Elamur Research⌕
☰
home / papers / 2026 / NOSE: Neural Olfactory-Semantic Embedding with Tri-Modal Orthogonal Contrastive Learning

NOSE: Neural Olfactory-Semantic Embedding with Tri-Modal Orthogonal Contrastive Learning

Paper · 2026 · Yanyi Su, Hongshuai Wang, Zhifeng Gao et al.

Summary

NOSE addresses the problem of building odor representations that reflect the full olfactory pathway, from odorant molecule to olfactory receptor to the words people use to describe smells. Earlier methods model only part of this chain and usually frame odor prediction as classification over discrete labels, which ignores how related descriptors and receptors are. The authors note that full molecule–receptor–description triplets are rare, but the two pair types exist separately. They therefore use the molecule as a hub. A frozen Uni-Mol molecular embedding is split by two adapters into a receptor-aligned part and a description-aligned part, and these are kept apart through Gram-Schmidt orthogonalization and an orthogonality loss. Description sparsity causes false negatives in contrastive learning. To reduce this, an LLM identifies semantically close descriptors, which are then treated as weak positives. The authors also release a curated pretraining corpus and a multi-level benchmark covering threshold, intensity, pleasantness, descriptors and mixtures. NOSE reports state-of-the-art results on this benchmark and strong zero-shot cross-modal retrieval. This matters for flavor design and sensory computing.

Key points

  • Encoders: The molecule encoder is Uni-Mol (frozen). Receptors are encoded with ESM-2 plus a trainable projector, and descriptions with Qwen3 Embedding fine-tuned using LoRA. At inference, the final embedding is a gated, weighted sum of the molecular vector and the two adapter outputs.
  • Pretraining data:
    • 3,877 SMILES–receptor pairs.
    • 88,512 SMILES–description pairs (e.g., Arctander).
    • An LLM-expanded set of 2,567,558 description pairs.
  • Loss design: The description–molecule loss is a soft-weighted InfoNCE, with weights of 1.0 for positives, 0.5 for weak positives and 0.0 for negatives. It is combined with intra-modal InfoNCE and orthogonality terms.
  • Zero-shot receptor retrieval: For activated receptors, Hits@5 reaches 61.5%. No non-activated receptor appears among the top 200 candidates.
  • Compositional queries: On 31 descriptor-arithmetic queries (e.g., Lemon − Sour), MRR rises from 0.0102 with the original Qwen3 Embedding to 0.2072 with LoRA plus a projection head.

Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.

 Institutions

🎓Xiamen UniversityXiamen · China24 works · 2,317 citations

 Fields, topics and concepts

📚 Shelves 5The field of science this work belongs to (OpenAlex fields).Computer Science · 18,614 worksArtificial Intelligence · 17,965 worksComputer Vision and Pattern Recognition · 3,486 worksNeuroscience · 186 worksSensory Systems · 1 work

Cite

Cite as Yanyi Su, Hongshuai Wang, Zhifeng Gao and Jun Cheng. 2026. NOSE: Neural Olfactory-Semantic Embedding with Tri-Modal Orthogonal Contrastive Learning. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers).

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.18653/v1/2026.acl-long.898

@inproceedings{su2026nose,
  title = {{NOSE: Neural Olfactory-Semantic Embedding with Tri-Modal Orthogonal Contrastive Learning}},
  author = {Yanyi Su, Hongshuai Wang, Zhifeng Gao and Jun Cheng},
  booktitle = {Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)},
  year = {2026},
  doi = {10.18653/v1/2026.acl-long.898},
  url = {https://doi.org/10.18653/v1/2026.acl-long.898}
}

