PixelUMM: Encoder-Free Unified Image and Video Understanding and Generation

arXiv:2609.38597 · cs.CV · Submitted 2026-09-29 · Read on arXiv

cs.CV

Submitted: 2026-09-29

Updated: 2026-09-29

Comments: 31 pages, 21 figures. Project page: https://nv-tlabs.github.io/PixelUMM/

Code: https://github.com/black-forest-labs/flux

Project page: https://nv-tlabs.github.io/PixelUMM/Abstract

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Transformer — 30× in this paper · explained in 2 episodes
• Benchmark — 13× in this paper · explained in 2 episodes
• Diffusion Model — 11× in this paper · explained in 10 episodes
• Diffusion Models — 8× in this paper · explained in 9 episodes
• Foundation Model — 8× in this paper · explained in 3 episodes
• Generative Model — 7× in this paper · explained in 2 episodes
• Generative Models — 7× in this paper · explained in 3 episodes
• Alignment — 6× in this paper
• Fine-Tuning — 6× in this paper · explained in 5 episodes
• Foundation Models — 6× in this paper · explained in 7 episodes
• Flow Matching — 4× in this paper · explained in 19 episodes
• Instruction Tuning — 4× in this paper · explained in 3 episodes
• Representation Learning — 4× in this paper · explained in 3 episodes
• Ablation — 3× in this paper · explained in 1 episode
• Aggregation — 3× in this paper
• Embeddings — 3× in this paper · explained in 2 episodes
• Latent Space — 3× in this paper · explained in 7 episodes
• Tokenization — 3× in this paper · explained in 2 episodes
• Latent Diffusion Model — 2× in this paper · explained in 3 episodes
• Quantization — 2× in this paper · explained in 15 episodes
• Rectified Flow — 2× in this paper · explained in 3 episodes
• Adam — 1× in this paper · explained in 2 episodes
• Benchmarking — 1× in this paper · explained in 4 episodes
• Consistency — 1× in this paper · explained in 3 episodes
• Contrastive Learning — 1× in this paper · explained in 8 episodes
• Core — 1× in this paper · explained in 2 episodes
• Decoupling — 1× in this paper · explained in 2 episodes
• Few-Shot Learning — 1× in this paper · explained in 5 episodes
• Fidelity — 1× in this paper · explained in 2 episodes
• Generalization — 1× in this paper · explained in 13 episodes
• Generative Modeling — 1× in this paper · explained in 3 episodes
• Hybrid Models — 1× in this paper · explained in 2 episodes
• Latent Diffusion Models — 1× in this paper · explained in 2 episodes
• Latent Representation — 1× in this paper · explained in 2 episodes
• Latent Representations — 1× in this paper · explained in 3 episodes
• Multimodal Learning — 1× in this paper · explained in 2 episodes
• Reinforcement Learning — 1× in this paper · explained in 4 episodes
• Semantic Understanding — 1× in this paper · explained in 3 episodes
• Temporal consistency — 1× in this paper · explained in 3 episodes
• Variational Bayes — 1× in this paper · explained in 2 episodes
• Vision Transformer (ViT) — 1× in this paper · explained in 2 episodes
• Vision-Language Model (VLM) — 1× in this paper · explained in 3 episodes
• World Model — 1× in this paper · explained in 7 episodes

Sources

• CM3: A Causal Masked Multimodal Model of the Internet
• Ming-Flash-Omni: A Sparse, Unified Architecture for Multimodal Perception and Generation
• Qwen2.5-VL Technical Report
• Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets
• HiDream-O1-Image: A Natively Unified Image Generative Foundation Model with Pixel-level Unified Transformer
• HunyuanImage 3.0 Technical Report
• AlignTok: Aligning Visual Foundation Encoders to Tokenizers for Diffusion Models
• BLIP3-o: A Family of Fully Open Unified Multimodal Models-Architecture, Training and Dataset
• PixelFlow: Pixel-Space Generative Models with Flow
• A Simple Framework for Contrastive Learning of Visual Representations
• VUGEN: Visual Understanding priors for GENeration
• Janus-Pro: Unified Multimodal Understanding and Generation with Data and Model Scaling
• DiP: Taming Diffusion Models in Pixel Space
• VideoLLaMA 2: Advancing Spatial-Temporal Modeling and Audio Understanding in Video-LLMs
• ANOLE: An Open, Autoregressive, Native Large Multimodal Models for Interleaved Image-Text Generation
• Emu3.5: Native Multimodal Models are World Learners
• FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning
• Emerging Properties in Unified Multimodal Pretraining
• Unveiling Encoder-Free Vision-Language Models
• From Pixels to Words -- Towards Native Vision-Language Primitives at Scale

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