Abstract
Vision-language models like CLIP struggle with concept binding despite recognizing individual concepts, but controlled transformer models can learn low-complexity binding functions that generalize better through multiplicative interactions.
Humans easily determine which color belongs to which shape in multi-object scenes, an ability known as concept binding. Vision-language embedding models such as CLIP struggle with binding: they recognize individual concepts but fail to represent which concepts form which objects. Although CLIP behaves like a bag-of-concepts model in cross-modal retrieval, object information is recoverable from its image and text embeddings separately. We study this tension through the binding function, which maps concepts to scene embeddings. We find that scene embeddings decompose additively into object representations, explaining why uni-modal probes can recover object information. However, CLIP's binding function is high-complexity, which likely prevents the image and text encoders from learning a shared binding mechanism that generalizes to unseen concept combinations. We then ask whether this limitation is fundamental. We show that it is not. In controlled transformer models trained from scratch, binding generalization emerges with sufficient data coverage. These models learn low-complexity binding functions characterized by multiplicative interactions between concepts, enabling systematic generalization. Code is publicly available at https://github.com/oshapio/binding-concepts-complexity.
Community
This is an automated message from the Librarian Bot. I found the following papers similar to this paper.
The following papers were recommended by the Semantic Scholar API
- Revisiting Compositionality in Dual-Encoder Vision-Language Models: The Role of Inference (2026)
- Geometry-Aware CLIP Retrieval via Local Cross-Modal Alignment and Steering (2026)
- When Do Diffusion Models learn to Generate Multiple Objects? (2026)
- Supervised Classification Heads as Semantic Prototypes: Unlocking Vision-Language Alignment via Weight Recycling (2026)
- Learning Relative Representations for Fine-Grained Multimodal Alignment with Limited Data (2026)
- Unlocking Compositional Generalization in Continual Few-Shot Learning (2026)
- CrossFlowDG: Bridging the Modality Gap with Cross-modal Flow Matching for Domain Generalization (2026)
Please give a thumbs up to this comment if you found it helpful!
If you want recommendations for any Paper on Hugging Face checkout this Space
You can directly ask Librarian Bot for paper recommendations by tagging it in a comment: @librarian-bot recommend
Get this paper in your agent:
hf papers read 2605.31503 Don't have the latest CLI?
curl -LsSf https://hf.co/cli/install.sh | bash Models citing this paper 0
No model linking this paper
Datasets citing this paper 0
No dataset linking this paper
Spaces citing this paper 0
No Space linking this paper
Collections including this paper 0
No Collection including this paper