% Key papers for Multimodal retrieval-augmented modeling (scime atlas, https://atlas.scime.ai). Authors are not included: add them from the paper pages.

@inproceedings{aaai2018_adaptive_105902,
  title = {{Adaptive Co-attention Network for Named Entity Recognition in Tweets}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2018},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/11962},
}

@inproceedings{aaai2019_multi_99714,
  title = {{Multi-Interactive Memory Network for Aspect Based Multimodal Sentiment Analysis}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2019},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/3807},
}

@inproceedings{aaai2016_senticap_105422,
  title = {{SentiCap: Generating Image Descriptions with Sentiments}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2016},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/10475},
}

@inproceedings{aaai2021_multi_1028,
  title = {{Multi-modal Graph Fusion for Named Entity Recognition with Targeted Visual Guidance}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2021},
  url = {https://aaai.org/papers/14347-multi-modal-graph-fusion-for-named-entity-recognition-with-targeted-visual-guidance/},
}

@inproceedings{aaai2021_rpbert_1299,
  title = {{RpBERT: A Text-image Relation Propagation-based BERT Model for Multimodal NER}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2021},
  url = {https://aaai.org/papers/13860-rpbert-a-text-image-relation-propagation-based-bert-model-for-multimodal-ner/},
}

@inproceedings{cvpr2022_open_19517,
  title = {{Open-Domain, Content-Based, Multi-Modal Fact-Checking of Out-of-Context Images via Online Resources}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2022},
}

@inproceedings{aaai2021_humor_734,
  title = {{Humor Knowledge Enriched Transformer for Understanding Multimodal Humor}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2021},
  url = {https://aaai.org/papers/12972-humor-knowledge-enriched-transformer-for-understanding-multimodal-humor/},
}

@inproceedings{cvpr2024_ufinebench_25103,
  title = {{UFineBench: Towards Text-based Person Retrieval with Ultra-fine Granularity}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/31143},
}

@inproceedings{aaai2020_aspect_103022,
  title = {{Aspect-Aware Multimodal Summarization for Chinese E-Commerce Products}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2020},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/6332},
}

@inproceedings{aaai2024_reinforced_7098,
  title = {{Reinforced Adaptive Knowledge Learning for Multimodal Fake News Detection}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/29618},
}

@inproceedings{aaai2021_let_845,
  title = {{LET: Linguistic Knowledge Enhanced Graph Transformer for Chinese Short Text Matching}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2021},
  url = {https://aaai.org/papers/13498-let-linguistic-knowledge-enhanced-graph-transformer-for-chinese-short-text-matching/},
}

@inproceedings{iclr2017_words_28208,
  title = {{Words or Characters? Fine-grained Gating for Reading Comprehension}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2017},
  url = {https://openreview.net/forum?id=B1hdzd5lg},
}

@inproceedings{aaai2024_multi_6702,
  title = {{Multi-Prompts Learning with Cross-Modal Alignment for Attribute-Based Person Re-identification}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/28524},
}

@inproceedings{cvpr2024_linguistic_24012,
  title = {{Linguistic-Aware Patch Slimming Framework for Fine-grained Cross-Modal Alignment}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/30209},
}

@inproceedings{aaai2020_image_103127,
  title = {{Image Enhanced Event Detection in News Articles}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2020},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/6437},
}

@inproceedings{aaai2023_bert_3152,
  title = {{BERT-ERC: Fine-Tuning BERT Is Enough for Emotion Recognition in Conversation}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2023},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/26582},
}

@inproceedings{aaai2018_knowledge_105889,
  title = {{Knowledge Enhanced Hybrid Neural Network for Text Matching}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2018},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/11949},
}

@inproceedings{icml2023_retrieval_42400,
  title = {{Retrieval-Augmented Multimodal Language Modeling}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2023},
  url = {https://icml.cc/virtual/2023/poster/25248},
}

@inproceedings{aaai2021_read_1240,
  title = {{Read, Retrospect, Select: An MRC Framework to Short Text Entity Linking}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2021},
  url = {https://aaai.org/papers/12920-read-retrospect-select-an-mrc-framework-to-short-text-entity-linking/},
}

@inproceedings{aaai2022_nice_2470,
  title = {{Nice Perfume. How Long Did You Marinate in It? Multimodal Sarcasm Explanation}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2022},
  url = {https://aaai.org/papers/10563-nice-perfume-how-long-did-you-marinate-in-it-multimodal-sarcasm-explanation/},
}

@inproceedings{aaai2024_generative_6132,
  title = {{Generative Multi-Modal Knowledge Retrieval with Large Language Models}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/29837},
}

@inproceedings{cvpr2025_human_26535,
  title = {{Human-centered Interactive Learning via MLLMs for Text-to-Image Person Re-identification}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/34768},
}

@inproceedings{cvpr2025_mm_26869,
  title = {{MM-OR: A Large Multimodal Operating Room Dataset for Semantic Understanding of High-Intensity Surgical Environments}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/32596},
}

@inproceedings{aaai2024_multi_6696,
  title = {{Multi-Modal Discussion Transformer: Integrating Text, Images and Graph Transformers to Detect Hate Speech on Social Media}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/30213},
}

@inproceedings{neurips2024_xrag_70623,
  title = {{xRAG: Extreme Context Compression for Retrieval-augmented Generation with One Token}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/96497},
}

@inproceedings{aaai2024_towards_7610,
  title = {{Towards Multi-Intent Spoken Language Understanding via Hierarchical Attention and Optimal Transport}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/29738},
}

@inproceedings{aaai2024_camel_5325,
  title = {{CAMEL: Capturing Metaphorical Alignment with Context Disentangling for Multimodal Emotion Recognition}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/28787},
}

@inproceedings{aaai2025_improving_9535,
  title = {{Improving Multimodal Social Media Popularity Prediction via Selective Retrieval Knowledge Augmentation}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/32078},
}

@inproceedings{cvpr2025_mmtl_26873,
  title = {{MMTL-UniAD: A Unified Framework for Multimodal and Multi-Task Learning in Assistive Driving Perception}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/34653},
}

@inproceedings{cvpr2025_modeling_26985,
  title = {{Modeling Thousands of Human Annotators for Generalizable Text-to-Image Person Re-identification}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/32928},
}

@inproceedings{aaai2024_mitigating_6646,
  title = {{Mitigating Idiom Inconsistency: A Multi-Semantic Contrastive Learning Method for Chinese Idiom Reading Comprehension}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/29893},
}

@inproceedings{aaai2025_multi_10011,
  title = {{Multi-Grained Query-Guided Set Prediction Network for Grounded Multimodal Named Entity Recognition}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/34711},
}

@inproceedings{aaai2025_excluir_9044,
  title = {{ExcluIR: Exclusionary Neural Information Retrieval}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/33451},
}

@inproceedings{aaai2025_aspect_8146,
  title = {{Aspect Enhancement and Text Simplification in Multimodal Aspect-Based Sentiment Analysis for Multi-Aspect and Multi-Sentiment Scenarios}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/32161},
}

@inproceedings{aaai2024_composite_5447,
  title = {{Composite Sketch+Text Queries for Retrieving Objects with Elusive Names and Complex Interactions}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/27956},
}

@inproceedings{neurips2024_multimodal_72503,
  title = {{Multimodal Task Vectors Enable Many-Shot Multimodal In-Context Learning}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/94861},
}