# CoBELa: Steering Transparent Generation via Concept Bottlenecks on Energy Landscapes

arXiv: https://arxiv.org/abs/2507.08334 · HTML: https://mlsanity.com/paper/2507.08334/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 24 of its 33 references that are in the map.
- First posted on arXiv 11 Jul 2025.

## Builds on (most cited first, 24 of 24)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [Denoising Diffusion Implicit Models](https://mlsanity.com/paper/2010.02502/) (2020)
- [Score-Based Generative Modeling through Stochastic Differential Equations](https://mlsanity.com/paper/2011.13456/) (2020)
- [Diffusion Models Beat GANs on Image Synthesis](https://mlsanity.com/paper/2105.05233/) (2021)
- [Classifier-Free Diffusion Guidance](https://mlsanity.com/paper/2207.12598/) (2022)
- [Improved Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2102.09672/) (2021)
- [Analyzing and Improving the Image Quality of StyleGAN](https://mlsanity.com/paper/1912.04958/) (2019)
- [Progressive Growing of GANs for Improved Quality, Stability, and Variation](https://mlsanity.com/paper/1710.10196/) (2017)
- [FiLM: Visual Reasoning with a General Conditioning Layer](https://mlsanity.com/paper/1709.07871/) (2017)
- [Concept Bottleneck Models](https://mlsanity.com/paper/2007.04612/) (2020)
- [Interpreting the Latent Space of GANs for Semantic Face Editing](https://mlsanity.com/paper/1907.10786/) (2019)
- [GANSpace: Discovering Interpretable GAN Controls](https://mlsanity.com/paper/2004.02546/) (2020)
- [Diffusion Models for Adversarial Purification](https://mlsanity.com/paper/2205.07460/) (2022)
- [Your Classifier is Secretly an Energy Based Model and You Should Treat it Like One](https://mlsanity.com/paper/1912.03263/) (2019)
- [Unsupervised Discovery of Interpretable Directions in the GAN Latent Space](https://mlsanity.com/paper/2002.03754/) (2020)
- [Understanding the Role of Individual Units in a Deep Neural Network](https://mlsanity.com/paper/2009.05041/) (2020)
- [Projected GANs Converge Faster](https://mlsanity.com/paper/2111.01007/) (2021)
- [GANalyze: Toward Visual Definitions of Cognitive Image Properties](https://mlsanity.com/paper/1906.10112/) (2019)
- [Navigating the GAN Parameter Space for Semantic Image Editing](https://mlsanity.com/paper/2011.13786/) (2020)
- [Energy-Based Concept Bottleneck Models: Unifying Prediction, Concept Intervention, and Probabilistic Interpretations](https://mlsanity.com/paper/2401.14142/) (2024)
- [Interpretable Generative Models through Post-hoc Concept Bottlenecks](https://mlsanity.com/paper/2503.19377/) (2025)
- [EQ-CBM: A Probabilistic Concept Bottleneck with Energy-based Models and Quantized Vectors](https://mlsanity.com/paper/2409.14630/) (2024)

## Abstract (arXiv)

Generative concept bottleneck models aim to enable interpretable generation by routing synthesis through explicit, user-facing concepts. In practice, prior approaches often rely on non-explicit bottleneck representations (e.g., vision cues or opaque concept embeddings) or black-box decoders to preserve image quality, which weakens the transparency. We propose CoBELa (Concept Bottlenecks on Energy Landscapes), a decoder-free, energy-based framework that eliminates non-explicit bottleneck representations by conditioning generation entirely through per-concept energy functions over the latent space of a frozen pretrained generator-requiring no generator retraining and enabling post-hoc interpretation. Because these concept energies compose additively, CoBELa naturally supports compositional concept interventions: concept conjunction and negation are realized by summing or subtracting per-concept energy terms without additional training. A diffusion-scheduled energy guidance scheme further replaces expensive MCMC chains with more stable, scheduled denoising for efficient concept-steered sampling. Experiments on CelebA-HQ and CUB-200-2011 demonstrate improvements over prior concept bottleneck generative models, achieving 75.70%/82.42% concept accuracy and 6.47/5.37 FID, respectively, while enabling reliable multi-concept interventions.