% Key papers for Vision-language model VQA evaluation (scime atlas, https://atlas.scime.ai). Authors are not included: add them from the paper pages.

@inproceedings{neurips2019_vilbert_59185,
  title = {{ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Tasks}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2019},
  url = {https://nips.cc/virtual/2019/poster/13250},
}

@inproceedings{cvpr2016_what_11979,
  title = {{What Value Do Explicit High Level Concepts Have in Vision to Language Problems?}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2016},
}

@inproceedings{cvpr2021_counterfactual_16760,
  title = {{Counterfactual VQA: A Cause-Effect Look at Language Bias}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2021},
}

@inproceedings{neurips2017_modulating_56482,
  title = {{Modulating early visual processing by language}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2017},
  url = {https://nips.cc/virtual/2017/poster/9428},
}

@inproceedings{cvpr2016_yin_11984,
  title = {{Yin and Yang: Balancing and Answering Binary Visual Questions}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2016},
}

@inproceedings{neurips2020_large_60140,
  title = {{Large-Scale Adversarial Training for Vision-and-Language Representation Learning}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2020},
  url = {https://nips.cc/virtual/2020/poster/17984},
}

@inproceedings{cvpr2023_from_21025,
  title = {{From Images to Textual Prompts: Zero-Shot Visual Question Answering With Frozen Large Language Models}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2023},
  url = {https://cvpr.thecvf.com/virtual/2023/poster/20999},
}

@inproceedings{cvpr2020_counterfactual_15298,
  title = {{Counterfactual Vision and Language Learning}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2020},
}

@inproceedings{aaai2020_federated_103717,
  title = {{Federated Learning for Vision-and-Language Grounding Problems}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2020},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/6824},
}

@inproceedings{aaai2021_knowledge_842,
  title = {{Knowledge-driven Data Construction for Zero-shot Evaluation in Commonsense Question Answering}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2021},
  url = {https://aaai.org/papers/13507-knowledge-driven-data-construction-for-zero-shot-evaluation-in-commonsense-question-answering/},
}

@inproceedings{cvpr2020_assessing_15152,
  title = {{Assessing Image Quality Issues for Real-World Problems}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2020},
}

@inproceedings{cvpr2021_predicting_17643,
  title = {{Predicting Human Scanpaths in Visual Question Answering}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2021},
}

@inproceedings{cvpr2019_multi_14549,
  title = {{Multi-Task Learning of Hierarchical Vision-Language Representation}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2019},
}

@inproceedings{aaai2022_playing_2557,
  title = {{Playing Lottery Tickets with Vision and Language}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2022},
  url = {https://aaai.org/papers/00652-playing-lottery-tickets-with-vision-and-language/},
}

@inproceedings{aaai2025_vhm_11215,
  title = {{VHM: Versatile and Honest Vision Language Model for Remote Sensing Image Analysis}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/32683},
}

@inproceedings{aaai2020_dmrm_102938,
  title = {{DMRM: A Dual-Channel Multi-Hop Reasoning Model for Visual Dialog}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2020},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/6248},
}

@inproceedings{neurips2020_removing_60700,
  title = {{Removing Bias in Multi-modal Classifiers: Regularization by Maximizing Functional Entropies}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2020},
  url = {https://nips.cc/virtual/2020/poster/18723},
}

@inproceedings{cvpr2023_mixphm_21572,
  title = {{MixPHM: Redundancy-Aware Parameter-Efficient Tuning for Low-Resource Visual Question Answering}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2023},
  url = {https://cvpr.thecvf.com/virtual/2023/poster/21937},
}

@inproceedings{cvpr2024_consistency_23016,
  title = {{Consistency and Uncertainty: Identifying Unreliable Responses From Black-Box Vision-Language Models for Selective Visual Question Answering}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/30163},
}

@inproceedings{neurips2021_scallop_63132,
  title = {{Scallop: From Probabilistic Deductive Databases to Scalable Differentiable Reasoning}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2021},
  url = {https://nips.cc/virtual/2021/poster/28073},
}

@inproceedings{cvpr2024_how_23717,
  title = {{How to Configure Good In-Context Sequence for Visual Question Answering}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/29319},
}

@inproceedings{aaai2024_exploiting_5910,
  title = {{Exploiting the Social-Like Prior in Transformer for Visual Reasoning}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/27977},
}

@inproceedings{cvpr2025_embodied_26115,
  title = {{Embodied Scene Understanding for Vision Language Models via MetaVQA}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/33852},
}

@inproceedings{cvpr2025_automated_25539,
  title = {{Automated Generation of Challenging Multiple-Choice Questions for Vision Language Model Evaluation}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/34956},
}

@inproceedings{aaai2026_stride_101140,
  title = {{STRIDE-QA: Visual Question Answering Dataset for Spatiotemporal Reasoning in Urban Driving Scenes}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2026},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/37441},
}

@inproceedings{aaai2024_tackling_7488,
  title = {{Tackling Vision Language Tasks through Learning Inner Monologues}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/29905},
}

@inproceedings{neurips2024_naturalbench_71159,
  title = {{NaturalBench: Evaluating Vision-Language Models on Natural Adversarial Samples}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/97799},
}

@inproceedings{neurips2024_a_73002,
  title = {{A Hitchhiker's Guide to Fine-Grained Face Forgery Detection Using Common Sense Reasoning}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/97603},
}

@inproceedings{aaai2025_defeasible_8685,
  title = {{Defeasible Visual Entailment: Benchmark, Evaluator, and Reward-Driven Optimization}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/34792},
}

@inproceedings{aaai2024_vision_7773,
  title = {{Vision-Language Models for Robot Success Detection}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/30552},
}

@inproceedings{neurips2025_robo2vlm_76892,
  title = {{Robo2VLM: Improving Visual Question Answering using Large-Scale Robot Manipulation Data}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2025},
  url = {https://openreview.net/forum?id=OChorZcZnY},
}

@inproceedings{iclr2024_rephrase_34201,
  title = {{Rephrase, Augment, Reason: Visual Grounding of Questions for Vision-Language Models}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2024},
  url = {https://iclr.cc/virtual/2024/poster/18874},
}

@inproceedings{neurips2025_vision_76550,
  title = {{Vision-and-Language Training Helps Deploy Taxonomic Knowledge but Does Not Fundamentally Alter It}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2025},
  url = {https://openreview.net/forum?id=KXmDTGKwhy},
}

@inproceedings{iclr2025_breaking_80820,
  title = {{Breaking Neural Network Scaling Laws with Modularity}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2025},
  url = {https://iclr.cc/virtual/2025/poster/30948},
}

@inproceedings{cvpr2026_act_95835,
  title = {{Act Like a Pathologist: Tissue-Aware Whole Slide Image Reasoning}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2026},
  url = {https://openaccess.thecvf.com/content/CVPR2026/html/Huang_Act_Like_a_Pathologist_Tissue-Aware_Whole_Slide_Image_Reasoning_CVPR_2026_paper.html},
}

@inproceedings{aaai2025_cross_8561,
  title = {{Cross-Lingual Text-Rich Visual Comprehension: An Information Theory Perspective}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/33049},
}

@inproceedings{aaai2025_mind_9953,
  title = {{Mind the Uncertainty in Human Disagreement: Evaluating Discrepancies Between Model Predictions and Human Responses in VQA}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/32468},
}

@inproceedings{icml2026_cbv_52247,
  title = {{CBV: Clean-label Backdoor Attacks on Vision Language Models via Diffusion Models}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2026},
  url = {https://openreview.net/forum?id=U1YNfdXkVD},
}