References

71 references, 6 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Michael H Abraham, Ricardo Sánchez-Moreno, J Enrique Cometto-Muñiz, and William S Cain. 2012. An algorithm for 353 odor detection thresholds in humans. Chemical senses, 37(3):207–218. find
  2. T Acree. 2004. Flavornet and human odor space. http://www.flavornet.org/flavornet.html. ↗
  3. Lucky Ahmed, Yuetian Zhang, Eric Block, Michael Buehl, Michael J Corr, Rodrigo A Cormanich, Sivaji Gundala, Hiroaki Matsunami, David O’Hagan, Mehmet Ozbil, and others. 2018. Molecular mechanism of activation of human musk receptors or5an1 and or1a1 by (r)-muscone and diverse other musk-smelling comp… find
  4. Steffen Arctander. 2017. Perfume and flavor materials of natural origin. Lulu.com. find
  5. Christian B Billesbølle, Claire A de March, Wijnand JC van der Velden, Ning Ma, Jeevan Tewari, Claudia Lli-nas Del Torrent, Linus Li, Bryan Faust, Nagarajan Vaidehi, Hiroaki Matsunami, and others. 2023. Structural basis of odorant recognition by a human odorant receptor. Nature, 615(7953):742–749. find
  6. Linda Buck and Richard Axel. 1991. A novel multigene family may encode odorant receptors: a molecular basis for odor recognition. Cell, 65(1):175–187. find
  7. Ting Chen, Simon Kornblith, Mohammad Norouzi, and Geoffrey Hinton. 2020. A simple framework for contrastive learning of visual representations. In International conference on machine learning, pages 1597–1607. PmLR.
  8. Seyone Chithrananda, Judith Amores, and Kevin K Yang. 2024. Mapping the combinatorial coding between olfactory receptors and perception with deep learning. bioRxiv, pages 2024–09. find
  9. Seyone Chithrananda, Gabriel Grand, and Bharath Ramsundar. 2020. Chemberta: large-scale self-supervised pretraining for molecular property prediction. arXiv preprint arXiv:2010.09885. find
  10. Chulwon Choi, Jungnam Bae, Seonghan Kim, Seho Lee, Hyunook Kang, Jinuk Kim, Injin Bang, Kiheon Kim, Won-Ki Huh, Chaok Seok, and others. 2023. Understanding the molecular mechanisms of odorant binding and activation of the human or52 family. Nature Communications, 14(1):8105. find
  11. Neelansh Garg, Apuroop Sethupathy, Rudraksh Tuwani, Rakhi Nk, Shubham Dokania, Arvind Iyer, Ayushi Gupta, Shubhra Agrawal, Navjot Singh, Shubham Shukla, and others. 2018. Flavordb: a database of flavor molecules. Nucleic acids research, 46(D1):D1210–D1216. find
  12. Christiane Geithe, Gaby Andersen, Agne Malki, and Dietmar Krautwurst. 2015. A butter aroma recombinate activates human class-i odorant receptors. Journal of agricultural and food chemistry, 63(43):9410–9420. find
  13. Rosa S Gisladottir, Erna V Ivarsdottir, Agnar Helga-son, Lina Jonsson, Nanna K Hannesdottir, Gudrun Rutsdottir, Gudny A Arnadottir, Astros Skuladottir, Benedikt A Jonsson, Gudmundur L Norddahl, and others. 2020. Sequence variants in taar5 and other loci affect human odor perception and naming. Curre… find
  14. Daya Guo, Dejian Yang, Haowei Zhang, Junxiao Song, Peiyi Wang, Qihao Zhu, Runxin Xu, Ruoyu Zhang, Shirong Ma, Xiao Bi, and others. 2025. Deepseek-r1 incentivizes reasoning in llms through reinforcement learning. Nature, 645(8081):633–638. find
