--- title: "DMSD — paper by Yang et al. (2026) — summary and ideas" description: "The authors argue that this leaves visual sub-concepts entangled and makes predictions vulnerable to co-occurrence bias in… 1 reference." authors: ["Pan Yang", "Jing Yang", "Ruan Xiao li", "Yuling Chen", "Yuankai Wu", "Quan Zhou", "Xu Wang"] year: 2026 venue: "Findings of the Association for Computational Linguistics: ACL 2026" source: "https://aclanthology.org/2026.findings-acl.1540/" doi: "10.18653/v1/2026.findings-acl.1540" licence: "CC BY 4.0 (ACL Anthology)" licence_url: "https://creativecommons.org/licenses/by/4.0/" summary_licence: "Elamur Cosmic License" canonical: "https://research.elamur.ai/free/en/papers/yang-2026-dmsd-dual-modal-semantic-disentanglement/" --- [Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/yang-2026-dmsd-dual-modal-semantic-disentanglement/) [home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2026](https://md.research.elamur.ai/free/en/papers/2026/page/30/) / DMSD: Dual-Modal Semantic Disentanglement for Compositional Zero-Shot Learning # DMSD: Dual-Modal Semantic Disentanglement for Compositional Zero-Shot Learning **Authors:** Pan Yang, [Jing Yang](https://md.research.elamur.ai/free/en/authors/jing-yang/), Ruan Xiao li, Yuling Chen, Yuankai Wu, Quan Zhou and [Xu Wang](https://md.research.elamur.ai/free/en/authors/xu-wang/) · **Year:** 2026 · **Venue:** [Findings of the Association for Computational Linguistics: ACL 2026](https://md.research.elamur.ai/free/en/venues/findings/) ([Findings of the Association for Computational Linguistics 2026](https://md.research.elamur.ai/free/en/venues/findings/2026/)) · **Publisher:** [Association for Computational Linguistics](https://md.research.elamur.ai/free/en/publishers/association-for-computational-linguistics/) · **Licence:** [CC BY 4.0 (ACL Anthology)](https://creativecommons.org/licenses/by/4.0/) **Links:** [Publisher's page](https://aclanthology.org/2026.findings-acl.1540/) · [PDF](https://aclanthology.org/2026.findings-acl.1540.pdf) · [DOI 10.18653/v1/2026.findings-acl.1540](https://doi.org/10.18653/v1/2026.findings-acl.1540) · [OpenAlex](https://openalex.org/W7166828290) **Citations:** 0 citations (OpenAlex, 2026-10-14) ## Summary Compositional Zero-Shot Learning (CZSL) asks a model to recognize attribute–object pairs it never saw in training, such as a "blue banana," by recombining primitives learned from seen pairs. Most CLIP-based approaches (CSP, Troika, LOGICZSL) separate attributes from objects mainly through text-side prompt tuning. The authors argue that this leaves visual sub-concepts entangled and makes predictions vulnerable to co-occurrence bias in language priors. Their framework, DMSD, addresses this from both modalities with three components: - **Contextual Prompt Space:** a shared set of contextual prompts injected into both the image and text encoders. - **Visual Sub-concept Prototypes:** learnable attribute and object prototypes (p_a, p_o) on the visual side. - **Class-Centroid Bridging Module:** a module built on CLIP's text encoder that cross-attends to visual features layer by layer, pulling class centroids toward the textual space. On MIT-States, UT-Zappos and C-GQA, DMSD tops every closed-world metric. It also stays competitive in the harder open-world setting. The work suggests that explicit visual disentanglement complements text-centric prompt learning for compositional generalization. ## Key points - Closed-world AUC is 24.2 on MIT-States, 46.2 on UT-Zappos and 16.6 on C-GQA. These are relative gains of 3.4%, 0.9% and 8.5% over the runner-up. - Open-world AUC is 8.8 on MIT-States, 35.8 on UT-Zappos and 4.0 on C-GQA. DMSD trails LOGICZSL on UT-Zappos but has higher unseen accuracy there, and it beats LOGICZSL on C-GQA. - In the ablation, removing the shared contextual space lowers AUC by about 6.1% (MIT-States) and 3.9% (UT-Zappos) in relative terms. - Using both p_a and p_o, rather than no visual prototypes, improves AUC by 6.6% and 4.5% on the same two datasets. - Code is released at github.com/ybyangjing/DMSD; the paper appears in Findings of ACL 2026. *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 - [Sichuan University](https://md.research.elamur.ai/free/en/universities/sichuan-university/) — University, Chengdu, China · 20 works · 1,293 citations - [Nanjing University of Posts and Telecommunications](https://md.research.elamur.ai/free/en/universities/nanjing-university-of-posts-and-telecommunications/) — University, Nanjing, China · 4 works · 22 citations Also on the byline: [Guizhou University](https://ror.org/02wmsc916). 📚 Shelves (3): [🖥️ Computer Science](https://md.research.elamur.ai/free/en/shelves/computer-science/) · 18,614 works · [🤖 Artificial Intelligence](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · 17,965 works · [👁️ Computer Vision and Pattern Recognition](https://md.research.elamur.ai/free/en/shelves/computer-science/computer-vision-and-pattern-recognition/) · 3,486 works ## Cite Cite as: Pan Yang, Jing Yang, Ruan Xiao li, Yuling Chen, Yuankai Wu, Quan Zhou and Xu Wang. 2026. DMSD: Dual-Modal Semantic Disentanglement for Compositional Zero-Shot Learning. Findings of the Association for Computational Linguistics: ACL 2026. The paper itself, not this page. BibTeX from the library's record of the work. ```bibtex @inproceedings{yang2026dmsd, title = {{DMSD: Dual-Modal Semantic Disentanglement for Compositional Zero-Shot Learning}}, author = {Pan Yang, Jing Yang, Ruan Xiao li, Yuling Chen, Yuankai Wu, Quan Zhou and Xu Wang}, booktitle = {Findings of the Association for Computational Linguistics: ACL 2026}, year = {2026}, doi = {10.18653/v1/2026.findings-acl.1540}, url = {https://doi.org/10.18653/v1/2026.findings-acl.1540} } ``` - [← previous DMN: A Compositional Framework for Jailbreaking Multimodal LLMs with Multi-Image Inputs](https://md.research.elamur.ai/free/en/papers/xu-2026-dmn-compositional-framework-jailbreaking-multimodal/) - [next → DNT at #SMM4H–HeaRD 2026: Leveraging BERT-based Encoders and LLMs for Medical Information Extraction](https://md.research.elamur.ai/free/en/papers/tien-2026-dnt-smm4h-heard-2026-leveraging/) - [↑ back to papers of 2026](https://md.research.elamur.ai/free/en/papers/2026/page/30/) ## References 1 references, 0 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet. 1. Yuval Atzmon, Felix Kreuk, Uri Shalit, and Gal Chechik. 2020. A causal view of compositional zero-shot recognition. In Advances in Neural Information Processing Systems, volume 33, pages 1462–1473. Curran Associates, Inc. \#\# Conclusion [find](https://scholar.google.com/scholar?q=Yuval+Atzmon%2C+Felix+Kreuk%2C+Uri+Shalit%2C+and+Gal+Chechik%2E+2020%2E+A+causal+view+of+compositional+zero%2Dshot+recognition%2E+In+Advances+in+Neural+Information+Processing+Systems%2C+volume+33%2C+pages+1462%E2%80%931473%2E+Cu) *Updated 2 November 2026*