No article text was recorded for this version.
discrete visual tokenization (vector-quantized image representation)
Version 2 of 2298 papers342 conceptsfrozen 2026-10-04
Papers in this version
- Blog: Compositional Discrete Latent Code for High Fidelity, Productive Diffusion Models
- Blog: Unified Multimodal Understanding and Generation Models: Advances, Challenges, and Opportunities
- Blog: UMTIT: Unifying Recognition, Translation, and Generation for Multimodal Text Image Translation
- Blog: CAST-LUT: Tokenizer-Guided HSV Look-Up Tables for Purple Flare Removal
- Blog: Iterative Token Evaluation and Refinement for Real-World Super-Resolution
- Blog: ManiTrans: Entity-Level Text-Guided Image Manipulation via Token-wise Semantic Alignment and Generation
- Blog: Libra: Building Decoupled Vision System on Large Language Models
- Blog: A Picture is Worth a Thousand Words: Using Cross-Modal Transformers and Variational AutoEncoders to Generate Images from Text
- Blog: SceneLLM: Implicit Language Reasoning in LLM for Dynamic Scene Graph Generation
- Blog: Cost-Effective Language Driven Image Editing with LX-DRIM
- Blog: Translatotron-V(ison): An End-to-End Model for In-Image Machine Translation
- Blog: Seeing Out of tHe bOx: End-to-End Pre-training for Vision-Language Representation Learning
- Blog: Vector-quantized Image Modeling with Improved VQGAN
- Blog: Zero-Shot Text-to-Image Generation
- Blog: VALHALLA: Visual Hallucination for Machine Translation
- Blog: HealthGPT: A Medical Large Vision-Language Model for Unifying Comprehension and Generation via Heterogeneous Knowledge Adaptation
- Blog: Sketch-guided Image Inpainting with Partial Discrete Diffusion Process
- Blog: MAGE: MAsked Generative Encoder to Unify Representation Learning and Image Synthesis
- Blog: Multi-modal Auto-regressive Modeling via Visual Tokens
- Blog: LexSym: Compositionality as Lexical Symmetry
- Blog: Flow to the Mode: Mode-Seeking Diffusion Autoencoders for State-of-the-Art Image Tokenization
- Blog: D-AR: Diffusion via Autoregressive Models
- Blog: MedUnifier: Unifying Vision-and-Language Pre-training on Medical Data with Vision Generation Task using Discrete Visual Representations
- Blog: VIOLET : End-to-End Video-Language Transformers with Masked Visual-token Modeling
- Blog: In-Image Neural Machine Translation with Segmented Pixel Sequence-to-Sequence Model
- Blog: Learning Representations by Predicting Bags of Visual Words
- Blog: aMUSEd: An Open MUSE Reproduction
- Blog: Efficient Large-Scale Multi-Modal Classification
- Blog: IF-Font: Ideographic Description Sequence-Following Font Generation
- Blog: Vector-quantized Image Modeling with Improved VQGAN
- Blog: Auto-Encoding Morph-Tokens for Multimodal LLM
- Blog: An Image is Worth 32 Tokens for Reconstruction and Generation
- Blog: All in Tokens: Unifying Output Space of Visual Tasks via Soft Token
- Blog: Iterative Token Evaluation and Refinement for Real-World Super-resolution
- Blog: ManiTrans: Entity-Level Text-Guided Image Manipulation via Token-wise Semantic Alignment and Generation
- Blog: Unified Multimodal Understanding via Byte-Pair Visual Encoding
- Blog: StyleDrop: Text-to-Image Synthesis of Any Style
- Blog: Translatotron-V(ison): An End-to-End Model for In-Image Machine Translation
- Blog: HoloHisto: End-to-end Gigapixel WSI Segmentation with 4K Resolution Sequential Tokenization
- Blog: Visual Prompting via Image Inpainting
- Blog: Pay Attention to Implicit Attribute Values: A Multi-modal Generative Framework for AVE Task
- Blog: X-LXMERT: Paint, Caption and Answer Questions with Multi-Modal Transformers
- Blog: Transformers for CT Reconstruction From Monoplanar and Biplanar Radiographs
- Blog: SeiT: Storage-Efficient Vision Training with Tokens Using 1% of Pixel Storage
- Blog: Explanatory Instructions: Towards Unified Vision Tasks Understanding and Zero-shot Generalization
- Blog: Democratizing Text-to-Image Masked Generative Models with Compact Text-Aware One-Dimensional Tokens
- Blog: All in Tokens: Unifying Output Space of Visual Tasks via Soft Token
- Blog: Sequential Modeling Enables Scalable Learning for Large Vision Models
- Blog: Generative Cross-Modal Retrieval: Memorizing Images in Multimodal Language Models for Retrieval and Beyond
- Blog: QLIP: Text-Aligned Visual Tokenization Unifies Auto-Regressive Multimodal Understanding and Generation
- Blog: Vary: Scaling up the Vision Vocabulary for Large Vision-Language Models
- Blog: Pixel-Level BPE for Auto-Regressive Image Generation
- Blog: Geometry-Free View Synthesis: Transformers and no 3D Priors
- Blog: PlanGen: Towards Unified Layout Planning and Image Generation in Auto-Regressive Vision Language Models
- Blog: Slot-MLLM: Object-Centric Visual Tokenization for Multimodal LLM
- Blog: MANZANO: A Simple and Scalable Unified Multimodal Model with a Hybrid Vision Tokenizer
- Blog: MaskBit: Embedding-free Image Generation via Bit Tokens
- Blog: CoGS: Controllable Generation and Search from Sketch and Style
- Blog: Prefix Language Models are Unified Modal Learners
- Blog: Discrete Markov Bridge
Showing 60 of 298 papers.
History & citation
Current · Permanent link
- discrete visual tokenization (discrete video tokenization) split from this direction (65% overlap)
Cite this direction
Latest version (a living page):
@misc{lacuna_discrete_visual_tokenization_vector_quan_f53177ef,
title = {discrete visual tokenization (vector-quantized image representation)},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/discrete-visual-tokenization-vector-quantized-image-representation/rdr_f53177ef20354bc3900f26f946de2108},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-20},
}This exact version (version 2, frozen text):
@misc{lacuna_discrete_visual_tokenization_vector_quan_f53177ef_v2,
title = {discrete visual tokenization (vector-quantized image representation)},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/discrete-visual-tokenization-vector-quantized-image-representation/rdr_f53177ef20354bc3900f26f946de2108/v/2},
note = {Version 2, frozen 2026-10-04. Accessed 2026-11-20},
}