  15. Ria Gupta, Aayushi Mittal, Vishesh Agrawal, Sushant Gupta, Krishan Gupta, Rishi Raj Jain, Prakriti Garg, Sanjay Kumar Mohanty, Riya Sogani, Harshit Singh Chhabra, and others. 2021. Odorify: a conglomerate of artificial intelligence–driven prediction engines for olfactory decoding. Journal of Biologi… find
  16. Linda B Buck. 2004. Olfactory receptors and odor coding in mammals. Nutrition reviews, 62(suppl_3):S184–S188. find
  17. Franziska Haag, Antonella Di Pizio, and Dietmar Krautwurst. 2022. The key food odorant receptive range of broadly tuned receptor or2w1. Food Chemistry, 375:131680. find
  18. Caroline Bushdid, Marcelo O Magnasco, Leslie B Vosshall, and Andreas Keller. 2014. Humans can discriminate more than 1 trillion olfactory stimuli. Science, 343(6177):1370–1372. find
  19. Elizabeth A Hamel, Jason B Castro, Travis J Gould, Robert Pellegrino, Zhiwei Liang, Liyah A Coleman, Famesh Patel, Derek S Wallace, Tanushri Bhatnagar, Joel D Mainland, and others. 2024. Pyrfume: A window to the world’s olfactory data. Scientific Data, 11(1):1220. human olfactory epithelium reflects… find
  20. Devamanyu Hazarika, Roger Zimmermann, and Soujanya Poria. 2020. Misa: Modality-invariant and-specific representations for multimodal sentiment analysis. In Proceedings of the 28th ACM international conference on multimedia, pages 1122–1131. find
  21. Brian K Lee, Emily J Mayhew, Benjamin Sanchez-Lengeling, Jennifer N Wei, Wesley W Qian, Kelsie A Little, Matthew Andres, Britney B Nguyen, Theresa Moloy, Jacob Yasonik, and others. 2023. A principal odor map unifies diverse tasks in olfactory perception. Science, 381(6661):999–1006. find
  22. Edward J Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen-Zhu, Yuanzhi Li, Shean Wang, Lu Wang, Weizhu Chen, and others. 2022. Lora: Low-rank adaptation of large language models. ICLR, 1(2):3.
  23. International Fragrance Association (IFRA). 2025. IFRA Fragrance Ingredient Glossary. https://ifrafragrance.org/ publications/guidance-reference-document/ Ac-ifra-fragrance-ingredient-glossary. cessed: December 10, 2025. ↗
  24. Yongquan Jiang, Xin Xie, Yan Yang, Yuerui Liu, Kuan-ping Gong, and Tianrui Li. 2025. Dual-branch graph neural network for predicting molecular odors and discovering the relationship between functional groups and odors. Journal of Computational Chemistry, 46(6):e70069. find
  25. Andreas Keller, Richard C Gerkin, Yuanfang Guan, Amit Dhurandhar, Gabor Turu, Bence Szalai, Joel D Mainland, Yusuke Ihara, Chung Wen Yu, Russ Wolfinger, and others. 2017. Predicting human olfactory perception from chemical features of odor molecules. Science, 355(6327):820–826. find
  26. Andreas Keller and Leslie B Vosshall. 2016. Olfactory perception of chemically diverse molecules. BMC neuroscience, 17(1):55. find
  27. TN Kipf. 2016. Semi-supervised classification with graph convolutional networks. arXiv preprint arXiv:1609.02907.
  28. Yogesh Kumar, Om Prakash, Himanshu Tripathi, Sudeep Tandon, Madan M Gupta, Laiq-Ur Rahman, Raj K Lal, Manoj Semwal, Mahendra Pan-durang Darokar, and Feroz Khan. 2018. Aromadb: a database of medicinal and aromatic plant’s aroma molecules with phytochemistry and therapeutic potentials. Frontiers in pl… find
  29. Murathan Kurfalı, Pawel Herman, Stephen Pierzchajlo, Jonas Olofsson, and Thomas Hörberg. 2025. Representations of smells: The next frontier for language models? Cognition, 264:106243. find
