% Key papers for Embodied multimodal LLM agents (scime atlas, https://atlas.scime.ai). Authors are not included: add them from the paper pages.

@inproceedings{cvpr2020_alfred_15097,
  title = {{ALFRED: A Benchmark for Interpreting Grounded Instructions for Everyday Tasks}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2020},
}

@inproceedings{icml2023_palm_42394,
  title = {{PaLM-E: An Embodied Multimodal Language Model}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2023},
  url = {https://icml.cc/virtual/2023/poster/23969},
}

@inproceedings{cvpr2020_robothor_16133,
  title = {{RoboTHOR: An Open Simulation-to-Real Embodied AI Platform}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2020},
}

@inproceedings{cvpr2024_unified_25138,
  title = {{Unified-IO 2: Scaling Autoregressive Multimodal Models with Vision Language Audio and Action}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/29572},
}

@inproceedings{cvpr2024_embodied_23353,
  title = {{Embodied Multi-Modal Agent trained by an LLM from a Parallel TextWorld}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/30385},
}

@inproceedings{iclr2018_interactive_28486,
  title = {{Interactive Grounded Language Acquisition and Generalization in a 2D World}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2018},
  url = {https://iclr.cc/virtual/2018/poster/275},
}

@inproceedings{cvpr2024_multiply_24222,
  title = {{MultiPLY: A Multisensory Object-Centric Embodied Large Language Model in 3D World}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/29685},
}

@inproceedings{cvpr2025_magma_26903,
  title = {{Magma: A Foundation Model for Multimodal AI Agents}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/33563},
}

@inproceedings{cvpr2025_showui_27667,
  title = {{ShowUI: One Vision-Language-Action Model for GUI Visual Agent}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/33472},
}

@inproceedings{cvpr2024_mp5_24075,
  title = {{MP5: A Multi-modal Open-ended Embodied System in Minecraft via Active Perception}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/29631},
}

@inproceedings{icml2024_an_44527,
  title = {{An Embodied Generalist Agent in 3D World}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/33925},
}

@inproceedings{neurips2022_vlmbench_64739,
  title = {{VLMbench: A Compositional Benchmark for Vision-and-Language Manipulation}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2022},
  url = {https://nips.cc/virtual/2022/poster/55749},
}

@inproceedings{neurips2023_androidinthewild_69178,
  title = {{AndroidInTheWild: A Large-Scale Dataset For Android Device Control}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2023},
  url = {https://nips.cc/virtual/2023/poster/73496},
}

@inproceedings{iclr2024_learning_35413,
  title = {{Learning Interactive Real-World Simulators}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2024},
  url = {https://iclr.cc/virtual/2024/poster/17660},
}

@inproceedings{neurips2021_silg_63364,
  title = {{SILG: The Multi-domain Symbolic Interactive Language Grounding Benchmark}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2021},
  url = {https://nips.cc/virtual/2021/poster/26214},
}

@inproceedings{neurips2024_pre_71613,
  title = {{Pre-trained Text-to-Image Diffusion Models Are Versatile Representation Learners for Control}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/95658},
}

@inproceedings{neurips2025_uav_78491,
  title = {{UAV-Flow Colosseo: A Real-World Benchmark for Flying-on-a-Word UAV Imitation Learning}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2025},
  url = {https://openreview.net/forum?id=fJMWkaT2HX},
}

@inproceedings{neurips2021_grounding_62533,
  title = {{Grounding Spatio-Temporal Language with Transformers}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2021},
  url = {https://nips.cc/virtual/2021/poster/25996},
}

@inproceedings{neurips2024_genrl_74646,
  title = {{GenRL: Multimodal-foundation world models for generalization in embodied agents}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/92947},
}

@inproceedings{neurips2025_openhoi_74733,
  title = {{OpenHOI: Open-World Hand-Object Interaction Synthesis with Multimodal Large Language Model}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2025},
  url = {https://openreview.net/forum?id=0biUwyjKkm},
}

@inproceedings{iclr2025_imaginenav_83906,
  title = {{ImagineNav: Prompting Vision-Language Models as Embodied Navigator through Scene Imagination}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2025},
  url = {https://iclr.cc/virtual/2025/poster/27914},
}

@inproceedings{cvpr2025_solami_27535,
  title = {{SOLAMI: Social Vision-Language-Action Modeling for Immersive Interaction with 3D Autonomous Characters}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/34683},
}

@inproceedings{icml2025_embodiedbench_46575,
  title = {{EmbodiedBench: Comprehensive Benchmarking Multi-modal Large Language Models for Vision-Driven Embodied Agents}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2025},
  url = {https://icml.cc/virtual/2025/poster/45994},
}

@inproceedings{neurips2024_grounding_70139,
  title = {{Grounding Multimodal Large Language Models in Actions}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/96941},
}

@inproceedings{iclr2025_articulate_83668,
  title = {{Articulate-Anything: Automatic Modeling of Articulated Objects via a Vision-Language Foundation Model}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2025},
  url = {https://iclr.cc/virtual/2025/poster/28149},
}

@inproceedings{aaai2025_from_9245,
  title = {{From Large Language Models to Large Action Models: Reasoning and Planning with Physical World Knowledge}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/35109},
}

@inproceedings{icml2025_ui_46133,
  title = {{UI-Vision: A Desktop-centric GUI Benchmark for Visual Perception and Interaction}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2025},
  url = {https://icml.cc/virtual/2025/poster/46427},
}

@inproceedings{icml2026_see_50310,
  title = {{See, Act, Adapt: Active Perception for Unsupervised Cross-Domain Visual Adaptation via Personalized VLM-Guided Agent}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2026},
  url = {https://openreview.net/forum?id=B6oQ9Cg5Sh},
}