Wonder 4: A Mixture-of-Experts Recipe for Image Quality Enhancement
cs.CV
Submitted: 2026-11-03
Updated: 2026-11-03
Code: https://github.com/black-forestlabs/flux
Terminology
Sources
- ST-MoE: Designing Stable and Transferable Sparse Expert Models
- Mixtral of Experts
- Auxiliary-Loss-Free Load Balancing Strategy for Mixture-of-Experts
- DeepSeek-V3 Technical Report
- Qwen3 Technical Report
- gpt-oss-120b & gpt-oss-20b Model Card
- Mixture of Ranks with Degradation-Aware Routing for One-Step Real-World Image Super-Resolution
- MiM-DiT: MoE in MoE with Diffusion Transformers for All-in-One Image Restoration
- Scaling Diffusion Transformers to 16 Billion Parameters
- Qwen-Image Technical Report
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