2026_cmid_108483,
  title = {{CMID: Towards Medical Visual Question Answering via Contrastive Mutual Information Decoding}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2026},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/40835},
}