Kilichbek Haydarov

Hi! I build emotion-aware multimodal AI: models that understand and respond to human emotion across images, dialogue, speech, and brain signals. My work spans affective image captioning (ArtEmis, CVPR 2021 & 2022), emotional reasoning in visual dialog (ECCV 2024), emotion-guided psychotherapy interventions (EMNLP 2025), and the shared emotional structure of language models and the human brain (2026).

I am currently pursuing my Ph.D. in Computer Science, with a research focus on Vision and Language, and Generative Modelling, in Visual Computing Center (VCC) at KAUST. I am a member of Vision-CAIR Research Group led by Prof. Mohamed Elhoseiny, and of KAUST NeuroAI, an interdisciplinary research community that combines neuroscience, AI, statistical modeling, and signal processing to decode and use brain signals in naturalistic settings.

Apart from research, I am also passionate about AI art, Chess.

Previously: I received my Bachelor’s Degree in Computer Science and Engineering from Sejong University (South Korea), Master’s Degree in Computer Science from KAUST (Saudi Arabia).

Research Interests: Affective Vision and Language, Generative Modelling, Neuroscience + AI

news

Sep 19, 2025	One paper accepted at the EMNLP 2025!
Aug 27, 2024	One paper accepted at the ECCV 2024!
Feb 27, 2024	One paper accepted at the CVPR 2024!
Jul 08, 2023	Our team won the 1st prize in the 2st SAAI Factory Hackathon (Art + AI)!
Jul 01, 2023	Co-organizing the 5th Workshop on Closing the Loop Between Vision and Language (CLVL) at ICCV 2023.

selected publications

arXiv

A Shared Valence Axis Across Modern LLMs and Human EEG: The Saturation Regularity

Yousef A. Radwan, Xuhui Liu, Kilichbek Haydarov, and 2 more authors

arXiv preprint arXiv:2606.00129, 2026

arXiv Bib

@article{radwan2026valence,
  title = {A Shared Valence Axis Across Modern {LLMs} and Human {EEG}: The Saturation Regularity},
  author = {Radwan, Yousef A. and Liu, Xuhui and Haydarov, Kilichbek and Fu, Yuqian and Elhoseiny, Mohamed},
  journal = {arXiv preprint arXiv:2606.00129},
  year = {2026},
}

EMNLP

Towards AI-Assisted Psychotherapy: Emotion-Guided Generative Interventions

Kilichbek Haydarov, Youssef Mohamed, Emilio Goldenhersch, and 3 more authors

In Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing (EMNLP), 2025

DOI Bib HTML PDF

@inproceedings{haydarov2025towards,
  title = {Towards {AI}-Assisted Psychotherapy: Emotion-Guided Generative Interventions},
  author = {Haydarov, Kilichbek and Mohamed, Youssef and Goldenhersch, Emilio and O'Callaghan, Paul and Li, Li-jia and Elhoseiny, Mohamed},
  booktitle = {Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing (EMNLP)},
  pages = {32736--32755},
  year = {2025},
  publisher = {Association for Computational Linguistics},
  doi = {10.18653/v1/2025.emnlp-main.1664},
}

EMNLP

No Culture Left Behind: ArtELingo-28, a Benchmark of WikiArt with Captions in 28 Languages

Youssef Mohamed, Runjia Li, Ibrahim Said Ahmad, and 4 more authors

In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing (EMNLP), 2024

DOI Bib HTML PDF

@inproceedings{mohamed2024culture,
  title = {No Culture Left Behind: {ArtELingo}-28, a Benchmark of {WikiArt} with Captions in 28 Languages},
  author = {Mohamed, Youssef and Li, Runjia and Ahmad, Ibrahim Said and Haydarov, Kilichbek and Torr, Philip and Church, Kenneth and Elhoseiny, Mohamed},
  booktitle = {Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing (EMNLP)},
  pages = {20939--20962},
  year = {2024},
  publisher = {Association for Computational Linguistics},
  doi = {10.18653/v1/2024.emnlp-main.1165},
}

