MoETok: Sparse Expert Routing for 1D Visual Tokenizers
cs.CV
Submitted: 2026-10-30
Updated: 2026-10-30
Code: https://github.com/black-forest-labs/flux
Project page: https://gjhhust.github.io/moetok-project
Terminology
Sources
- LLaVA-OneVision-1.5: Fully Open Framework for Democratized Multimodal Training
- BLIP3-o: A Family of Fully Open Unified Multimodal Models-Architecture, Training and Dataset
- ShareGPT-4o-Image: Aligning Multimodal Models with GPT-4o-Level Image Generation
- Janus-Pro: Unified Multimodal Understanding and Generation with Data and Model Scaling
- Emu3.5: Native Multimodal Models are World Learners
- DeepSeek-V3 Technical Report
- Emerging Properties in Unified Multimodal Pretraining
- Bi-Orthogonal Factor Decomposition for Vision Transformers
- Improving Flexible Image Tokenizers for Autoregressive Image Generation
- ELLA: Equip Diffusion Models with LLM for Enhanced Semantic Alignment
- DINO-Tok: Adapting DINO for Visual Tokenizers
- GenEval 2: Addressing Benchmark Drift in Text-to-Image Evaluation
- DetailFlow: 1D Coarse-to-Fine Autoregressive Image Generation via Next-Detail Prediction
- Fine-T2I: An Open, Large-Scale, and Diverse Dataset for High-Quality T2I Fine-Tuning
- Autoregressive Model Beats Diffusion: Llama for Scalable Image Generation
- StableVQ: Practical Guidelines for Stable Vector-Quantized Tokenizer Training
- SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Features
- TextAtlas5M: A Large-scale Dataset for Dense Text Image Generation
- ARM: An AutoRegressive Large Multimodal Model with Unified Discrete Representations
- Emu3: Next-Token Prediction is All You Need
Related papers
- TEA: Text Encoder Alignment for Robust Concept Erasure in Text-to-Image Models
- Do Egocentric Video-Language Models Capture Both Hand- and Object-Centric Cues?
- Aura: Consistent Multi-Subject Video Generation via VLM-Grounded Semantic Alignment
- PVRF: All-in-one Adverse Weather Removal via Prior-modulated and Velocity-constrained Rectified Flow
- DLWM: Diverse Latent World Models for Efficient Multimodal Reasoning
- Out of Sight, Still in Mind: Token Compression for Omni-LLMs