Cover Image

SemHiTok: A Unified Image Tokenizer via Semantic-Guided Hierarchical Codebook for Multimodal Understanding and Generation

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Chen, Zisheng, Wang, Chunwei, Huang, Runhui, Xu, Hongbin, Chen, Xiuwei, Zhou, Jun, Han, Jianhua, Xu, Hang, Liang, Xiaodan
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

HiRes-LLaVA: Restoring Fragmentation Input in High-Resolution Large Vision-Language Models
by: Huang, Runhui, et al.
Published: (2024)

HiTokSR: A Coarse-to-Fine Tokenizer with Hierarchical Codebooks for High-Fidelity Real-World Image Super-Resolution
by: Li, Mingxi
Published: (2026)

C2-Evo: Co-Evolving Multimodal Data and Model for Self-Improving Reasoning
by: Chen, Xiuwei, et al.
Published: (2025)

UniWeTok: An Unified Binary Tokenizer with Codebook Size $\mathit{2^{128}}$ for Unified Multimodal Large Language Model
by: Zhuang, Shaobin, et al.
Published: (2026)

TransMamba: Fast Universal Architecture Adaption from Transformers to Mamba
by: Chen, Xiuwei, et al.
Published: (2025)

ILLUME+: Illuminating Unified MLLM with Dual Visual Tokenization and Diffusion Refinement
by: Huang, Runhui, et al.
Published: (2025)

Towards Unified Multimodal Interleaved Generation via Group Relative Policy Optimization
by: Nie, Ming, et al.
Published: (2026)

AtomicVLA: Unlocking the Potential of Atomic Skill Learning in Robots
by: Zhang, Likui, et al.
Published: (2026)

HiSem: Hierarchical Semantic Disentangling for Remote Sensing Image Change Captioning
by: Wang, Man, et al.
Published: (2026)

LayerDiff: Exploring Text-guided Multi-layered Composable Image Synthesis via Layer-Collaborative Diffusion Model
by: Huang, Runhui, et al.
Published: (2024)

HiMTok: Learning Hierarchical Mask Tokens for Image Segmentation with Large Multimodal Model
by: Wang, Tao, et al.
Published: (2025)

MuseTok: Symbolic Music Tokenization for Generation and Semantic Understanding
by: Huang, Jingyue, et al.
Published: (2025)

UNIT: Unifying Image and Text Recognition in One Vision Encoder
by: Zhu, Yi, et al.
Published: (2024)

TokenFlow: Unified Image Tokenizer for Multimodal Understanding and Generation
by: Qu, Liao, et al.
Published: (2024)

ILLUME: Illuminating Your LLMs to See, Draw, and Self-Enhance
by: Wang, Chunwei, et al.
Published: (2024)

MelTok: 2D Tokenization for Single-Codebook Audio Compression
by: Li, Jingyi, et al.
Published: (2025)

UniTok: A Unified Tokenizer for Visual Generation and Understanding
by: Ma, Chuofan, et al.
Published: (2025)

UniCode$^2$: Cascaded Large-scale Codebooks for Unified Multimodal Understanding and Generation
by: Chen, Yanzhe, et al.
Published: (2025)

FlowTok: Flowing Seamlessly Across Text and Image Tokens
by: He, Ju, et al.
Published: (2025)

MergeTok: Unified Continuous and Discrete Visual Tokenization via Token Merging
by: Zhang, Luyuan, et al.
Published: (2026)

ResTok: Learning Hierarchical Residuals in 1D Visual Tokenizers for Autoregressive Image Generation
by: Zhang, Xu, et al.
Published: (2026)

RealignDiff: Boosting Text-to-Image Diffusion Model with Coarse-to-fine Semantic Re-alignment
by: Jiang, Zutao, et al.
Published: (2023)

EvoTok: A Unified Image Tokenizer via Residual Latent Evolution for Visual Understanding and Generation
by: Li, Yan, et al.
Published: (2026)

KFFocus: Highlighting Keyframes for Enhanced Video Understanding
by: Nie, Ming, et al.
Published: (2025)

Switchable Token-Specific Codebook Quantization For Face Image Compression
by: Wang, Yongbo, et al.
Published: (2025)

SlowFocus: Enhancing Fine-grained Temporal Understanding in Video LLM
by: Nie, Ming, et al.
Published: (2026)

HiPrune: Hierarchical Attention for Efficient Token Pruning in Vision-Language Models
by: Liu, Jizhihui, et al.
Published: (2025)

DualToken: Towards Unifying Visual Understanding and Generation with Dual Visual Vocabularies
by: Song, Wei, et al.
Published: (2025)

HiSpatial: Taming Hierarchical 3D Spatial Understanding in Vision-Language Models
by: Liang, Huizhi, et al.
Published: (2026)

PointDC:Unsupervised Semantic Segmentation of 3D Point Clouds via Cross-modal Distillation and Super-Voxel Clustering
by: Chen, Zisheng, et al.
Published: (2023)

DriveTok: 3D Driving Scene Tokenization for Unified Multi-View Reconstruction and Understanding
by: Zhuo, Dong, et al.
Published: (2026)

CodeBind: Decoupled Representation Learning for Multimodal Alignment with Unified Compositional Codebook
by: Chen, Zeyu, et al.
Published: (2026)

ImageScope: Unifying Language-Guided Image Retrieval via Large Multimodal Model Collective Reasoning
by: Luo, Pengfei, et al.
Published: (2025)

SAGE: Selective Attention-Guided Extraction for Token-Efficient Document Indexing
by: Wang, Xinzhi, et al.
Published: (2026)

HiVG: Hierarchical Multimodal Fine-grained Modulation for Visual Grounding
by: Xiao, Linhui, et al.
Published: (2024)

TrajTok: Learning Trajectory Tokens enables better Video Understanding
by: Zheng, Chenhao, et al.
Published: (2026)

HieraTok: Multi-Scale Visual Tokenizer Improves Image Reconstruction and Generation
by: Chen, Cong, et al.
Published: (2025)

HiVLA: A Visual-Grounded-Centric Hierarchical Embodied Manipulation System
by: Yang, Tianshuo, et al.
Published: (2026)

HiLM-D: Enhancing MLLMs with Multi-Scale High-Resolution Details for Autonomous Driving
by: Ding, Xinpeng, et al.
Published: (2023)

UniToken: Harmonizing Multimodal Understanding and Generation through Unified Visual Encoding
by: Jiao, Yang, et al.
Published: (2025)