% Key papers for Memory and subgoal-based manipulation (scime atlas, https://atlas.scime.ai). Authors are not included: add them from the paper pages.

@inproceedings{cvpr2024_manipllm_24106,
  title = {{ManipLLM: Embodied Multimodal Large Language Model for Object-Centric Robotic Manipulation}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/30495},
}

@inproceedings{icml2020_visual_38927,
  title = {{Visual Grounding of Learned Physical Models}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2020},
  url = {https://icml.cc/virtual/2020/poster/6550},
}

@inproceedings{cvpr2024_unigarmentmanip_25127,
  title = {{UniGarmentManip: A Unified Framework for Category-Level Garment Manipulation via Dense Visual Correspondence}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/30566},
}

@inproceedings{cvpr2024_cyberdemo_23073,
  title = {{CyberDemo: Augmenting Simulated Human Demonstration for Real-World Dexterous Manipulation}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/30316},
}

@inproceedings{cvpr2025_code_25734,
  title = {{Code-as-Monitor: Constraint-aware Visual Programming for Reactive and Proactive Robotic Failure Detection}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/34558},
}

@inproceedings{cvpr2025_roboground_27473,
  title = {{RoboGround: Robotic Manipulation with Grounded Vision-Language Priors}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/34049},
}

@inproceedings{neurips2023_imagebrush_67438,
  title = {{ImageBrush: Learning Visual In-Context Instructions for Exemplar-Based Image Manipulation}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2023},
  url = {https://nips.cc/virtual/2023/poster/72295},
}

@inproceedings{neurips2022_actionsense_66000,
  title = {{ActionSense: A Multimodal Dataset and Recording Framework for Human Activities Using Wearable Sensors in a Kitchen Environment}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2022},
  url = {https://nips.cc/virtual/2022/poster/55638},
}

@inproceedings{aaai2026_dexgraspvla_106646,
  title = {{DexGraspVLA: A Vision-Language-Action Framework Towards General Dexterous Grasping}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2026},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/38953},
}

@inproceedings{cvpr2024_generate_23601,
  title = {{Generate Subgoal Images before Act: Unlocking the Chain-of-Thought Reasoning in Diffusion Model for Robot Manipulation with Multimodal Prompts}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/29511},
}

@inproceedings{cvpr2025_mitigating_26966,
  title = {{Mitigating the Human-Robot Domain Discrepancy in Visual Pre-training for Robotic Manipulation}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/32537},
}

@inproceedings{aaai2021_learning_882,
  title = {{Learning Intuitive Physics with Multimodal Generative Models}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2021},
  url = {https://aaai.org/papers/06110-learning-intuitive-physics-with-multimodal-generative-models/},
}

@inproceedings{iclr2025_rdt_84082,
  title = {{RDT-1B: a Diffusion Foundation Model for Bimanual Manipulation}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2025},
  url = {https://iclr.cc/virtual/2025/poster/27746},
}

@inproceedings{cvpr2025_phoenix_27248,
  title = {{Phoenix: A Motion-based Self-Reflection Framework for Fine-grained Robotic Action Correction}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/32789},
}

@inproceedings{iclr2024_unleashing_34313,
  title = {{Unleashing Large-Scale Video Generative Pre-training for Visual Robot Manipulation}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2024},
  url = {https://iclr.cc/virtual/2024/poster/18762},
}

@inproceedings{neurips2025_sofar_79015,
  title = {{SoFar: Language-Grounded Orientation Bridges Spatial Reasoning and Object Manipulation}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2025},
  url = {https://openreview.net/forum?id=kmv7yg6QXv},
}

@inproceedings{iclr2025_aha_81671,
  title = {{AHA: A Vision-Language-Model for Detecting and Reasoning Over Failures in Robotic Manipulation}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2025},
  url = {https://iclr.cc/virtual/2025/poster/30106},
}

@inproceedings{cvpr2025_garmentpile_26380,
  title = {{GarmentPile: Point-Level Visual Affordance Guided Retrieval and Adaptation for Cluttered Garments Manipulation}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/32949},
}

@inproceedings{neurips2024_pivot_73327,
  title = {{PIVOT-R: Primitive-Driven Waypoint-Aware World Model for Robotic Manipulation}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/94118},
}

@inproceedings{neurips2024_humanvla_73980,
  title = {{HumanVLA: Towards Vision-Language Directed Object Rearrangement by Physical Humanoid}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/93535},
}

@inproceedings{iclr2025_data_83511,
  title = {{Data Scaling Laws in Imitation Learning for Robotic Manipulation}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2025},
  url = {https://iclr.cc/virtual/2025/poster/28305},
}

@inproceedings{cvpr2025_generating_26412,
  title = {{Generating 6DoF Object Manipulation Trajectories from Action Description in Egocentric Vision}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/34183},
}

@inproceedings{cvpr2025_grounding_26457,
  title = {{Grounding 3D Object Affordance with Language Instructions, Visual Observations and Interactions}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/33183},
}

@inproceedings{neurips2025_touch_77692,
  title = {{Touch in the Wild: Learning Fine-Grained Manipulation with a Portable Visuo-Tactile Gripper}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2025},
  url = {https://openreview.net/forum?id=WabVVQKTUF},
}