Image de couverture de livre

Concept-Centric Token Interpretation for Vector-Quantized Generative Models

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Yang, Tianze, Shi, Yucheng, Du, Mengnan, Wu, Xuansheng, Tan, Qiaoyu, Sun, Jin, Liu, Ninghao
Format:	Preprint
Publié:	2025
Sujets:	Computer Vision and Pattern Recognition Machine Learning
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Self-Improving Small Object Grounding in LVLMs
par: Yang, Tianze, et autres
Publié: (2026)

Common Inpainted Objects In-N-Out of Context
par: Yang, Tianze, et autres
Publié: (2025)

Enhancing Cognition and Explainability of Multimodal Foundation Models with Self-Synthesized Data
par: Shi, Yucheng, et autres
Publié: (2025)

Vector-Quantized Vision Foundation Models for Object-Centric Learning
par: Zhao, Rongzhen, et autres
Publié: (2025)

Denoising Concept Vectors with Sparse Autoencoders for Improved Language Model Steering
par: Zhao, Haiyan, et autres
Publié: (2025)

LMOD: A Large Multimodal Ophthalmology Dataset and Benchmark for Large Vision-Language Models
par: Qin, Zhenyue, et autres
Publié: (2024)

Moment Quantization for Video Temporal Grounding
par: Sun, Xiaolong, et autres
Publié: (2025)

VQ-Seg: Vector-Quantized Token Perturbation for Semi-Supervised Medical Image Segmentation
par: Yang, Sicheng, et autres
Publié: (2026)

VQ-VLA: Improving Vision-Language-Action Models via Scaling Vector-Quantized Action Tokenizers
par: Wang, Yating, et autres
Publié: (2025)

Mario: Multimodal Graph Reasoning with Large Language Models
par: Sun, Yuanfu, et autres
Publié: (2026)

IC-Mapper: Instance-Centric Spatio-Temporal Modeling for Online Vectorized Map Construction
par: Zhu, Jiangtong, et autres
Publié: (2025)

Does Vector Quantization Fail in Spatio-Temporal Forecasting? Exploring a Differentiable Sparse Soft-Vector Quantization Approach
par: Chen, Chao, et autres
Publié: (2023)

OUSAC: Optimized Guidance Scheduling with Adaptive Caching for DiT Acceleration
par: Sun, Ruitong, et autres
Publié: (2025)

Retrieval-enhanced Knowledge Editing in Language Models for Multi-Hop Question Answering
par: Shi, Yucheng, et autres
Publié: (2024)

SVGen: Interpretable Vector Graphics Generation with Large Language Models
par: Wang, Feiyu, et autres
Publié: (2025)

LottieGPT: Tokenizing Vector Animation for Autoregressive Generation
par: Chen, Junhao, et autres
Publié: (2026)

Autoregressive Video Generation without Vector Quantization
par: Deng, Haoge, et autres
Publié: (2024)

Autoregressive Image Generation without Vector Quantization
par: Li, Tianhong, et autres
Publié: (2024)

EQ-CBM: A Probabilistic Concept Bottleneck with Energy-based Models and Quantized Vectors
par: Kim, Sangwon, et autres
Publié: (2024)

Improving Interpretation Faithfulness for Vision Transformers
par: Hu, Lijie, et autres
Publié: (2023)

Inlier-Centric Post-Training Quantization for Object Detection Models
par: Kim, Minsu, et autres
Publié: (2026)

Interpretable Generative Models through Post-hoc Concept Bottlenecks
par: Kulkarni, Akshay, et autres
Publié: (2025)

Towards Joint Quantization and Token Pruning of Vision-Language Models
par: Li, Xinqing, et autres
Publié: (2026)

GCAV: A Global Concept Activation Vector Framework for Cross-Layer Consistency in Interpretability
par: He, Zhenghao, et autres
Publié: (2025)

From Weights to Concepts: Data-Free Interpretability of CLIP via Singular Vector Decomposition
par: Gentile, Francesco, et autres
Publié: (2026)

Scalable Image Tokenization with Index Backpropagation Quantization
par: Shi, Fengyuan, et autres
Publié: (2024)

OmniLottie: Generating Vector Animations via Parameterized Lottie Tokens
par: Yang, Yiying, et autres
Publié: (2026)

A Creative Agent is Worth a 64-Token Template
par: Shi, Ruixiao, et autres
Publié: (2026)

SoFlow: Solution Flow Models for One-Step Generative Modeling
par: Luo, Tianze, et autres
Publié: (2025)

Decomposed Vector-Quantized Variational Autoencoder for Human Grasp Generation
par: Zhao, Zhe, et autres
Publié: (2024)

VQ-Map: Bird's-Eye-View Map Layout Estimation in Tokenized Discrete Space via Vector Quantization
par: Zhang, Yiwei, et autres
Publié: (2024)

Non-confusing Generation of Customized Concepts in Diffusion Models
par: Lin, Wang, et autres
Publié: (2024)

Differential Vector Erasure: Unified Training-Free Concept Erasure for Flow Matching Models
par: Zhang, Zhiqi, et autres
Publié: (2026)

Interpretable Zero-shot Learning with Infinite Class Concepts
par: Ye, Zihan, et autres
Publié: (2025)

Separable Multi-Concept Erasure from Diffusion Models
par: Zhao, Mengnan, et autres
Publié: (2024)

Beyond Artifacts: Real-Centric Envelope Modeling for Reliable AI-Generated Image Detection
par: Liu, Ruiqi, et autres
Publié: (2025)

UniCTokens: Boosting Personalized Understanding and Generation via Unified Concept Tokens
par: An, Ruichuan, et autres
Publié: (2025)

LayoutRAG: Retrieval-Augmented Model for Content-agnostic Conditional Layout Generation
par: Wu, Yuxuan, et autres
Publié: (2025)

Channel-wise Vector Quantization
par: Song, Wei, et autres
Publié: (2026)

Differentiable Vector Quantization for Rate-Distortion Optimization of Generative Image Compression
par: Jiang, Shiyin, et autres
Publié: (2026)