# Neural Concept Binder

arXiv: https://arxiv.org/abs/2406.09949 · HTML: https://mlsanity.com/paper/2406.09949/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- Placed in Multimodal reasoning, one of 17 directions in LLM reasoning.
- Builds on 63 of its 86 references that are in the map.
- First posted on arXiv 14 Jun 2024.

## Placed in

- LLM reasoning / [Multimodal reasoning](https://mlsanity.com/lr/multimodal-reasoning/)

## Builds on (most cited first, 30 of 63)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [Neural Discrete Representation Learning](https://mlsanity.com/paper/1711.00937/) (2017)
- [Axiomatic Attribution for Deep Networks](https://mlsanity.com/paper/1703.01365/) (2017)
- [Categorical Reparameterization with Gumbel-Softmax](https://mlsanity.com/paper/1611.01144/) (2016)
- [CLEVR: A Diagnostic Dataset for Compositional Language and Elementary Visual Reasoning](https://mlsanity.com/paper/1612.06890/) (2016)
- [The Concrete Distribution: A Continuous Relaxation of Discrete Random Variables](https://mlsanity.com/paper/1611.00712/) (2016)
- [Concept Bottleneck Models](https://mlsanity.com/paper/2007.04612/) (2020)
- [An Introduction to Variational Autoencoders](https://mlsanity.com/paper/1906.02691/) (2019)
- [Challenging Common Assumptions in the Unsupervised Learning of Disentangled Representations](https://mlsanity.com/paper/1811.12359/) (2018)
- [Object-Centric Learning with Slot Attention](https://mlsanity.com/paper/2006.15055/) (2020)
- [This Looks Like That: Deep Learning for Interpretable Image Recognition](https://mlsanity.com/paper/1806.10574/) (2018)
- [Towards Robust Interpretability with Self-Explaining Neural Networks](https://mlsanity.com/paper/1806.07538/) (2018)
- [The Neuro-Symbolic Concept Learner: Interpreting Scenes, Words, and Sentences From Natural Supervision](https://mlsanity.com/paper/1904.12584/) (2019)
- [Language in a Bottle: Language Model Guided Concept Bottlenecks for Interpretable Image Classification](https://mlsanity.com/paper/2211.11158/) (2022)
- [Right for the Right Reasons: Training Differentiable Models by Constraining their Explanations](https://mlsanity.com/paper/1703.03717/) (2017)
- [On Completeness-aware Concept-Based Explanations in Deep Neural Networks](https://mlsanity.com/paper/1910.07969/) (2019)
- [Weakly-Supervised Disentanglement Without Compromises](https://mlsanity.com/paper/2002.02886/) (2020)
- [Deep Learning for Case-Based Reasoning through Prototypes: A Neural Network that Explains Its Predictions](https://mlsanity.com/paper/1710.04806/) (2017)
- [On the Binding Problem in Artificial Neural Networks](https://mlsanity.com/paper/2012.05208/) (2020)
- [Measuring abstract reasoning in neural networks](https://mlsanity.com/paper/1807.04225/) (2018)
- [SAVi++: Towards End-to-End Object-Centric Learning from Real-World Videos](https://mlsanity.com/paper/2206.07764/) (2022)
- [Illiterate DALL-E Learns to Compose](https://mlsanity.com/paper/2110.11405/) (2021)
- [Making deep neural networks right for the right scientific reasons by interacting with their explanations](https://mlsanity.com/paper/2001.05371/) (2020)
- [Promises and Pitfalls of Black-Box Concept Learning Models](https://mlsanity.com/paper/2106.13314/) (2021)
- [Probabilistic Concept Bottleneck Models](https://mlsanity.com/paper/2306.01574/) (2023)
- [The Dangers of Post-hoc Interpretability: Unjustified Counterfactual Explanations](https://mlsanity.com/paper/1907.09294/) (2019)
- [Right for the Right Concept: Revising Neuro-Symbolic Concepts by Interacting with their Explanations](https://mlsanity.com/paper/2011.12854/) (2020)
- [Weakly Supervised Disentanglement with Guarantees](https://mlsanity.com/paper/1910.09772/) (2019)
- [Concept Bottleneck Model with Additional Unsupervised Concepts](https://mlsanity.com/paper/2202.01459/) (2022)

## Built on by (most cited first, 14 of 14)

- [Bongard in Wonderland: Visual Puzzles that Still Make AI Go Mad?](https://mlsanity.com/paper/2410.19546/) (2024)
- [BlendRL: A Framework for Merging Symbolic and Neural Policy Learning](https://mlsanity.com/paper/2410.11689/) (2024)
- [Object Centric Concept Bottlenecks](https://mlsanity.com/paper/2505.24492/) (2025)
- [Interpretable end-to-end Neurosymbolic Reinforcement Learning agents](https://mlsanity.com/paper/2410.14371/) (2024)
- [Fodor and Pylyshyn's Legacy: Still No Human-like Systematic Compositionality in Neural Networks](https://mlsanity.com/paper/2506.01820/) (2025)
- [DiCo: Disentangled Concept Representation for Text-to-image Person Re-identification](https://mlsanity.com/paper/2601.10053/) (2026)
- [Rethinking Concept Bottleneck Models: From Pitfalls to Solutions](https://mlsanity.com/paper/2603.05629/) (2026)
- [Reasoning in Neurosymbolic AI](https://mlsanity.com/paper/2505.20313/) (2025)
- [Augmented Vision-Language Models: A Systematic Review](https://mlsanity.com/paper/2507.22933/) (2025)
- [Do Sparse Autoencoders Learn Meaningful Concept Hierarchies?](https://mlsanity.com/paper/2606.22994/) (2026)
- [Leveraging Color Channel Independence for Improved Unsupervised Object Detection](https://mlsanity.com/paper/2412.15150/) (2024)
- [Neural Concept Verifier: Scaling Prover-Verifier Games via Concept Encodings](https://mlsanity.com/paper/2507.07532/) (2025)
- [Mitigating Shortcut Learning via Feature Disentanglement in Medical Imaging: A Benchmark Study](https://mlsanity.com/paper/2602.18502/) (2026)
- [GRAIL: Autonomous Concept Grounding for Neuro-Symbolic Reinforcement Learning](https://mlsanity.com/paper/2604.16871/) (2026)

## Abstract (arXiv)

The challenge in object-based visual reasoning lies in generating concept representations that are both descriptive and distinct. Achieving this in an unsupervised manner requires human users to understand the model's learned concepts and, if necessary, revise incorrect ones. To address this challenge, we introduce the Neural Concept Binder (NCB), a novel framework for deriving both discrete and continuous concept representations, which we refer to as "concept-slot encodings". NCB employs two types of binding: "soft binding", which leverages the recent SysBinder mechanism to obtain object-factor encodings, and subsequent "hard binding", achieved through hierarchical clustering and retrieval-based inference. This enables obtaining expressive, discrete representations from unlabeled images. Moreover, the structured nature of NCB's concept representations allows for intuitive inspection and the straightforward integration of external knowledge, such as human input or insights from other AI models like GPT-4. Additionally, we demonstrate that incorporating the hard binding mechanism preserves model performance while enabling seamless integration into both neural and symbolic modules for complex reasoning tasks. We validate the effectiveness of NCB through evaluations on our newly introduced CLEVR-Sudoku dataset.