Cover Image

CoBELa: Steering Transparent Generation via Concept Bottlenecks on Energy Landscapes

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Kim, Sangwon, Lee, Kyoungoh, Dong, Jeyoun, Kim, Kwang-Ju
Format:	Preprint
Published:	2025
Subjects:	Computer Vision and Pattern Recognition Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

EQ-CBM: A Probabilistic Concept Bottleneck with Energy-based Models and Quantized Vectors
by: Kim, Sangwon, et al.
Published: (2024)

Scene Graph Generation Strategy with Co-occurrence Knowledge and Learnable Term Frequency
by: Kim, Hyeongjin, et al.
Published: (2024)

Improving Intervention Efficacy via Concept Realignment in Concept Bottleneck Models
by: Singhi, Nishad, et al.
Published: (2024)

Explainable Visual Anomaly Detection via Concept Bottleneck Models
by: Stropeni, Arianna, et al.
Published: (2025)

FlipConcept: Tuning-Free Multi-Concept Personalization for Text-to-Image Generation
by: Woo, Young Beom, et al.
Published: (2025)

Reflexive Guidance: Improving OoDD in Vision-Language Models via Self-Guided Image-Adaptive Concept Generation
by: Kim, Jihyo, et al.
Published: (2024)

Identity Decoupling for Multi-Subject Personalization of Text-to-Image Models
by: Jang, Sangwon, et al.
Published: (2024)

Mosaic: Compositional Multi-Concept Erasure via Vector Field Blending
by: Ko, Junseok, et al.
Published: (2026)

Localized Concept Erasure in Text-to-Image Diffusion Models via High-Level Representation Misdirection
by: Lee, Uichan, et al.
Published: (2026)

Energy-Based Concept Bottleneck Models: Unifying Prediction, Concept Intervention, and Probabilistic Interpretations
by: Xu, Xinyue, et al.
Published: (2024)

Uncertainty-Aware Concept Bottleneck Models with Enhanced Interpretability
by: Zhang, Haifei, et al.
Published: (2025)

Hierarchical, Interpretable, Label-Free Concept Bottleneck Model
by: Xie, Haodong, et al.
Published: (2026)

Physically Guided Visual Mass Estimation from a Single RGB Image
by: Lee, Sungjae, et al.
Published: (2026)

Extreme Blind Image Restoration via Prompt-Conditioned Information Bottleneck
by: Kim, Hongeun, et al.
Published: (2025)

Discover-then-Name: Task-Agnostic Concept Bottlenecks via Automated Concept Discovery
by: Rao, Sukrut, et al.
Published: (2024)

Concept Complement Bottleneck Model for Interpretable Medical Image Diagnosis
by: Wang, Hongmei, et al.
Published: (2024)

Editable Concept Bottleneck Models
by: Hu, Lijie, et al.
Published: (2024)

CrimEdit: Controllable Editing for Counterfactual Object Removal, Insertion, and Movement
by: Jeon, Boseong, et al.
Published: (2025)

FIQ: Fundamental Question Generation with the Integration of Question Embeddings for Video Question Answering
by: Oh, Ju-Young, et al.
Published: (2025)

Frame Guidance: Training-Free Guidance for Frame-Level Control in Video Diffusion Models
by: Jang, Sangwon, et al.
Published: (2025)

Zero-shot Concept Bottleneck Models
by: Yamaguchi, Shin'ya, et al.
Published: (2025)

Process-Guided Concept Bottleneck Model
by: Asiyabi, Reza M., et al.
Published: (2026)

Semi-supervised Concept Bottleneck Models
by: Hu, Lijie, et al.
Published: (2024)

Local Representative Token Guided Merging for Text-to-Image Generation
by: Lee, Min-Jeong, et al.
Published: (2025)

CoE: Chain-of-Explanation via Automatic Visual Concept Circuit Description and Polysemanticity Quantification
by: Yu, Wenlong, et al.
Published: (2025)

SAIL: Similarity-Aware Guidance and Inter-Caption Augmentation-based Learning for Weakly-Supervised Dense Video Captioning
by: Kim, Ye-Chan, et al.
Published: (2026)

VG-CoT: Towards Trustworthy Visual Reasoning via Grounded Chain-of-Thought
by: Lim, Byeonggeuk, et al.
Published: (2026)

Anomaly as Non-Conformity via Training-Free Graph Laplacian Energy Minimization
by: Seo, Jungwook, et al.
Published: (2026)

Concept Unlearning via Cross-Attention Activation Projection for Diffusion Models
by: Moon, Saemi, et al.
Published: (2026)

Scene Graph-Guided Proactive Replanning for Failure-Resilient Embodied Agent
by: Yu, Che Rin, et al.
Published: (2025)

Safety Alignment Backfires: Preventing the Re-emergence of Suppressed Concepts in Fine-tuned Text-to-Image Diffusion Models
by: Kim, Sanghyun, et al.
Published: (2024)

Class-Continuous Conditional Generative Neural Radiance Field
by: Kim, Jiwook, et al.
Published: (2023)

A Comprehensive Survey on Concept Erasure in Text-to-Image Diffusion Models
by: Kim, Changhoon, et al.
Published: (2025)

PSA-VLM: Enhancing Vision-Language Model Safety through Progressive Concept-Bottleneck-Driven Alignment
by: Liu, Zhendong, et al.
Published: (2024)

TraSCE: Trajectory Steering for Concept Erasure
by: Jain, Anubhav, et al.
Published: (2024)

MedSteer: Counterfactual Endoscopic Synthesis via Training-Free Activation Steering
by: Pham, Trong-Thang, et al.
Published: (2026)

How Blind and Low-Vision Individuals Prefer Large Vision-Language Model-Generated Scene Descriptions
by: An, Na Min, et al.
Published: (2025)

MVP-CBM:Multi-layer Visual Preference-enhanced Concept Bottleneck Model for Explainable Medical Image Classification
by: Wang, Chunjiang, et al.
Published: (2025)

Adaptive Concept Bottleneck for Foundation Models Under Distribution Shifts
by: Choi, Jihye, et al.
Published: (2024)

MemoryTalker: Personalized Speech-Driven 3D Facial Animation via Audio-Guided Stylization
by: Kim, Hyung Kyu, et al.
Published: (2025)