# Does Object Binding Naturally Emerge in Large Pretrained Vision Transformers?

arXiv: https://arxiv.org/abs/2510.24709 · HTML: https://mlsanity.com/paper/2510.24709/

## Key facts

- Cited by 19 papers in the map (data through 14 Oct 2026).
- Builds on 35 of its 68 references that are in the map.
- First posted on arXiv 28 Oct 2025.

## Builds on (most cited first, 30 of 35)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [Emerging Properties in Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.14294/) (2021)
- [SAM 2: Segment Anything in Images and Videos](https://mlsanity.com/paper/2408.00714/) (2024)
- [DINOv3](https://mlsanity.com/paper/2508.10104/) (2025)
- [Understanding intermediate layers using linear classifier probes](https://mlsanity.com/paper/1610.01644/) (2016)
- [Object-Centric Learning with Slot Attention](https://mlsanity.com/paper/2006.15055/) (2020)
- [The Linear Representation Hypothesis and the Geometry of Large Language Models](https://mlsanity.com/paper/2311.03658/) (2023)
- [Dynamic Routing Between Capsules](https://mlsanity.com/paper/1710.09829/) (2017)
- [MONet: Unsupervised Scene Decomposition and Representation](https://mlsanity.com/paper/1901.11390/) (2019)
- [Multi-Object Representation Learning with Iterative Variational Inference](https://mlsanity.com/paper/1903.00450/) (2019)
- [Deep ViT Features as Dense Visual Descriptors](https://mlsanity.com/paper/2112.05814/) (2021)
- [Conditional Object-Centric Learning from Video](https://mlsanity.com/paper/2111.12594/) (2021)
- [On the Binding Problem in Artificial Neural Networks](https://mlsanity.com/paper/2012.05208/) (2020)
- [Bridging the Gap to Real-World Object-Centric Learning](https://mlsanity.com/paper/2209.14860/) (2022)
- [Simple Unsupervised Object-Centric Learning for Complex and Naturalistic Videos](https://mlsanity.com/paper/2205.14065/) (2022)
- [TokenCut: Segmenting Objects in Images and Videos with Self-supervised Transformer and Normalized Cut](https://mlsanity.com/paper/2209.00383/) (2022)
- [How do Language Models Bind Entities in Context?](https://mlsanity.com/paper/2310.17191/) (2023)
- [Object-Centric Slot Diffusion](https://mlsanity.com/paper/2303.10834/) (2023)
- [Understanding the Limits of Vision Language Models Through the Lens of the Binding Problem](https://mlsanity.com/paper/2411.00238/) (2024)
- [Token Merging for Training-Free Semantic Binding in Text-to-Image Synthesis](https://mlsanity.com/paper/2411.07132/) (2024)
- [Capturing the objects of vision with neural networks](https://mlsanity.com/paper/2109.03351/) (2021)
- [MOVE: Unsupervised Movable Object Segmentation and Detection](https://mlsanity.com/paper/2210.07920/) (2022)
- [Going in circles is the way forward: the role of recurrence in visual inference](https://mlsanity.com/paper/2003.12128/) (2020)
- [Self-attention in Vision Transformers Performs Perceptual Grouping, Not Attention](https://mlsanity.com/paper/2303.01542/) (2023)
- [Learning to Compose: Improving Object Centric Learning by Injecting Compositionality](https://mlsanity.com/paper/2405.00646/) (2024)
- [Is the Reversal Curse a Binding Problem? Uncovering Limitations of Transformers from a Basic Generalization Failure](https://mlsanity.com/paper/2504.01928/) (2025)
- [Are We Done with Object-Centric Learning?](https://mlsanity.com/paper/2504.07092/) (2025)

