% Key papers for Audio-visual speech separation (scime atlas, https://atlas.scime.ai). Authors are not included: add them from the paper pages.

@inproceedings{aaai2018_multi_105964,
  title = {{Multi-attention Recurrent Network for Human Communication Comprehension}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2018},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/12024},
}

@inproceedings{aaai2020_m3er_100573,
  title = {{M3ER: Multiplicative Multimodal Emotion Recognition using Facial, Textual, and Speech Cues}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2020},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/5492},
}

@inproceedings{cvpr2018_seeing_13569,
  title = {{Seeing Voices and Hearing Faces: Cross-Modal Biometric Matching}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2018},
  url = {https://openaccess.thecvf.com/content_cvpr_2018/html/Nagrani_Seeing_Voices_and_CVPR_2018_paper.html},
}

@inproceedings{cvpr2021_visualvoice_18132,
  title = {{VisualVoice: Audio-Visual Speech Separation With Cross-Modal Consistency}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2021},
}

@inproceedings{cvpr2022_learning_19185,
  title = {{Learning Hierarchical Cross-Modal Association for Co-Speech Gesture Generation}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2022},
}

@inproceedings{cvpr2022_expressive_18809,
  title = {{Expressive Talking Head Generation With Granular Audio-Visual Control}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2022},
}

@inproceedings{cvpr2016_temporal_11914,
  title = {{Temporal Multimodal Learning in Audiovisual Speech Recognition}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2016},
}

@inproceedings{cvpr2020_discriminative_15413,
  title = {{Discriminative Multi-Modality Speech Recognition}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2020},
}

@inproceedings{aaai2020_hearing_102312,
  title = {{Hearing Lips: Improving Lip Reading by Distilling Speech Recognizers}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2020},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/6174},
}

@inproceedings{aaai2018_cmcgan_104070,
  title = {{CMCGAN: A Uniform Framework for Cross-Modal Visual-Audio Mutual Generation}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2018},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/12329},
}

@inproceedings{aaai2016_look_105418,
  title = {{Look, Listen and Learn — A Multimodal LSTM for Speaker Identification}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2016},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/10471},
}

@inproceedings{cvpr2021_learning_17278,
  title = {{Learning From the Master: Distilling Cross-Modal Advanced Knowledge for Lip Reading}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2021},
}

@inproceedings{aaai2022_distinguishing_1990,
  title = {{Distinguishing Homophenes Using Multi-Head Visual-Audio Memory for Lip Reading}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2022},
  url = {https://aaai.org/papers/01174-distinguishing-homophenes-using-multi-head-visual-audio-memory-for-lip-reading/},
}

@inproceedings{cvpr2021_vx2text_18136,
  title = {{Vx2Text: End-to-End Learning of Video-Based Text Generation From Multimodal Inputs}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2021},
}

@inproceedings{aaai2025_enriching_8996,
  title = {{Enriching Multimodal Sentiment Analysis Through Textual Emotional Descriptions of Visual-Audio Content}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/32152},
}

@inproceedings{cvpr2022_sound_19902,
  title = {{Sound-Guided Semantic Image Manipulation}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2022},
}

@inproceedings{iclr2021_parameter_30016,
  title = {{Parameter Efficient Multimodal Transformers for Video Representation Learning}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2021},
  url = {https://iclr.cc/virtual/2021/poster/2901},
}

@inproceedings{aaai2018_integrating_104071,
  title = {{Integrating Both Visual and Audio Cues for Enhanced Video Caption}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2018},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/12330},
}

@inproceedings{aaai2024_v2a_7737,
  title = {{V2A-Mapper: A Lightweight Solution for Vision-to-Audio Generation by Connecting Foundation Models}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/29475},
}

@inproceedings{cvpr2022_audio_18310,
  title = {{Audio-Visual Speech Codecs: Rethinking Audio-Visual Speech Enhancement by Re-Synthesis}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2022},
}

