% Key papers for Instruction-tuned multimodal assistants (scime atlas, https://atlas.scime.ai). Authors are not included: add them from the paper pages.

@inproceedings{cvpr2024_eyes_23422,
  title = {{Eyes Wide Shut? Exploring the Visual Shortcomings of Multimodal LLMs}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/30013},
}

@inproceedings{iclr2024_grounding_35139,
  title = {{Grounding Multimodal Large Language Models to the World}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2024},
  url = {https://iclr.cc/virtual/2024/poster/17934},
}

@inproceedings{cvpr2024_chat_22960,
  title = {{Chat-UniVi: Unified Visual Representation Empowers Large Language Models with Image and Video Understanding}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/31713},
}

@inproceedings{cvpr2024_gsva_23565,
  title = {{GSVA: Generalized Segmentation via 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/31608},
}

@inproceedings{cvpr2024_v_25179,
  title = {{V?: Guided Visual Search as a Core Mechanism in Multimodal LLMs}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/31596},
}

@inproceedings{cvpr2024_honeybee_23713,
  title = {{Honeybee: Locality-enhanced Projector for Multimodal LLM}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/29641},
}

@inproceedings{cvpr2024_osprey_24388,
  title = {{Osprey: Pixel Understanding with Visual Instruction Tuning}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/31799},
}

@inproceedings{cvpr2024_lion_23891,
  title = {{LION: Empowering Multimodal Large Language Model with Dual-Level Visual Knowledge}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/31645},
}

@inproceedings{cvpr2024_maplm_24052,
  title = {{MAPLM: A Real-World Large-Scale Vision-Language Benchmark for Map and Traffic Scene Understanding}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/30180},
}

@inproceedings{iclr2024_ferret_33538,
  title = {{Ferret: Refer and Ground Anything Anywhere at Any Granularity}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2024},
  url = {https://iclr.cc/virtual/2024/poster/19537},
}

@inproceedings{neurips2024_cambrian_72481,
  title = {{Cambrian-1: A Fully Open, Vision-Centric Exploration of Multimodal LLMs}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/94880},
}

@inproceedings{aaai2025_lidar_9787,
  title = {{LiDAR-LLM: Exploring the Potential of Large Language Models for 3D LiDAR Understanding}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/33001},
}

@inproceedings{cvpr2024_groundhog_23561,
  title = {{GROUNDHOG: Grounding Large Language Models to Holistic Segmentation}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/30796},
}

@inproceedings{cvpr2024_vcoder_25183,
  title = {{VCoder: Versatile Vision Encoders 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/31412},
}

@inproceedings{cvpr2024_cloud_22974,
  title = {{Cloud-Device Collaborative Learning 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/31459},
}

@inproceedings{cvpr2025_slidechat_27693,
  title = {{SlideChat: A Large Vision-Language Assistant for Whole-Slide Pathology Image Understanding}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/35105},
}

@inproceedings{cvpr2024_pink_24469,
  title = {{Pink: Unveiling the Power of Referential Comprehension 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/29891},
}

@inproceedings{iclr2024_q_33459,
  title = {{Q-Bench: A Benchmark for General-Purpose Foundation Models on Low-level Vision}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2024},
  url = {https://iclr.cc/virtual/2024/poster/19616},
}

@inproceedings{neurips2024_vitron_73590,
  title = {{Vitron: A Unified Pixel-level Vision LLM for Understanding, Generating, Segmenting, Editing}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/93896},
}

@inproceedings{neurips2025_spatial_77239,
  title = {{Spatial-MLLM: Boosting MLLM Capabilities in Visual-based Spatial Intelligence}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2025},
  url = {https://openreview.net/forum?id=RnXS7aK4rK},
}