% Key papers for Attention-based visual token pruning (scime atlas, https://atlas.scime.ai). Authors are not included: add them from the paper pages.

@inproceedings{cvpr2025_visionzip_28120,
  title = {{VisionZip: Longer is Better but Not Necessary in Vision Language Models}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/34888},
}

@inproceedings{cvpr2025_nvila_27050,
  title = {{NVILA: Efficient Frontier Visual Language Models}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/33311},
}

@inproceedings{cvpr2025_fastvlm_26237,
  title = {{FastVLM: Efficient Vision Encoding for Vision Language Models}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/32887},
}

@inproceedings{cvpr2025_atp_25412,
  title = {{ATP-LLaVA: Adaptive Token Pruning for Large Vision Language Models}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/33610},
}

@inproceedings{aaai2025_hired_9427,
  title = {{HiRED: Attention-Guided Token Dropping for Efficient Inference of High-Resolution Vision-Language Models}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/32171},
}

@inproceedings{cvpr2025_voco_28130,
  title = {{VoCo-LLaMA: Towards Vision Compression with Large Language Models}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/33214},
}

@inproceedings{cvpr2025_topv_27885,
  title = {{TopV: Compatible Token Pruning with Inference Time Optimization for Fast and Low-Memory Multimodal Vision Language Model}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/33168},
}

@inproceedings{neurips2024_q_73338,
  title = {{Q-VLM: Post-training Quantization for Large Vision-Language Models}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/94107},
}

@inproceedings{cvpr2025_a_25370,
  title = {{A Stitch in Time Saves Nine: Small VLM is a Precise Guidance for Accelerating Large VLMs}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/34456},
}

@inproceedings{cvpr2025_docvlm_25988,
  title = {{DocVLM: Make Your VLM an Efficient Reader}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/34337},
}

@inproceedings{cvpr2025_efficientllava_26105,
  title = {{EfficientLLaVA: Generalizable Auto-Pruning for Large Vision-language Models}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/34439},
}

@inproceedings{cvpr2025_hires_26506,
  title = {{HiRes-LLaVA: Restoring Fragmentation Input in High-Resolution Large Vision-Language Models}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/33169},
}

@inproceedings{iclr2024_inducing_33881,
  title = {{Inducing High Energy-Latency of Large Vision-Language Models with Verbose Images}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2024},
  url = {https://iclr.cc/virtual/2024/poster/19194},
}

@inproceedings{neurips2024_matryoshka_70986,
  title = {{Matryoshka Query Transformer for Large Vision-Language Models}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/96220},
}

@inproceedings{aaai2025_a_7947,
  title = {{A-VL: Adaptive Attention for Large Vision-Language Models}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/34403},
}

@inproceedings{aaai2025_unified_11159,
  title = {{Unified Knowledge Maintenance Pruning and Progressive Recovery with Weight Recalling for Large Vision-Language Models}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/32923},
}

@inproceedings{cvpr2025_scaling_27581,
  title = {{Scaling Vision Pre-Training to 4K Resolution}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/33120},
}

@inproceedings{aaai2026_remember_100669,
  title = {{Remember Me: Bridging the Long-Range Gap in LVLMs with Three-Step Inference-Only Decay Resilience Strategies}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2026},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/42409},
}

@inproceedings{aaai2026_rethinking_107597,
  title = {{Rethinking Visual Token Reduction in LVLMs Under Cross-Modal Misalignment}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2026},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/39949},
}

@inproceedings{cvpr2025_conical_25765,
  title = {{Conical Visual Concentration for Efficient Large Vision-Language Models}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/33817},
}