dNaViT: Discrete Codes are General-Purpose Visual Representations
cs.CV, cs.AI
Submitted: 2026-11-09
Updated: 2026-11-09
Code: https://github.com/black-forest-labs/flux
Terminology
Sources
- BitDance: Scaling Autoregressive Generative Models with Binary Tokens
- GENIUS: Generative Fluid Intelligence Evaluation Suite
- LLaVA-OneVision-1.5: Fully Open Framework for Democratized Multimodal Training
- LLaVA-OneVision-2: Towards Next-Generation Perceptual Intelligence
- Qwen3-VL Technical Report
- Qwen2.5-VL Technical Report
- LLaDA2.0-Uni: Unifying Multimodal Understanding and Generation with Diffusion Large Language Model
- FLUX.1 Kontext: Flow Matching for In-Context Image Generation and Editing in Latent Space
- Language Models are Few-Shot Learners
- Seedream 4.0: Toward Next-generation Multimodal Image Generation
- HiDream-I1: A High-Efficient Image Generative Foundation Model with Sparse Diffusion Transformer
- Chameleon: Mixed-Modal Early-Fusion Foundation Models
- Eagle 2.5: Boosting Long-Context Post-Training for Frontier Vision-Language Models
- Deep Compression Autoencoder for Efficient High-Resolution Diffusion Models
- Janus-Pro: Unified Multimodal Understanding and Generation with Data and Model Scaling
- PerceptionLM: Open-Access Data and Models for Detailed Visual Understanding
- Molmo2: Open Weights and Data for Vision-Language Models with Video Understanding and Grounding
- Emu3.5: Native Multimodal Models are World Learners
- Language Modeling Is Compression
- Emerging Properties in Unified Multimodal Pretraining
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