% Key papers for Multimodal prompt-driven manipulation (scime atlas, https://atlas.scime.ai). Authors are not included: add them from the paper pages.

@inproceedings{aaai2017_natural_104583,
  title = {{Natural Language Acquisition and Grounding for Embodied Robotic Systems}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2017},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/11161},
}

@inproceedings{neurips2017_multi_56487,
  title = {{Multi-Modal Imitation Learning from Unstructured Demonstrations using Generative Adversarial Nets}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2017},
  url = {https://nips.cc/virtual/2017/poster/8916},
}

@inproceedings{neurips2022_behavior_65394,
  title = {{Behavior Transformers: Cloning \$k\$ modes with one stone}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2022},
  url = {https://nips.cc/virtual/2022/poster/55332},
}

@inproceedings{icml2023_liv_41940,
  title = {{LIV: Language-Image Representations and Rewards for Robotic Control}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2023},
  url = {https://icml.cc/virtual/2023/poster/23808},
}

@inproceedings{cvpr2025_robobrain_27472,
  title = {{RoboBrain: A Unified Brain Model for Robotic Manipulation from Abstract to Concrete}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/34105},
}

@inproceedings{cvpr2018_reward_13536,
  title = {{Reward Learning From Narrated Demonstrations}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2018},
  url = {https://openaccess.thecvf.com/content_cvpr_2018/html/Tung_Reward_Learning_From_CVPR_2018_paper.html},
}

@inproceedings{aaai2018_guiding_105906,
  title = {{Guiding Exploratory Behaviors for Multi-Modal Grounding of Linguistic Descriptions}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2018},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/11966},
}

@inproceedings{neurips2024_scaling_72022,
  title = {{Scaling Proprioceptive-Visual Learning with Heterogeneous Pre-trained Transformers}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/95294},
}

@inproceedings{cvpr2025_object_27107,
  title = {{Object-Centric Prompt-Driven Vision-Language-Action Model for Robotic Manipulation}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/34522},
}

@inproceedings{iclr2018_imitation_28524,
  title = {{Imitation Learning from Visual Data with Multiple Intentions}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2018},
  url = {https://iclr.cc/virtual/2018/poster/53},
}

@inproceedings{cvpr2020_gold_15612,
  title = {{Gold Seeker: Information Gain From Policy Distributions for Goal-Oriented Vision-and-Langauge Reasoning}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2020},
}

@inproceedings{iclr2023_programmatically_33246,
  title = {{Programmatically Grounded, Compositionally Generalizable Robotic Manipulation}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2023},
  url = {https://iclr.cc/virtual/2023/poster/11828},
}

@inproceedings{icml2024_robocodex_45759,
  title = {{RoboCodeX: Multimodal Code Generation for Robotic Behavior Synthesis}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/32693},
}

@inproceedings{neurips2024_peria_74671,
  title = {{PERIA: Perceive, Reason, Imagine, Act via Holistic Language and Vision Planning for Manipulation}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/92925},
}

@inproceedings{iclr2023_using_32034,
  title = {{Using Both Demonstrations and Language Instructions to Efficiently Learn Robotic Tasks}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2023},
  url = {https://iclr.cc/virtual/2023/poster/10957},
}

@inproceedings{aaai2026_intention_106490,
  title = {{Intention-Guided Cognitive Reasoning for Egocentric Long-Term Action Anticipation}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2026},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/38797},
}

@inproceedings{cvpr2025_robotic_27478,
  title = {{Robotic Visual Instruction}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/34129},
}

@inproceedings{icml2024_mastering_45733,
  title = {{Mastering Robot Manipulation with Multimodal Prompts through Pretraining and Multi-task Fine-tuning}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/32719},
}

@inproceedings{neurips2025_robocerebra_74704,
  title = {{RoboCerebra: A Large-scale Benchmark for Long-horizon Robotic Manipulation Evaluation}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2025},
  url = {https://openreview.net/forum?id=0JtNyaHbNx},
}

@inproceedings{iclr2025_strap_80760,
  title = {{STRAP: Robot Sub-Trajectory Retrieval for Augmented Policy Learning}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2025},
  url = {https://iclr.cc/virtual/2025/poster/31008},
}

@inproceedings{iclr2025_robots_84102,
  title = {{Robots Pre-train Robots: Manipulation-Centric Robotic Representation from Large-Scale Robot Datasets}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2025},
  url = {https://iclr.cc/virtual/2025/poster/27726},
}

@inproceedings{aaai2026_maniplvm_106615,
  title = {{ManipLVM-R1: Reinforcement Learning for Reasoning in Embodied Manipulation with Large Vision-Language Models}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2026},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/38922},
}

@inproceedings{iclr2024_what_33902,
  title = {{What Matters to You? Towards Visual Representation Alignment for Robot Learning}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2024},
  url = {https://iclr.cc/virtual/2024/poster/19173},
}

@inproceedings{icml2024_decisionnce_43323,
  title = {{DecisionNCE: Embodied Multimodal Representations via Implicit Preference Learning}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/35129},
}

@inproceedings{icml2024_robomp_44946,
  title = {{RoboMP\$^2\$: A Robotic Multimodal Perception-Planning Framework with Multimodal Large Language Models}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/33506},
}

@inproceedings{icml2025_vip_47924,
  title = {{VIP: Vision Instructed Pre-training for Robotic Manipulation}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2025},
  url = {https://icml.cc/virtual/2025/poster/44680},
}

@inproceedings{icml2025_hi_48415,
  title = {{Hi Robot: Open-Ended Instruction Following with Hierarchical Vision-Language-Action Models}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2025},
  url = {https://icml.cc/virtual/2025/poster/44202},
}

@inproceedings{icml2026_robomme_50069,
  title = {{RoboMME: Benchmarking and Understanding Memory for Robotic Generalist Policies}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2026},
  url = {https://openreview.net/forum?id=8m30ogkPk2},
}

@inproceedings{neurips2024_any2policy_70775,
  title = {{Any2Policy: Learning Visuomotor Policy with Any-Modality}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/96353},
}

@inproceedings{neurips2025_provable_75038,
  title = {{Provable Ordering and Continuity in Vision-Language Pretraining for Generalizable Embodied Agents}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2025},
  url = {https://openreview.net/forum?id=3fDypdR4VN},
}