% Key papers for Training-free token reduction for MLLMs (scime atlas, https://atlas.scime.ai). Authors are not included: add them from the paper pages.

@inproceedings{cvpr2025_divprune_25974,
  title = {{DivPrune: Diversity-based Visual Token Pruning for Large Multimodal Models}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/34849},
}

@inproceedings{aaai2025_boosting_8282,
  title = {{Boosting Multimodal Large Language Models with Visual Tokens Withdrawal for Rapid Inference}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/32567},
}

@inproceedings{aaai2025_fit_9203,
  title = {{Fit and Prune: Fast and Training-free Visual Token Pruning for Multi-modal Large Language Models}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/34366},
}

@inproceedings{aaai2025_enhancing_8978,
  title = {{Enhancing Multimodal Large Language Models Complex Reason via Similarity Computation}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/33107},
}

@inproceedings{cvpr2025_reasoning_27403,
  title = {{Reasoning to Attend: Try to Understand How <SEG> Token Works}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/32873},
}

@inproceedings{aaai2025_dockylin_8789,
  title = {{DocKylin: A Large Multimodal Model for Visual Document Understanding with Efficient Visual Slimming}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/33076},
}

@inproceedings{neurips2024_efficient_70556,
  title = {{Efficient Large Multi-modal Models via Visual Context Compression}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/96558},
}

@inproceedings{neurips2024_controlmllm_71712,
  title = {{ControlMLLM: Training-Free Visual Prompt Learning for Multimodal Large Language Models}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/95574},
}

@inproceedings{neurips2024_implicit_70805,
  title = {{Implicit Multimodal Alignment: On the Generalization of Frozen LLMs to Multimodal Inputs}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/96328},
}

@inproceedings{aaai2025_recoverable_10486,
  title = {{Recoverable Compression: A Multimodal Vision Token Recovery Mechanism Guided by Text Information}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/32229},
}

@inproceedings{aaai2025_st3_10641,
  title = {{ST3: Accelerating Multimodal Large Language Model by Spatial-Temporal Visual Token Trimming}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/33201},
}

@inproceedings{aaai2025_what_11288,
  title = {{What Kind of Visual Tokens Do We Need? Training-Free Visual Token Pruning for Multi-Modal Large Language Models from the Perspective of Graph}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/32427},
}

@inproceedings{cvpr2025_accelerating_25419,
  title = {{Accelerating Multimodal Large Language Models by Searching Optimal Vision Token Reduction}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/33104},
}

@inproceedings{cvpr2025_flashsloth_26277,
  title = {{FlashSloth : Lightning Multimodal Large Language Models via Embedded Visual Compression}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/34869},
}

@inproceedings{cvpr2025_lifting_26793,
  title = {{Lifting the Veil on Visual Information Flow in MLLMs: Unlocking Pathways to Faster Inference}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/34818},
}

@inproceedings{iclr2025_feast_80546,
  title = {{Feast Your Eyes: Mixture-of-Resolution Adaptation for Multimodal Large Language Models}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2025},
  url = {https://iclr.cc/virtual/2025/poster/31217},
}

@inproceedings{neurips2024_leveraging_72545,
  title = {{Leveraging Visual Tokens for Extended Text Contexts in Multi-Modal Learning}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/94826},
}

@inproceedings{aaai2026_filter_100720,
  title = {{Filter, Correlate, Compress: Training-Free Token Reduction for MLLM Acceleration}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2026},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/42460},
}

@inproceedings{aaai2026_efficient_104843,
  title = {{Efficient Segmentation with Multimodal Large Language Model via Token Routing}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2026},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/38032},
}

@inproceedings{aaai2026_d_105478,
  title = {{D²Pruner: Debiased Importance and Structural Diversity for MLLM Token Pruning}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2026},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/38234},
}