  30. Maxence Lalis, Matej Hladiš, Samar Abi Khalil, Loïc Briand, Sébastien Fiorucci, and Jérémie Topin. 2024. M2or: a database of olfactory receptor–odorant pairs for understanding the molecular mechanisms of olfaction. Nucleic Acids Research, 52(D1):D1370– D1379. find
  31. Hadas Lapid, Sagit Shushan, Anton Plotkin, Hillary Voet, Yehudah Roth, Thomas Hummel, Elad Schnei-dman, and Noam Sobel. 2011. Neural activity at the Paul Pu Liang, Zihao Deng, Martin Q Ma, James Y Zou, Louis-Philippe Morency, and Ruslan Salakhutdinov. 2023. Factorized contrastive learning: Going bey… find
  32. Zeming Lin, Halil Akin, Roshan Rao, Brian Hie, Zhongkai Zhu, Wenting Lu, Nikita Smetanin, Robert Verkuil, Ori Kabeli, Yaniv Shmueli, and others. 2023. Evolutionary-scale prediction of atomic-level protein structure with a language model. Science, 379(6637):1123–1130. find
  33. Shengzhong Liu, Tomoyoshi Kimura, Dongxin Liu, Ruijie Wang, Jinyang Li, Suhas Diggavi, Mani Srivastava, and Tarek Abdelzaher. 2023. Focal: Contrastive learning for multimodal time-series sensing signals in factorized orthogonal latent space. Advances in Neural Information Processing Systems, 36:4730… find
  34. Yue Ma, Ke Tang, Yan Xu, and Thierry Thomas-Danguin. 2021. A dataset on odor intensity and odor pleasantness of 222 binary mixtures of 72 key food odorants rated by a sensory panel of 30 trained assessors. Data in brief, 36:107143. find
  35. Joel D Mainland, Yun R Li, Ting Zhou, Wen Ling L Liu, and Hiroaki Matsunami. 2015. Human olfactory receptor responses to odorants. Scientific data, 2(1):1–9. find
  36. Bettina Malnic, Junzo Hirono, Takaaki Sato, and Linda B Buck. 1999. Combinatorial receptor codes for odors. Cell, 96(5):713–723. find
  37. Emily J Mayhew, Charles J Arayata, Richard C Gerkin, Brian K Lee, Jonathan M Magill, Lindsey L Snyder, Kelsie A Little, Chung Wen Yu, and Joel D Mainland. 2022. Transport features predict if a molecule is odorous. Proceedings of the National Academy of Sciences, 119(15):e2116576119. find
  38. Grant D McConachie, Emily Duniec, Florence Guerina, Meg A Younger, and Brian DePasquale. 2025. Low rank adaptation of chemical foundation models generates effective odorant representations. bioRxiv, pages 2025–11. find
  39. Guillaume Ollitrault, Rayane Achebouche, Antoine Dreux, Samuel Murail, Karine Audouze, Anne Tromelin, and Olivier Taboureau. 2024. Pred-o3, a web server to predict molecules, olfactory receptors and odor relationships. Nucleic Acids Research, 52(W1):W507–W512. find
  40. Alec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, and others. 2021. Learning transferable visual models from natural language supervision. In International conference on machine learning, pages 8748–876…
  41. Aharon Ravia, Kobi Snitz, Danielle Honigstein, Maya Finkel, Rotem Zirler, Ofer Perl, Lavi Secundo, Christophe Laudamiel, David Harel, and Noam Sobel. 2020. A measure of smell enables the creation of olfactory metamers. Nature, 588(7836):118–123. find
  42. David Rogers and Mathew Hahn. 2010. Extended-connectivity fingerprints. Journal of chemical information and modeling, 50(5):742–754. find
  43. Vivek Sagar, Laura K Shanahan, Christina M Ze-lano, Jay A Gottfried, and Thorsten Kahnt. 2023. High-precision mapping reveals the structure of odor coding in the human brain. Nature neuroscience, 26(9):1595–1602. find