@inproceedings{cvpr2024_emoportraits_23310,
  title = {{EMOPortraits: Emotion-enhanced Multimodal One-shot Head Avatars}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/31267},
}

@inproceedings{aaai2025_megactor_9933,
  title = {{MegActor-Sigma: Unlocking Flexible Mixed-Modal Control in Portrait Animation with Diffusion Transformer}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/33002},
}

@inproceedings{aaai2025_multi_10050,
  title = {{Multi-modal Deepfake Detection via Multi-task Audio-Visual Prompt Learning}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/32042},
}

@inproceedings{cvpr2025_hop_26473,
  title = {{HOP: Heterogeneous Topology-based Multimodal Entanglement for Co-Speech Gesture Generation}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/33675},
}

@inproceedings{aaai2025_mental_9939,
  title = {{Mental-Perceiver: Audio-Textual Multi-Modal Learning for Estimating Mental Disorders}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/34687},
}

@inproceedings{neurips2024_towards_74363,
  title = {{Towards Open Respiratory Acoustic Foundation Models: Pretraining and Benchmarking}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/97457},
}

@inproceedings{neurips2025_vita_78456,
  title = {{VITA-Audio: Fast Interleaved Audio-Text Token Generation for Efficient Large Speech-Language Model}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2025},
  url = {https://openreview.net/forum?id=epZTfZF7JC},
}

@inproceedings{iclr2026_wave_86164,
  title = {{WAVE: Learning Unified \& Versatile Audio-Visual Embeddings with Multimodal LLM}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2026},
  url = {https://openreview.net/forum?id=MiV3WXDYJb},
}

@inproceedings{aaai2026_omnidpo_106797,
  title = {{OmniDPO: A Preference Optimization Framework to Address Omni-Modal Hallucination}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2026},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/39104},
}

@inproceedings{aaai2024_independency_6316,
  title = {{Independency Adversarial Learning for Cross-Modal Sound Separation}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/28140},
}

@inproceedings{iclr2024_rtfs_34359,
  title = {{RTFS-Net: Recurrent Time-Frequency Modelling for Efficient Audio-Visual Speech Separation}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2024},
  url = {https://iclr.cc/virtual/2024/poster/18716},
}

@inproceedings{neurips2025_avcd_75074,
  title = {{AVCD: Mitigating Hallucinations in Audio-Visual Large Language Models through Contrastive Decoding}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2025},
  url = {https://openreview.net/forum?id=3zx087XPtz},
}

@inproceedings{neurips2025_the_76148,
  title = {{The Curse of Multi-Modalities: Evaluating Hallucinations of Large Multimodal Models across Language, Visual, and Audio}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2025},
  url = {https://openreview.net/forum?id=G4AZhSEcrV},
}

@inproceedings{icml2024_iianet_43911,
  title = {{IIANet: An Intra- and Inter-Modality Attention Network for Audio-Visual Speech Separation}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/34541},
}

@inproceedings{icml2025_flam_46250,
  title = {{FLAM: Frame-Wise Language-Audio Modeling}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2025},
  url = {https://icml.cc/virtual/2025/poster/46310},
}

@inproceedings{icml2026_lalm_49449,
  title = {{LALM-as-a-Judge: Benchmarking Large Audio-Language Models for Safety Evaluation in Multi-Turn Spoken Dialogues}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2026},
  url = {https://openreview.net/forum?id=2ftHZlIUKE},
}

@inproceedings{icml2026_acoustic_50812,
  title = {{Acoustic Interference: A New Paradigm Weaponizing Acoustic Latent Semantic for Universal Jailbreak against Large Audio Language Models}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2026},
  url = {https://openreview.net/forum?id=FygaF16KNo},
}

@inproceedings{icml2026_sam_51805,
  title = {{SAM Audio: Segment Anything in Audio}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2026},
  url = {https://openreview.net/forum?id=Q4Cca8N7na},
}