Cover Image

VL-SAE: Interpreting and Enhancing Vision-Language Alignment with a Unified Concept Set

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Shen, Shufan, Sun, Junshu, Huang, Qingming, Wang, Shuhui
Format:	Preprint
Published:	2025
Subjects:	Computer Vision and Pattern Recognition Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Kernelized Sparse Fine-Tuning with Bi-level Parameter Competition for Vision Models
by: Shen, Shufan, et al.
Published: (2025)

Enhancing Pre-trained Representation Classifiability can Boost its Interpretability
by: Shen, Shufan, et al.
Published: (2025)

Expanding Sparse Tuning for Low Memory Usage
by: Shen, Shufan, et al.
Published: (2024)

Locate-then-Sparsify: Attribution Guided Sparse Strategy for Visual Hallucination Mitigation
by: Dang, Tiantian, et al.
Published: (2026)

UniVL: Unified Vision-Language Embedding for Spatially Grounded Contextual Image Generation
by: Wang, Jiayun, et al.
Published: (2026)

Unified Vision-Language Modeling via Concept Space Alignment
by: Qiu, Yifu, et al.
Published: (2026)

LUCID-SAE: Learning Unified Vision-Language Sparse Codes for Interpretable Concept Discovery
by: Gu, Difei, et al.
Published: (2026)

Handling Imbalanced Pseudolabels for Vision-Language Models with Concept Alignment and Confusion-Aware Calibrated Margin
by: Wang, Yuchen, et al.
Published: (2025)

Universal Sparse Autoencoders: Interpretable Cross-Model Concept Alignment
by: Thasarathan, Harrish, et al.
Published: (2025)

Unified Lexical Representation for Interpretable Visual-Language Alignment
by: Li, Yifan, et al.
Published: (2024)

CytoSAE: Interpretable Cell Embeddings for Hematology
by: Dasdelen, Muhammed Furkan, et al.
Published: (2025)

ASCENT-ViT: Attention-based Scale-aware Concept Learning Framework for Enhanced Alignment in Vision Transformers
by: Sinha, Sanchit, et al.
Published: (2025)

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

Roboflow100-VL: A Multi-Domain Object Detection Benchmark for Vision-Language Models
by: Robicheaux, Peter, et al.
Published: (2025)

Self-Evolving Visual Concept Library using Vision-Language Critics
by: Sehgal, Atharva, et al.
Published: (2025)

Enhancing Zero-Shot Image Recognition in Vision-Language Models through Human-like Concept Guidance
by: Liu, Hui, et al.
Published: (2025)

UMind-VL: A Generalist Ultrasound Vision-Language Model for Unified Grounded Perception and Comprehensive Interpretation
by: Chen, Dengbo, et al.
Published: (2025)

Ultrasound Vision-Language Alignment via Contrastive Learning
by: Lyu, Zhuoyang, et al.
Published: (2026)

RadAlign: Advancing Radiology Report Generation with Vision-Language Concept Alignment
by: Gu, Difei, et al.
Published: (2025)

IPO: Interpretable Prompt Optimization for Vision-Language Models
by: Du, Yingjun, et al.
Published: (2024)

Interpretable Generative Models through Post-hoc Concept Bottlenecks
by: Kulkarni, Akshay, et al.
Published: (2025)

GrootVL: Tree Topology is All You Need in State Space Model
by: Xiao, Yicheng, et al.
Published: (2024)

Concept-Centric Token Interpretation for Vector-Quantized Generative Models
by: Yang, Tianze, et al.
Published: (2025)

Attention Guided Alignment in Efficient Vision-Language Models
by: Mahajan, Shweta, et al.
Published: (2025)

Improved Alignment of Modalities in Large Vision Language Models
by: Jangra, Kartik, et al.
Published: (2025)

MCPNet: An Interpretable Classifier via Multi-Level Concept Prototypes
by: Wang, Bor-Shiun, et al.
Published: (2024)

Interpreting and Editing Vision-Language Representations to Mitigate Hallucinations
by: Jiang, Nick, et al.
Published: (2024)

Interpreting Neurons in Deep Vision Networks with Language Models
by: Bai, Nicholas, et al.
Published: (2024)

Beyond Scalars: Concept-Based Alignment Analysis in Vision Transformers
by: Vielhaben, Johanna, et al.
Published: (2024)

ICED: Concept-level Machine Unlearning via Interpretable Concept Decomposition
by: Lin, Shen, et al.
Published: (2026)

CrossVL: Complexity-Aware Feature Routing and Paired Curriculum for Cross-View Vision-Language Detection
by: Liu, Zhipeng, et al.
Published: (2026)

SpectralKD: A Unified Framework for Interpreting and Distilling Vision Transformers via Spectral Analysis
by: Tian, Huiyuan, et al.
Published: (2024)

Unified Concept Editing in Diffusion Models
by: Gandikota, Rohit, et al.
Published: (2023)

Enhancing Visual-Language Modality Alignment in Large Vision Language Models via Self-Improvement
by: Wang, Xiyao, et al.
Published: (2024)

VLG-CBM: Training Concept Bottleneck Models with Vision-Language Guidance
by: Srivastava, Divyansh, et al.
Published: (2024)

A Two-Step Concept-Based Approach for Enhanced Interpretability and Trust in Skin Lesion Diagnosis
by: Patrício, Cristiano, et al.
Published: (2024)

Bi-MCQ: Reformulating Vision-Language Alignment for Negation Understanding
by: Kim, Tae Hun, et al.
Published: (2026)

CASL: Concept-Aligned Sparse Latents for Interpreting Diffusion Models
by: He, Zhenghao, et al.
Published: (2026)

From Segments to Concepts: Interpretable Image Classification via Concept-Guided Segmentation
by: Eisenberg, Ran, et al.
Published: (2025)

Towards Interpreting Visual Information Processing in Vision-Language Models
by: Neo, Clement, et al.
Published: (2024)