Copertina

CoE: Chain-of-Explanation via Automatic Visual Concept Circuit Description and Polysemanticity Quantification

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Yu, Wenlong, Wang, Qilong, Liu, Chuang, Li, Dong, Hu, Qinghua
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Computer Vision and Pattern Recognition Artificial Intelligence
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Fine-Grained Domain Generalization with Feature Structuralization
di: Yu, Wenlong, et al.
Pubblicazione: (2024)

PURE: Turning Polysemantic Neurons Into Pure Features by Identifying Relevant Circuits
di: Dreyer, Maximilian, et al.
Pubblicazione: (2024)

Fine-Grained Generalization via Structuralizing Concept and Feature Space into Commonality, Specificity and Confounding
di: Wang, Zhen, et al.
Pubblicazione: (2026)

Video-CoE: Reinforcing Video Event Prediction via Chain of Events
di: Su, Qile, et al.
Pubblicazione: (2026)

Automatic Discovery of Visual Circuits
di: Rajaram, Achyuta, et al.
Pubblicazione: (2024)

RGBX-R1: Visual Modality Chain-of-Thought Guided Reinforcement Learning for Multimodal Grounding
di: Wu, Jiahe, et al.
Pubblicazione: (2026)

A$^2$M$^2$-Net: Adaptively Aligned Multi-Scale Moment for Few-Shot Action Recognition
di: Gao, Zilin, et al.
Pubblicazione: (2025)

CoE: Deep Coupled Embedding for Non-Rigid Point Cloud Correspondences
di: Zeng, Huajian, et al.
Pubblicazione: (2024)

Constrained Prompt Enhancement for Improving Zero-Shot Generalization of Vision-Language Models
di: Yin, Xiaojie, et al.
Pubblicazione: (2025)

Granular Concept Circuits: Toward a Fine-Grained Circuit Discovery for Concept Representations
di: Kwon, Dahee, et al.
Pubblicazione: (2025)

Unsupervised Interpretable Basis Extraction for Concept-Based Visual Explanations
di: Doumanoglou, Alexandros, et al.
Pubblicazione: (2023)

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

MCA-RG: Enhancing LLMs with Medical Concept Alignment for Radiology Report Generation
di: Xing, Qilong, et al.
Pubblicazione: (2025)

CoBELa: Steering Transparent Generation via Concept Bottlenecks on Energy Landscapes
di: Kim, Sangwon, et al.
Pubblicazione: (2025)

Text Guided Image Editing with Automatic Concept Locating and Forgetting
di: Li, Jia, et al.
Pubblicazione: (2024)

ConceptScope: Characterizing Dataset Bias via Disentangled Visual Concepts
di: Choi, Jinho, et al.
Pubblicazione: (2025)

FACE: Faithful Automatic Concept Extraction
di: Bhusal, Dipkamal, et al.
Pubblicazione: (2025)

Looking into Concept Explanation Methods for Diabetic Retinopathy Classification
di: Storås, Andrea M., et al.
Pubblicazione: (2024)

V-CECE: Visual Counterfactual Explanations via Conceptual Edits
di: Spanos, Nikolaos, et al.
Pubblicazione: (2025)

Disentangling Polysemantic Neurons with a Null-Calibrated Polysemanticity Index and Causal Patch Interventions
di: Gupta, Manan, et al.
Pubblicazione: (2025)

Helping CLIP See Both the Forest and the Trees: A Decomposition and Description Approach
di: Xue, Leyan, et al.
Pubblicazione: (2025)

ClinCoT: Clinical-Aware Visual Chain-of-Thought for Medical Vision Language Models
di: Liu, Xiwei, et al.
Pubblicazione: (2026)

MM-CoT:A Benchmark for Probing Visual Chain-of-Thought Reasoning in Multimodal Models
di: Zhang, Jusheng, et al.
Pubblicazione: (2025)

CoGR-MoE: Concept-Guided Expert Routing with Consistent Selection and Flexible Reasoning for Visual Question Answering
di: Zeng, Xiyin, et al.
Pubblicazione: (2026)

$S^3$: Synonymous Semantic Space for Improving Zero-Shot Generalization of Vision-Language Models
di: Yin, Xiaojie, et al.
Pubblicazione: (2024)

Euclid: Supercharging Multimodal LLMs with Synthetic High-Fidelity Visual Descriptions
di: Zhang, Jiarui, et al.
Pubblicazione: (2024)

On The Coherence of Quantitative Evaluation of Visual Explanations
di: Vandersmissen, Benjamin, et al.
Pubblicazione: (2023)

CoRGI: Verified Chain-of-Thought Reasoning with Post-hoc Visual Grounding
di: Yi, Shixin, et al.
Pubblicazione: (2025)

Doc-CoB: Enhancing Document Understanding with Visual Chain-of-Boxes Reasoning
di: Mo, Ye, et al.
Pubblicazione: (2025)

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

ImgCoT: Compressing Long Chain of Thought into Compact Visual Tokens for Efficient Reasoning of Large Language Model
di: Chen, Xiaoshu, et al.
Pubblicazione: (2026)

Statistically Significant Concept-based Explanation of Image Classifiers via Model Knockoffs
di: Xu, Kaiwen, et al.
Pubblicazione: (2023)

Measuring the (Un)Faithfulness of Concept-Based Explanations
di: Kumar, Shubham, et al.
Pubblicazione: (2025)

CoCo-SAM3: Harnessing Concept Conflict in Open-Vocabulary Semantic Segmentation
di: Chen, Yanhui, et al.
Pubblicazione: (2026)

Finer-CAM: Spotting the Difference Reveals Finer Details for Visual Explanation
di: Zhang, Ziheng, et al.
Pubblicazione: (2025)

Contrastive Pretraining for Visual Concept Explanations of Socioeconomic Outcomes
di: Obadic, Ivica, et al.
Pubblicazione: (2024)

All in One: Visual-Description-Guided Unified Point Cloud Segmentation
di: Han, Zongyan, et al.
Pubblicazione: (2025)

Enhancing Skin Disease Diagnosis: Interpretable Visual Concept Discovery with SAM
di: Hu, Xin, et al.
Pubblicazione: (2024)

Diversity Over Frequency: Rethinking Tool Use in Visual Chain-of-Thought Agents
di: Kim, Dong-Hee, et al.
Pubblicazione: (2026)

LLaVA-VSD: Large Language-and-Vision Assistant for Visual Spatial Description
di: Jin, Yizhang, et al.
Pubblicazione: (2024)