  44. Kobi Snitz, Adi Yablonka, Tali Weiss, Idan Frumin, Rehan M Khan, and Noam Sobel. 2013. Predicting odor perceptual similarity from odor structure. PLoS computational biology, 9(9):e1003184. find
  45. Noam Sobel, Vivek Prabhakaran, John E Desmond, Gary H Glover, RL Goode, Edith V Sullivan, and John DE Gabrieli. 1998. Sniffing and smelling: separate subsystems in the human olfactory cortex. Nature, 392(6673):282–286. find
  46. Chih-Ying Su, Karen Menuz, and John R Carlson. 2009. Olfactory perception: receptors, cells, and circuits. Cell, 139(1):45–59. find
  47. Farzaneh Taleb, Miguel Vasco, Antonio Ribeiro, Mårten Björkman, and Danica Kragic. 2024. Can transformers smell like humans? Advances in Neural Information Processing Systems, 37:72032–72060. find
  48. The Good Scents Company. 2025. The Good Scents Company Information System. https://www.thegoodscentscompany.com/. Accessed: December 10, 2025. ↗
  49. Benjamin Sanchez-Lengeling, Jennifer N Wei, Brian K Lee, Richard C Gerkin, Alán Aspuru-Guzik, and Alexander B Wiltschko. 2019. Machine learning for scent: Learning generalizable perceptual representations of small molecules. arXiv preprint arXiv:1910.10685. — [arXiv:1910.10685](https://arxiv.org/abs/1910.10685) find
  50. Gary Tom, Cher Tian Ser, Ella M Rajaonson, Stanley Lo, Hyun Suk Park, Brian K Lee, and Benjamin Sanchez-Lengeling. 2025. Does this smell the same? learning representations of olfactory mixtures using inductive biases. Machine Learning: Science and Technology, 6(3):035063. find
  51. Charles S Sell. 2006. On the unpredictability of odor. Angewandte Chemie International Edition, 45(38):6254–6261. find
  52. Hugo Touvron, Piotr Bojanowski, Mathilde Caron, Matthieu Cord, Alaaeldin El-Nouby, Edouard Grave, Gautier Izacard, Armand Joulin, Gabriel Synnaeve, Jakob Verbeek, and others. 2022. Resmlp: Feed-forward networks for image classification with data-efficient training. IEEE transactions on pattern analy… find
  53. Anju Sharma, Rajnish Kumar, Shabnam Ranjta, and Pritish Kumar Varadwaj. 2021. Smiles to smell: decoding the structure–odor relationship of chemical compounds using the deep neural network approach. Journal of Chemical Information and Modeling, 61(2):676–688. find
  54. Anju Sharma, Bishal Kumar Saha, Rajnish Kumar, and Pritish Kumar Varadwaj. 2022. Olfactionbase: a repository to explore odors, odorants, olfactory receptors and odorant–receptor interactions. Nucleic Acids Research, 50(D1):D678–D686. find
  55. Mrityunjay Sharma, Sarabeshwar Balaji, Pinaki Saha, and Ritesh Kumar. 2025. Navigating the fragrance space using graph generative models and predicting odors. Journal of Chemical Information and Modeling, 65(10):4818–4832. find
  56. Daniel Shin, Gao Pei, Priyadarshini Kumari, and Tarek R Besold. 2023. Optimizing learning across multimodal transfer features for modeling olfactory perception. In 29th ACM SIGKDD Cof. on Knowledge Discovery and Data Mining. find
  57. Sigma-Aldrich. 2025. Sigma-Aldrich Website. https://www.sigmaaldrich.com/SG/en. Accessed: December 10, 2025. ↗
  58. Ngoc Tran, Daniel Kepple, Sergey Shuvaev, and Alexei Koulakov. 2019. Deepnose: Using artificial neural networks to represent the space of odorants. In International Conference on Machine Learning, pages 6305–6314. PMLR. find
