# From Model Patterns to Abstract Semantics in Compositional Zero-Shot Learning

arXiv: https://arxiv.org/abs/2609.15649 · HTML: https://mlsanity.com/paper/2609.15649/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 10 of its 16 references that are in the map.
- First posted on arXiv 14 Sep 2026.

## Builds on (most cited first, 10 of 10)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Document Ranking with a Pretrained Sequence-to-Sequence Model](https://mlsanity.com/paper/2003.06713/) (2020)
- [Learning Graph Embeddings for Compositional Zero-shot Learning](https://mlsanity.com/paper/2102.01987/) (2021)
- [Troika: Multi-Path Cross-Modal Traction for Compositional Zero-Shot Learning](https://mlsanity.com/paper/2303.15230/) (2023)
- [Prompting Language-Informed Distribution for Compositional Zero-Shot Learning](https://mlsanity.com/paper/2305.14428/) (2023)
- [Context-based and Diversity-driven Specificity in Compositional Zero-Shot Learning](https://mlsanity.com/paper/2402.17251/) (2024)
- [Leveraging Passage Embeddings for Efficient Listwise Reranking with Large Language Models](https://mlsanity.com/paper/2406.14848/) (2024)
- [Learning Clustering-based Prototypes for Compositional Zero-shot Learning](https://mlsanity.com/paper/2502.06501/) (2025)
- [Learning Visual Proxy for Compositional Zero-Shot Learning](https://mlsanity.com/paper/2501.13859/) (2025)
- [A Conditional Probability Framework for Compositional Zero-shot Learning](https://mlsanity.com/paper/2507.17377/) (2025)

## Abstract (arXiv)

Compositional Zero Shot Learning aims to recognize unseen compositions by recombining learned primitives. Recent methods rely on vision language models and attempt to explicitly model contextual variations of primitives through multiple representations. However, such approaches are limited by fixed variant capacity and competition between abstract and concrete semantics. In this work, we present a new perspective that views primitive variations as the context-driven activation of concrete visual cues rather than independent entities. Based on it, we propose CLEAR, a CLoze-style rEAsoning-based Re-ranking framework inspired by human perceptual processes. CLEAR extracts conditional variants from the primitive candidate set in a coarse-to-fine manner, performs cloze-style reasoning to infer high-level semantics, and re-ranks predictions to correct biases toward salient concrete primitives. Extensive experiments demonstrate that CLEAR consistently improves the Base Model and outperforms state-of-the-art methods on the challenging C-GQA and MIT-States datasets. Code is available at https://github.com/buptLwz/CLEAR.