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

@inproceedings{aaai2018_film_102404,
  title = {{FiLM: Visual Reasoning with a General Conditioning Layer}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2018},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/11671},
}

@inproceedings{cvpr2017_clevr_12099,
  title = {{CLEVR: A Diagnostic Dataset for Compositional Language and Elementary Visual Reasoning}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2017},
}

@inproceedings{neurips2022_flamingo_64364,
  title = {{Flamingo: a Visual Language Model for Few-Shot Learning}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2022},
  url = {https://nips.cc/virtual/2022/poster/54165},
}

@inproceedings{cvpr2019_from_14224,
  title = {{From Recognition to Cognition: Visual Commonsense Reasoning}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2019},
}

@inproceedings{cvpr2017_visual_12743,
  title = {{Visual Dialog}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2017},
}

@inproceedings{cvpr2020_12_15046,
  title = {{12-in-1: Multi-Task Vision and Language Representation Learning}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2020},
}

@inproceedings{cvpr2017_guesswhat_12321,
  title = {{GuessWhat?! Visual Object Discovery Through Multi-Modal Dialogue}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2017},
}

@inproceedings{cvpr2018_transparency_13669,
  title = {{Transparency by Design: Closing the Gap Between Performance and Interpretability in Visual Reasoning}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2018},
  url = {https://openaccess.thecvf.com/content_cvpr_2018/html/Mascharka_Transparency_by_Design_CVPR_2018_paper.html},
}

@inproceedings{cvpr2023_visual_22541,
  title = {{Visual Programming: Compositional Visual Reasoning Without Training}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2023},
  url = {https://cvpr.thecvf.com/virtual/2023/poster/22652},
}

@inproceedings{icml2021_unifying_40084,
  title = {{Unifying Vision-and-Language Tasks via Text Generation}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2021},
  url = {https://icml.cc/virtual/2021/poster/9961},
}

@inproceedings{cvpr2019_raven_14690,
  title = {{RAVEN: A Dataset for Relational and Analogical Visual REasoNing}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2019},
}

@inproceedings{cvpr2024_generative_23612,
  title = {{Generative Multimodal Models are In-Context Learners}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/29520},
}

@inproceedings{cvpr2018_two_13673,
  title = {{Two Can Play This Game: Visual Dialog With Discriminative Question Generation and Answering}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2018},
  url = {https://openaccess.thecvf.com/content_cvpr_2018/html/Jain_Two_Can_Play_CVPR_2018_paper.html},
}

@inproceedings{aaai2021_visualmrc_1621,
  title = {{VisualMRC: Machine Reading Comprehension on Document Images}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2021},
  url = {https://aaai.org/papers/13878-visualmrc-machine-reading-comprehension-on-document-images/},
}

@inproceedings{cvpr2024_on_24340,
  title = {{On Scaling Up a Multilingual Vision and Language Model}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/31319},
}

@inproceedings{cvpr2018_flipdial_13123,
  title = {{FlipDial: A Generative Model for Two-Way Visual Dialogue}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2018},
  url = {https://openaccess.thecvf.com/content_cvpr_2018/html/Massiceti_FlipDial_A_Generative_CVPR_2018_paper.html},
}

@inproceedings{aaai2021_a_7,
  title = {{A Case Study of the Shortcut Effects in Visual Commonsense Reasoning}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2021},
  url = {https://aaai.org/papers/03181-a-case-study-of-the-shortcut-effects-in-visual-commonsense-reasoning/},
}

@inproceedings{cvpr2020_attention_15159,
  title = {{Attention-Based Context Aware Reasoning for Situation Recognition}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2020},
}

@inproceedings{cvpr2023_are_20402,
  title = {{Are Deep Neural Networks SMARTer Than Second Graders?}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2023},
  url = {https://cvpr.thecvf.com/virtual/2023/poster/21997},
}

@inproceedings{cvpr2024_egothink_23349,
  title = {{EgoThink: Evaluating First-Person Perspective Thinking Capability of Vision-Language Models}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/30136},
}

@inproceedings{cvpr2024_situational_24831,
  title = {{Situational Awareness Matters in 3D Vision Language Reasoning}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/30234},
}

@inproceedings{iclr2024_the_34762,
  title = {{The All-Seeing Project: Towards Panoptic Visual Recognition and Understanding of the Open World}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2024},
  url = {https://iclr.cc/virtual/2024/poster/18312},
}

@inproceedings{aaai2025_evaluating_9017,
  title = {{Evaluating Image Hallucination in Text-to-Image Generation with Question-Answering}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/34827},
}

@inproceedings{cvpr2024_self_24789,
  title = {{Self-Training Large Language Models for Improved Visual Program Synthesis With Visual Reinforcement}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/29639},
}

@inproceedings{icml2024_unifying_44215,
  title = {{Unifying Image Processing as Visual Prompting Question Answering}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/34237},
}

@inproceedings{aaai2024_image_6270,
  title = {{Image Content Generation with Causal Reasoning}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/29269},
}

@inproceedings{aaai2024_detection_5678,
  title = {{Detection-Based Intermediate Supervision for Visual Question Answering}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/29315},
}

@inproceedings{icml2024_fool_44025,
  title = {{Fool Your (Vision and) Language Model with Embarrassingly Simple Permutations}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/34427},
}

@inproceedings{iclr2025_teochat_83527,
  title = {{TEOChat: A Large Vision-Language Assistant for Temporal Earth Observation Data}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2025},
  url = {https://iclr.cc/virtual/2025/poster/28289},
}

@inproceedings{cvpr2025_document_25990,
  title = {{Document Haystacks:  Vision-Language Reasoning Over Piles of 1000+ Documents}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/33281},
}

@inproceedings{iclr2024_vdc_35664,
  title = {{VDC: Versatile Data Cleanser based on Visual-Linguistic Inconsistency by Multimodal Large Language Models}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2024},
  url = {https://iclr.cc/virtual/2024/poster/17409},
}

@inproceedings{neurips2024_vlm4bio_72441,
  title = {{VLM4Bio: A Benchmark Dataset to Evaluate Pretrained Vision-Language Models for Trait Discovery from Biological Images}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/97668},
}

@inproceedings{neurips2024_learning_74312,
  title = {{Learning to Reason Iteratively and Parallelly for Complex Visual Reasoning Scenarios}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/93246},
}

@inproceedings{cvpr2025_viunit_28070,
  title = {{ViUniT: Visual Unit Tests for More Robust Visual Programming}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/34922},
}

@inproceedings{neurips2024_t2vs_70138,
  title = {{T2Vs Meet VLMs: A Scalable Multimodal Dataset for Visual Harmfulness Recognition}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/97879},
}

@inproceedings{neurips2025_indego_78884,
  title = {{IndEgo: A Dataset of Industrial Scenarios and Collaborative Work for Egocentric Assistants}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2025},
  url = {https://openreview.net/forum?id=jKw3Qhc8m1},
}

@inproceedings{aaai2026_imageset2text_104299,
  title = {{ImageSet2Text: Describing Sets of Images Through Text}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2026},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/37826},
}