## Built on by (most cited first, 19 of 19)

- [Decomposing Query-Key Feature Interactions Using Contrastive Covariances](https://mlsanity.com/paper/2602.04752/) (2026)
- [Counting Circuits: Mechanistic Interpretability of Visual Reasoning in Large Vision-Language Models](https://mlsanity.com/paper/2603.18523/) (2026)
- [Human-like Object Grouping in Self-supervised Vision Transformers](https://mlsanity.com/paper/2603.13994/) (2026)
- [Embedding-Aware Feature Discovery: Bridging Latent Representations and Interpretable Features in Event Sequences](https://mlsanity.com/paper/2603.15713/) (2026)
- [I Walk the Line: Examining the Role of Gestalt Continuity in Object Binding for Vision Transformers](https://mlsanity.com/paper/2604.09942/) (2026)
- [Rethinking Temporal Consistency in Video Object-Centric Learning: From Prediction to Correspondence](https://mlsanity.com/paper/2605.03650/) (2026)
- [Uncovering and Shaping the Latent Representation of 3D Scene Topology in Vision-Language Models](https://mlsanity.com/paper/2605.07148/) (2026)
- [Generating metamers of human scene understanding](https://mlsanity.com/paper/2601.11675/) (2026)
- [Logit Distance Bounds Representational Similarity](https://mlsanity.com/paper/2602.15438/) (2026)
- [Capability neq Interpretability: Human Interpretability of Vision Foundation Models](https://mlsanity.com/paper/2605.20337/) (2026)
- [Unsupervised Semantic Segmentation Facilitates Model Understanding](https://mlsanity.com/paper/2605.29691/) (2026)
- [How can embedding models bind concepts?](https://mlsanity.com/paper/2605.31503/) (2026)
- [Formalizing the Binding Problem](https://mlsanity.com/paper/2606.03976/) (2026)
- [Intermediate Text Representation Guided Text-to-Image Generation for Enhancing One-and-Only Alignment](https://mlsanity.com/paper/2606.30262/) (2026)
- [Mask-supervised Object-centric Representation Learning with LeJEPA](https://mlsanity.com/paper/2607.02404/) (2026)
- [Vision Transformers Learn Gestalt-Like Figure-Ground Cues from Natural Images](https://mlsanity.com/paper/2607.08932/) (2026)
- [Self-supervised Automatic Matting](https://mlsanity.com/paper/2607.10395/) (2026)
- [Linguistic Context Recodes Visual Representations in Vision-Language Models](https://mlsanity.com/paper/2608.00035/) (2026)
- [Emergent Object Binding Has a Finite Spatial Horizon](https://mlsanity.com/paper/2610.00006/) (2026)

## Abstract (arXiv)

Object binding, the brain's ability to bind the many features that collectively represent an object into a coherent whole, is central to human cognition. It groups low-level perceptual features into high-level object representations, stores those objects efficiently and compositionally in memory, and supports human reasoning about individual object instances. While prior work often imposes object-centric attention (e.g., Slot Attention) explicitly to probe these benefits, it remains unclear whether this ability naturally emerges in pre-trained Vision Transformers (ViTs). Intuitively, they could: recognizing which patches belong to the same object should be useful for downstream prediction and thus guide attention. Motivated by the quadratic nature of self-attention, we hypothesize that ViTs represent whether two patches belong to the same object, a property we term IsSameObject. We decode IsSameObject from patch embeddings across ViT layers using a quadratic similarity probe, which reaches over 90% accuracy. Crucially, this object-binding capability emerges reliably in DINO, CLIP, and ImageNet-supervised ViTs, but is markedly weaker in MAE, suggesting that binding is not a trivial architectural artifact, but an ability acquired through specific pretraining objectives. We further discover that IsSameObject is encoded in a low-dimensional subspace on top of object features, and that this signal actively guides attention. Ablating IsSameObject from model activations degrades downstream performance and works against the learning objective, implying that emergent object binding naturally serves the pretraining objective. Our findings challenge the view that ViTs lack object binding and highlight how symbolic knowledge of "which parts belong together" emerges naturally in a connectionist system.