Disagreement-Aware Distribution Matching Distillation for Few-Step Diffusion Models
cs.AI
Submitted: 2026-11-09
Updated: 2026-11-09
Code: https://github.com/christophschuhmann/improved-aesthetic-predictor
Terminology
Sources
- Optimizing Few-Step Generation with Adaptive Matching Distillation
- SenseFlow: Scaling Distribution Matching for Flow-based Text-to-Image Distillation
- Distribution Matching Distillation Meets Reinforcement Learning
- GenEval 2: Addressing Benchmark Drift in Text-to-Image Evaluation
- Decoupled DMD: CFG Augmentation as the Spear, Distribution Matching as the Shield
- Latent Consistency Models: Synthesizing High-Resolution Images with Few-Step Inference
- TDM-R1: Reinforcing Few-Step Diffusion Models with Non-Differentiable Reward
- Progressive Distillation for Fast Sampling of Diffusion Models
- Efficient Video Diffusion Models: Advancements and Challenges
- Denoising Diffusion Implicit Models
- TIIF-Bench: How Does Your T2I Model Follow Your Instructions?
- Diversity-Preserved Distribution Matching Distillation for Fast Visual Synthesis
- Qwen-Image-Flash: Rethinking the Training Recipe for Few-Step Distillation
- Human Preference Score v2: A Solid Benchmark for Evaluating Human Preferences of Text-to-Image Synthesis
- SANA: Efficient High-Resolution Image Synthesis with Linear Diffusion Transformers
- SANA 1.5: Efficient Scaling of Training-Time and Inference-Time Compute in Linear Diffusion Transformer
- Scaling Autoregressive Models for Content-Rich Text-to-Image Generation
Related papers
- Multi-Objective Structured Pruning of LLMs for Latency and Model Size Optimization
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- Embeddings for Preferences, Not Semantics
- Can We Trust Item Response Theory for AI Evaluation?
- Diagnosing Task Insensitivity in Language Agents