Cover Image

Concept-Centric Token Interpretation for Vector-Quantized Generative Models

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Yang, Tianze, Shi, Yucheng, Du, Mengnan, Wu, Xuansheng, Tan, Qiaoyu, Sun, Jin, Liu, Ninghao
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

Self-Improving Small Object Grounding in LVLMs
by: Yang, Tianze, et al.
Published: (2026)

Common Inpainted Objects In-N-Out of Context
by: Yang, Tianze, et al.
Published: (2025)

Enhancing Cognition and Explainability of Multimodal Foundation Models with Self-Synthesized Data
by: Shi, Yucheng, et al.
Published: (2025)

Vector-Quantized Vision Foundation Models for Object-Centric Learning
by: Zhao, Rongzhen, et al.
Published: (2025)

Denoising Concept Vectors with Sparse Autoencoders for Improved Language Model Steering
by: Zhao, Haiyan, et al.
Published: (2025)

LMOD: A Large Multimodal Ophthalmology Dataset and Benchmark for Large Vision-Language Models
by: Qin, Zhenyue, et al.
Published: (2024)

Moment Quantization for Video Temporal Grounding
by: Sun, Xiaolong, et al.
Published: (2025)

VQ-Seg: Vector-Quantized Token Perturbation for Semi-Supervised Medical Image Segmentation
by: Yang, Sicheng, et al.
Published: (2026)

VQ-VLA: Improving Vision-Language-Action Models via Scaling Vector-Quantized Action Tokenizers
by: Wang, Yating, et al.
Published: (2025)

Mario: Multimodal Graph Reasoning with Large Language Models
by: Sun, Yuanfu, et al.
Published: (2026)

IC-Mapper: Instance-Centric Spatio-Temporal Modeling for Online Vectorized Map Construction
by: Zhu, Jiangtong, et al.
Published: (2025)

Does Vector Quantization Fail in Spatio-Temporal Forecasting? Exploring a Differentiable Sparse Soft-Vector Quantization Approach
by: Chen, Chao, et al.
Published: (2023)

OUSAC: Optimized Guidance Scheduling with Adaptive Caching for DiT Acceleration
by: Sun, Ruitong, et al.
Published: (2025)

Retrieval-enhanced Knowledge Editing in Language Models for Multi-Hop Question Answering
by: Shi, Yucheng, et al.
Published: (2024)

SVGen: Interpretable Vector Graphics Generation with Large Language Models
by: Wang, Feiyu, et al.
Published: (2025)

LottieGPT: Tokenizing Vector Animation for Autoregressive Generation
by: Chen, Junhao, et al.
Published: (2026)

Autoregressive Video Generation without Vector Quantization
by: Deng, Haoge, et al.
Published: (2024)

Autoregressive Image Generation without Vector Quantization
by: Li, Tianhong, et al.
Published: (2024)

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

Improving Interpretation Faithfulness for Vision Transformers
by: Hu, Lijie, et al.
Published: (2023)

Inlier-Centric Post-Training Quantization for Object Detection Models
by: Kim, Minsu, et al.
Published: (2026)

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

Towards Joint Quantization and Token Pruning of Vision-Language Models
by: Li, Xinqing, et al.
Published: (2026)

GCAV: A Global Concept Activation Vector Framework for Cross-Layer Consistency in Interpretability
by: He, Zhenghao, et al.
Published: (2025)

From Weights to Concepts: Data-Free Interpretability of CLIP via Singular Vector Decomposition
by: Gentile, Francesco, et al.
Published: (2026)

Scalable Image Tokenization with Index Backpropagation Quantization
by: Shi, Fengyuan, et al.
Published: (2024)

OmniLottie: Generating Vector Animations via Parameterized Lottie Tokens
by: Yang, Yiying, et al.
Published: (2026)

A Creative Agent is Worth a 64-Token Template
by: Shi, Ruixiao, et al.
Published: (2026)

SoFlow: Solution Flow Models for One-Step Generative Modeling
by: Luo, Tianze, et al.
Published: (2025)

Decomposed Vector-Quantized Variational Autoencoder for Human Grasp Generation
by: Zhao, Zhe, et al.
Published: (2024)

VQ-Map: Bird's-Eye-View Map Layout Estimation in Tokenized Discrete Space via Vector Quantization
by: Zhang, Yiwei, et al.
Published: (2024)

Non-confusing Generation of Customized Concepts in Diffusion Models
by: Lin, Wang, et al.
Published: (2024)

Differential Vector Erasure: Unified Training-Free Concept Erasure for Flow Matching Models
by: Zhang, Zhiqi, et al.
Published: (2026)

Interpretable Zero-shot Learning with Infinite Class Concepts
by: Ye, Zihan, et al.
Published: (2025)

Separable Multi-Concept Erasure from Diffusion Models
by: Zhao, Mengnan, et al.
Published: (2024)

Beyond Artifacts: Real-Centric Envelope Modeling for Reliable AI-Generated Image Detection
by: Liu, Ruiqi, et al.
Published: (2025)

UniCTokens: Boosting Personalized Understanding and Generation via Unified Concept Tokens
by: An, Ruichuan, et al.
Published: (2025)

LayoutRAG: Retrieval-Augmented Model for Content-agnostic Conditional Layout Generation
by: Wu, Yuxuan, et al.
Published: (2025)

Channel-wise Vector Quantization
by: Song, Wei, et al.
Published: (2026)

Differentiable Vector Quantization for Rate-Distortion Optimization of Generative Image Compression
by: Jiang, Shiyin, et al.
Published: (2026)