Multimodal Flow: Unified Flow Modeling of Language and Vision in Embedding Spaces
cs.CV
Submitted: 2026-09-30
Updated: 2026-09-30
Code: https://github.com/hustvl/Multimodal-Flow
Terminology
Sources
- LLaVA-OneVision-1.5: Fully Open Framework for Democratized Multimodal Training
- Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond
- GPIC: A Giant Permissive Image Corpus for Visual Generation
- 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
- MobileVLM V2: Faster and Stronger Baseline for Vision Language Model
- Emerging Properties in Unified Multimodal Pretraining
- DiffuSeq: Sequence to Sequence Text Generation with Diffusion Models
- Continuous Latent Diffusion Language Model
- Visual Generation Tuning
- Classifier-Free Diffusion Guidance
- ELF: Embedded Language Flows
- ELLA: Equip Diffusion Models with LLM for Enhanced Semantic Alignment
- Hunyuan-DiT: A Powerful Multi-Resolution Diffusion Transformer with Fine-Grained Chinese Understanding
- Flow Matching for Generative Modeling
- OneFlow: Concurrent Mixed-Modal and Interleaved Generation with Edit Flows
- DINOv2: Learning Robust Visual Features without Supervision
- Muddit: Liberating Generation Beyond Text-to-Image with a Unified Discrete Diffusion Model
- Unified Multimodal Discrete Diffusion
Related papers
- Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
- AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
- Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
- MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
- TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
- A Survey on Efficient Vision-Language-Action Models