% Key papers for Unified any-modality language models (scime atlas, https://atlas.scime.ai). Authors are not included: add them from the paper pages.

@inproceedings{cvpr2024_cogagent_22988,
  title = {{CogAgent: A Visual Language Model for GUI Agents}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/30177},
}

@inproceedings{neurips2023_language_68316,
  title = {{Language Is Not All You Need: Aligning Perception with Language Models}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2023},
  url = {https://nips.cc/virtual/2023/poster/71488},
}

@inproceedings{cvpr2024_onellm_24362,
  title = {{OneLLM: One Framework to Align All Modalities with Language}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/31234},
}

@inproceedings{aaai2025_cobra_8440,
  title = {{Cobra: Extending Mamba to Multi-Modal Large Language Model for Efficient Inference}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/33131},
}

@inproceedings{aaai2025_harnessing_9411,
  title = {{Harnessing Multimodal Large Language Models for Multimodal Sequential Recommendation}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/33426},
}

@inproceedings{aaai2025_chemvlm_8414,
  title = {{ChemVLM: Exploring the Power of Multimodal Large Language Models in Chemistry Area}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/32020},
}

@inproceedings{cvpr2024_codi_22980,
  title = {{CoDi-2: In-Context Interleaved and Interactive Any-to-Any Generation}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/31512},
}

@inproceedings{cvpr2024_exploring_23417,
  title = {{Exploring the Transferability of Visual Prompting for Multimodal Large Language Models}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/31172},
}

@inproceedings{cvpr2024_omni_24329,
  title = {{Omni-SMoLA: Boosting Generalist Multimodal Models with Soft Mixture of Low-rank Experts}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/31830},
}

@inproceedings{iclr2024_dreamllm_35643,
  title = {{DreamLLM: Synergistic Multimodal Comprehension and Creation}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2024},
  url = {https://iclr.cc/virtual/2024/poster/17430},
}

@inproceedings{aaai2024_umie_7670,
  title = {{UMIE: Unified Multimodal Information Extraction with Instruction Tuning}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/29873},
}

@inproceedings{cvpr2025_doclayllm_25986,
  title = {{DocLayLLM: An Efficient Multi-modal Extension of Large Language Models for Text-rich Document Understanding}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/33575},
}

@inproceedings{cvpr2024_prompt_24528,
  title = {{Prompt Highlighter: Interactive Control for Multi-Modal LLMs}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/30785},
}

@inproceedings{cvpr2025_immune_26596,
  title = {{Immune: Improving Safety Against Jailbreaks in Multi-modal LLMs via Inference-Time Alignment}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/34085},
}

@inproceedings{neurips2024_single_72682,
  title = {{Single Image Unlearning: Efficient Machine Unlearning in Multimodal Large Language Models}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/94704},
}

@inproceedings{neurips2024_web2code_73368,
  title = {{Web2Code: A Large-scale Webpage-to-Code Dataset and Evaluation Framework for Multimodal LLMs}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/97572},
}

@inproceedings{cvpr2025_syntab_27783,
  title = {{SynTab-LLaVA: Enhancing Multimodal Table Understanding with Decoupled Synthesis}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/33173},
}

@inproceedings{cvpr2025_silmm_27523,
  title = {{SILMM: Self-Improving Large Multimodal Models for Compositional Text-to-Image Generation}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/33558},
}

@inproceedings{iclr2024_jointly_33659,
  title = {{Jointly Training Large Autoregressive Multimodal Models}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2024},
  url = {https://iclr.cc/virtual/2024/poster/19416},
}

@inproceedings{cvpr2025_rap_27350,
  title = {{RAP: Retrieval-Augmented Personalization for Multimodal Large Language Models}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/32822},
}

@inproceedings{icml2024_llark_44012,
  title = {{LLark: A Multimodal Instruction-Following Language Model for Music}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/34440},
}