  59. Yuta Wakutsu and Hiromasa Kaneko. 2025. Molecular odor prediction using olfactory receptor information. Molecular Informatics, 44(3):e202400274. find
  60. Ivonne Wallrabenstein, Jonas Kuklan, Lea Weber, Sandra Zborala, Markus Werner, Janine Altmüller, Christian Becker, Anna Schmidt, Hanns Hatt, Thomas Hummel, and others. 2013. Human trace amine-associated receptor taar5 can be activated by trimethylamine. PloS one, 8(2):e54950. find
  61. David Weininger. 1988. Smiles, a chemical language and information system. 1. introduction to methodology and encoding rules. Journal of chemical information and computer sciences, 28(1):31–36. find
  62. Ruibin Xiong, Yunchang Yang, Di He, Kai Zheng, Shuxin Zheng, Chen Xing, Huishuai Zhang, Yanyan Lan, Liwei Wang, and Tieyan Liu. 2020. On layer normalization in the transformer architecture. In International conference on machine learning, pages 10524–10533. PMLR. find
  63. Zhaoping Xiong, Dingyan Wang, Xiaohong Liu, Feisheng Zhong, Xiaozhe Wan, Xutong Li, Zhaojun Li, Xiaomin Luo, Kaixian Chen, Hualiang Jiang, and others. 2019. Pushing the boundaries of molecular representation for drug discovery with the graph attention mechanism. Journal of medicinal chemistry, 63(16… find
  64. Keyulu Xu, Weihua Hu, Jure Leskovec, and Stefanie Jegelka. 2018. How powerful are graph neural networks? arXiv preprint arXiv:1810.00826.
  65. Keiichi Yoshikawa, Jun Deguchi, Jieying Hu, Hsiu-Yi Lu, and Hiroaki Matsunami. 2022. An odorant receptor that senses four classes of musk compounds. Current Biology, 32(23):5172–5179. find
  66. Xin Yuan, Zhe Lin, Jason Kuen, Jianming Zhang, Yilin Wang, Michael Maire, Ajinkya Kale, and Baldo Fai-eta. 2021. Multimodal contrastive training for visual representation learning. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 6995–7004. find
  67. Shitong Zeng, Lili Zhang, Peng Li, Dandan Pu, Yingjie Fu, Ruiyi Zheng, Hui Xi, Kaina Qiao, Dingzhong Wang, Baoguo Sun, and others. 2023. Molecular mechanisms of caramel-like odorant-olfactory receptor interactions based on a computational chemistry approach. Food Research International, 171:113063. find
  68. Yanzhao Zhang, Mingxin Li, Dingkun Long, Xin Zhang, Huan Lin, Baosong Yang, Pengjun Xie, An Yang, Dayiheng Liu, Junyang Lin, and others. 2025. Qwen3 embedding: Advancing text embedding and reranking through foundation models. arXiv preprint arXiv:2506.05176.
  69. Shu Zhong, Zetao Zhou, Christopher Dawes, Giada Brianz, and Marianna Obrist. 2024. Sniff ai: Is my’spicy’your’spicy’? exploring llm’s perceptual alignment with human smell experiences. arXiv preprint arXiv:2411.06950. — [arXiv:2411.06950](https://arxiv.org/abs/2411.06950) find
  70. Gengmo Zhou, Zhifeng Gao, Qiankun Ding, Hang Zheng, Hongteng Xu, Zhewei Wei, Linfeng Zhang, and Guolin Ke. 2023. Uni-mol: A universal 3d molecular representation learning framework. In The eleventh international conference on learning representations. find
  71. Pan Zhou, Caiming Xiong, Xiaotong Yuan, and Steven Chu Hong Hoi. 2021. A theory-driven self-labeling refinement method for contrastive representation learning. Advances in Neural Information Processing Systems, 34:6183–6197. find

Updated

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/su-2026-nose-neural-olfactory-semantic-embedding/