% Key papers for Attention and prior-robust VQA (scime atlas, https://atlas.scime.ai). Authors are not included: add them from the paper pages.

@inproceedings{cvpr2017_making_12449,
  title = {{Making the v in VQA Matter: Elevating the Role of Image Understanding in Visual Question Answering}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2017},
}

@inproceedings{neurips2016_hierarchical_55769,
  title = {{Hierarchical Question-Image Co-Attention for Visual Question Answering}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2016},
  url = {https://nips.cc/virtual/2016/poster/7040},
}

@inproceedings{cvpr2016_neural_11727,
  title = {{Neural Module Networks}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2016},
}

@inproceedings{cvpr2018_don_13038,
  title = {{Don't Just Assume; Look and Answer: Overcoming Priors for 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/Agrawal_Dont_Just_Assume_CVPR_2018_paper.html},
}

@inproceedings{cvpr2016_where_11983,
  title = {{Where to Look: Focus Regions for Visual Question Answering}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2016},
}

@inproceedings{cvpr2017_graph_12317,
  title = {{Graph-Structured Representations for Visual Question Answering}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2017},
}

@inproceedings{aaai2018_scitail_105962,
  title = {{SciTaiL: A Textual Entailment Dataset from Science Question Answering}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2018},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/12022},
}

@inproceedings{cvpr2019_dynamic_14119,
  title = {{Dynamic Fusion With Intra- and Inter-Modality Attention Flow for Visual Question Answering}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2019},
}

@inproceedings{cvpr2018_improved_13214,
  title = {{Improved Fusion of Visual and Language Representations by Dense Symmetric Co-Attention for 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/Nguyen_Improved_Fusion_of_CVPR_2018_paper.html},
}

@inproceedings{cvpr2016_ask_11403,
  title = {{Ask Me Anything: Free-Form Visual Question Answering Based on Knowledge From External Sources}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2016},
}

@inproceedings{cvpr2020_in_15684,
  title = {{In Defense of Grid Features for Visual Question Answering}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2020},
}

@inproceedings{neurips2018_neural_57436,
  title = {{Neural-Symbolic VQA: Disentangling Reasoning from Vision and Language Understanding}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2018},
  url = {https://nips.cc/virtual/2018/poster/11123},
}

@inproceedings{cvpr2019_murel_14496,
  title = {{MUREL: Multimodal Relational Reasoning for Visual Question Answering}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2019},
}

@inproceedings{aaai2019_beyond_103490,
  title = {{Beyond RNNs: Positional Self-Attention with Co-Attention for Video Question Answering}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2019},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/4887},
}

@inproceedings{aaai2016_learning_105389,
  title = {{Learning to Answer Questions from Image Using Convolutional Neural Network}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2016},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/10442},
}

@inproceedings{cvpr2017_multi_12467,
  title = {{Multi-Level Attention Networks for Visual Question Answering}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2017},
}

@inproceedings{iclr2018_learning_28394,
  title = {{Learning to Count Objects in Natural Images for Visual Question Answering}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2018},
  url = {https://iclr.cc/virtual/2018/poster/307},
}

@inproceedings{cvpr2019_cycle_13993,
  title = {{Cycle-Consistency for Robust Visual Question Answering}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2019},
}

@inproceedings{cvpr2020_towards_16354,
  title = {{Towards Causal VQA: Revealing and Reducing Spurious Correlations by Invariant and Covariant Semantic Editing}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2020},
}

@inproceedings{neurips2018_learning_57279,
  title = {{Learning Conditioned Graph Structures for Interpretable Visual Question Answering}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2018},
  url = {https://nips.cc/virtual/2018/poster/11797},
}

@inproceedings{cvpr2024_gram_23560,
  title = {{GRAM: Global Reasoning for Multi-Page VQA}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/30457},
}

@inproceedings{aaai2025_retrieval_10545,
  title = {{Retrieval-Augmented Visual Question Answering via Built-in Autoregressive Search Engines}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/34653},
}

@inproceedings{aaai2024_vqattack_7749,
  title = {{VQAttack: Transferable Adversarial Attacks on Visual Question Answering via Pre-trained Models}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/28499},
}

