% Key papers for Chain-of-thought multimodal reasoning (scime atlas, https://atlas.scime.ai). Authors are not included: add them from the paper pages.

@inproceedings{cvpr2024_compositional_23006,
  title = {{Compositional Chain-of-Thought Prompting for Large Multimodal Models}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/30291},
}

@inproceedings{aaai2024_visual_7777,
  title = {{Visual Chain-of-Thought Prompting for Knowledge-Based Visual Reasoning}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/27888},
}

@inproceedings{cvpr2024_visual_25251,
  title = {{Visual Program Distillation: Distilling Tools and Programmatic Reasoning into Vision-Language Models}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/30913},
}

@inproceedings{cvpr2021_transformation_18045,
  title = {{Transformation Driven Visual Reasoning}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2021},
}

@inproceedings{neurips2024_visual_71340,
  title = {{Visual Sketchpad: Sketching as a Visual Chain of Thought for Multimodal Language Models}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/95908},
}

@inproceedings{cvpr2025_insight_26627,
  title = {{Insight-V: Exploring Long-Chain Visual Reasoning with Multimodal Large Language Models}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/34306},
}

@inproceedings{neurips2024_understanding_72055,
  title = {{Understanding the Limits of Vision Language Models Through the Lens of the Binding Problem}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/95266},
}

@inproceedings{iclr2026_medagent_87236,
  title = {{MedAgent-Pro: Towards Evidence-based Multi-modal Medical Diagnosis via Reasoning Agentic Workflow}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2026},
  url = {https://openreview.net/forum?id=ZOuU0udyA4},
}

@inproceedings{cvpr2025_interleaved_26648,
  title = {{Interleaved-Modal Chain-of-Thought}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/33645},
}

@inproceedings{aaai2016_a_104946,
  title = {{A Semantical Analysis of Second-Order Propositional Modal Logic}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2016},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/10100},
}

@inproceedings{cvpr2024_what_25278,
  title = {{What If the TV Was Off? Examining Counterfactual Reasoning Abilities of Multi-modal Language Models}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/30858},
}

@inproceedings{aaai2024_multi_6698,
  title = {{Multi-Modal Latent Space Learning for Chain-of-Thought Reasoning in Language Models}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/29776},
}

@inproceedings{cvpr2025_perception_27237,
  title = {{Perception Tokens Enhance Visual Reasoning in Multimodal Language Models}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/33465},
}

@inproceedings{cvpr2025_ecbench_26052,
  title = {{ECBench: Can Multi-modal Foundation Models Understand the Egocentric World? A Holistic Embodied Cognition Benchmark}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/33904},
}

@inproceedings{neurips2025_openvlthinker_78629,
  title = {{OpenVLThinker: Complex Vision-Language Reasoning via Iterative SFT-RL Cycles}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2025},
  url = {https://openreview.net/forum?id=gfX1nqBKtu},
}

@inproceedings{neurips2025_videochat_79359,
  title = {{VideoChat-R1.5: Visual Test-Time Scaling to Reinforce Multimodal Reasoning by Iterative Perception}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2025},
  url = {https://openreview.net/forum?id=oVDAfLuRie},
}

@inproceedings{neurips2021_reascan_62239,
  title = {{ReaSCAN: Compositional Reasoning in Language Grounding}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2021},
  url = {https://openreview.net/forum?id=Rtquf4Jk0jN},
}

@inproceedings{neurips2025_got_78395,
  title = {{GoT: Unleashing Reasoning Capability of MLLM for Visual Generation and Editing}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2025},
  url = {https://openreview.net/forum?id=eCElREEUsr},
}

@inproceedings{iclr2023_gamr_33013,
  title = {{GAMR: A Guided Attention Model for (visual) Reasoning}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2023},
  url = {https://iclr.cc/virtual/2023/poster/11853},
}

@inproceedings{neurips2024_gita_72250,
  title = {{GITA: Graph to Visual and Textual Integration for Vision-Language Graph Reasoning}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/95093},
}

@inproceedings{iclr2025_visual_83414,
  title = {{Visual Agents as Fast and Slow Thinkers}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2025},
  url = {https://iclr.cc/virtual/2025/poster/28402},
}

@inproceedings{aaai2025_comt_8433,
  title = {{CoMT: A Novel Benchmark for Chain of Multi-modal Thought on Large Vision-Language Models}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/34538},
}

@inproceedings{aaai2026_lens_105649,
  title = {{LENS: Learning to Segment Anything with Unified Reinforced Reasoning}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2026},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/38405},
}

@inproceedings{neurips2024_cracking_72903,
  title = {{Cracking the Code of Juxtaposition: Can AI Models Understand the Humorous Contradictions}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/94508},
}