{"ID":2895580,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2507.08334","arxiv_id":"2507.08334","title":"CoBELa: Steering Transparent Generation via Concept Bottlenecks on Energy Landscapes","abstract":"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.","short_abstract":"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, w...","url_abs":"https://arxiv.org/abs/2507.08334","url_pdf":"https://arxiv.org/pdf/2507.08334v3","authors":"[\"Sangwon Kim\",\"Kyoungoh Lee\",\"Jeyoun Dong\",\"Kwang-Ju Kim\"]","published":"2025-07-11T06:27:11Z","proceeding":"cs.CV","tasks":"[\"cs.CV\",\"cs.AI\"]","methods":"[\"Diffusion Model\"]","has_code":false}