@inproceedings{cvpr2025_marten_26924,
  title = {{Marten: Visual Question Answering with Mask Generation for Multi-modal Document Understanding}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/33267},
}

@inproceedings{aaai2024_bok_5259,
  title = {{BOK-VQA: Bilingual outside Knowledge-Based Visual Question Answering via Graph Representation Pretraining}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/29798},
}

@inproceedings{cvpr2025_avqacl_25416,
  title = {{AVQACL: A Novel Benchmark for Audio-Visual Question Answering Continual Learning}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/35098},
}

@inproceedings{cvpr2025_separation_27642,
  title = {{Separation of Powers: On Segregating Knowledge from Observation in LLM-enabled Knowledge-based Visual Question Answering}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/33258},
}

@inproceedings{iclr2024_open_33973,
  title = {{Open-ended VQA benchmarking of Vision-Language models by exploiting Classification datasets and their semantic hierarchy}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2024},
  url = {https://iclr.cc/virtual/2024/poster/19102},
}

@inproceedings{neurips2024_spatialpin_72689,
  title = {{SpatialPIN: Enhancing Spatial Reasoning Capabilities of Vision-Language Models through Prompting and Interacting 3D Priors}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/94696},
}

@inproceedings{aaai2026_roadscenevqa_100694,
  title = {{RoadSceneVQA: Benchmarking Visual Question Answering in Roadside Perception Systems for Intelligent Transportation System}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2026},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/42434},
}

@inproceedings{aaai2024_bidirectional_5296,
  title = {{Bidirectional Contrastive Split Learning for Visual Question Answering}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/30158},
}

@inproceedings{aaai2025_glen_9281,
  title = {{GLEN: Generalized Focal Loss Ensemble of Low-Rank Networks for Calibrated Visual Question Answering}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/34154},
}

@inproceedings{aaai2025_multimodal_10065,
  title = {{Multimodal Commonsense Knowledge Distillation for Visual Question Answering (Student Abstract)}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/35320},
}

@inproceedings{iclr2025_exploring_81300,
  title = {{Exploring the Effectiveness of Object-Centric Representations in Visual Question Answering: Comparative Insights with Foundation Models}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2025},
  url = {https://iclr.cc/virtual/2025/poster/30471},
}

@inproceedings{aaai2024_skillclip_7353,
  title = {{SkillCLIP: Skill Aware Modality Fusion Visual Question Answering (Student Abstract)}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/30486},
}

@inproceedings{icml2025_re_46551,
  title = {{Re-ranking Reasoning Context with Tree Search Makes Large Vision-Language Models Stronger}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2025},
  url = {https://icml.cc/virtual/2025/poster/46017},
}

@inproceedings{icml2026_real_53408,
  title = {{REAL: Resolving Knowledge Conflicts in Knowledge-Intensive Visual Question Answering via Reasoning-Pivot Alignment}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2026},
  url = {https://openreview.net/forum?id=fDlpwEHT4z},
}

@inproceedings{neurips2025_language_79623,
  title = {{Language‑Bias‑Resilient Visual Question Answering via Adaptive Multi‑Margin Collaborative Debiasing}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2025},
  url = {https://openreview.net/forum?id=rIwUDnRGky},
}

@inproceedings{cvpr2026_sea_97074,
  title = {{SEA: Evaluating Sketch Abstraction Efficiency via Element-level Commonsense Visual Question Answering}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2026},
  url = {https://openaccess.thecvf.com/content/CVPR2026/html/Park_SEA_Evaluating_Sketch_Abstraction_Efficiency_via_Element-level_Commonsense_Visual_Question_CVPR_2026_paper.html},
}

@inproceedings{cvpr2026_m4_97421,
  title = {{M4-RAG: A Massive-Scale Multilingual Multi-Cultural Multimodal RAG}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2026},
  url = {https://openaccess.thecvf.com/content/CVPR2026/html/Anugraha_M4-RAG_A_Massive-Scale_Multilingual_Multi-Cultural_Multimodal_RAG_CVPR_2026_paper.html},
}