CVPR

Adversarial Text to Continuous Image Generation

Kilichbek Haydarov, Aashiq Muhamed, Xiaoqian Shen, and 4 more authors

In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2024

Bib HTML PDF

@inproceedings{haydarov2023adversarial,
  title = {Adversarial Text to Continuous Image Generation},
  author = {Haydarov, Kilichbek and Muhamed, Aashiq and Shen, Xiaoqian and Lazarevic, Jovana and Skorokhodov, Ivan and Galappaththige, Chamuditha Jayanga and Elhoseiny, Mohamed},
  booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  pages = {6316--6326},
  year = {2024},
}

ECCV

Affective Visual Dialog: A Large-Scale Benchmark for Emotional Reasoning Based on Visually Grounded Conversations

Kilichbek Haydarov, Xiaoqian Shen, Avinash Madasu, and 4 more authors

In Proceedings of the European Conference on Computer Vision (ECCV), 2024

DOI arXiv Bib

@inproceedings{haydarov2023affective,
  title = {Affective Visual Dialog: A Large-Scale Benchmark for Emotional Reasoning Based on Visually Grounded Conversations},
  author = {Haydarov, Kilichbek and Shen, Xiaoqian and Madasu, Avinash and Salem, Mahmoud and Li, Li-Jia and Elsayed, Gamaleldin and Elhoseiny, Mohamed},
  booktitle = {Proceedings of the European Conference on Computer Vision (ECCV)},
  pages = {18--36},
  year = {2024},
  publisher = {Springer},
  doi = {10.1007/978-3-031-73226-3_2},
}

TMLR

ChatGPT Asks, BLIP-2 Answers: Automatic Questioning Towards Enriched Visual Descriptions

Deyao Zhu, Jun Chen, Kilichbek Haydarov, and 3 more authors

Transactions on Machine Learning Research, 2024

arXiv Bib HTML Code

@article{zhu2023chatgpt,
  title = {{ChatGPT} Asks, {BLIP-2} Answers: Automatic Questioning Towards Enriched Visual Descriptions},
  author = {Zhu, Deyao and Chen, Jun and Haydarov, Kilichbek and Shen, Xiaoqian and Zhang, Wenxuan and Elhoseiny, Mohamed},
  journal = {Transactions on Machine Learning Research},
  year = {2024},
}

arXiv

Video ChatCaptioner: Towards Enriched Spatiotemporal Descriptions

Jun Chen, Deyao Zhu, Kilichbek Haydarov, and 2 more authors

arXiv preprint arXiv:2304.04227, 2023

arXiv Bib Code

@article{chen2023video,
  title = {Video {ChatCaptioner}: Towards Enriched Spatiotemporal Descriptions},
  author = {Chen, Jun and Zhu, Deyao and Haydarov, Kilichbek and Li, Xiang and Elhoseiny, Mohamed},
  journal = {arXiv preprint arXiv:2304.04227},
  year = {2023},
}

CVPR

It is Okay to Not Be Okay: Overcoming Emotional Bias in Affective Image Captioning by Contrastive Data Collection

Youssef Mohamed, Faizan Farooq Khan, Kilichbek Haydarov, and 1 more author

In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2022

arXiv Bib HTML

@inproceedings{mohamed2022okay,
  title = {It is Okay to Not Be Okay: Overcoming Emotional Bias in Affective Image Captioning by Contrastive Data Collection},
  author = {Mohamed, Youssef and Khan, Faizan Farooq and Haydarov, Kilichbek and Elhoseiny, Mohamed},
  booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  pages = {21263--21272},
  year = {2022},
}

CVPR

ArtEmis: Affective Language for Visual Art

Panos Achlioptas, Maks Ovsjanikov, Kilichbek Haydarov, and 2 more authors

In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2021

arXiv Bib HTML

@inproceedings{achlioptas2021artemis,
  title = {{ArtEmis}: Affective Language for Visual Art},
  author = {Achlioptas, Panos and Ovsjanikov, Maks and Haydarov, Kilichbek and Elhoseiny, Mohamed and Guibas, Leonidas J.},
  booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  pages = {11569--11579},
  year = {2021},
}