On-Policy Self-Distillation for Multi-Turn Image Editing

arXiv:2609.35611 · cs.CV, cs.LG · Submitted 2026-09-28 · Read on arXiv

cs.CV, cs.LG

Submitted: 2026-09-28

Updated: 2026-09-28

Project page: https://liangbingzhao.github.io/MT-OPSD

Terminology

• Distillation — 24× in this paper · explained in 2 episodes
• Self-Distillation — 17× in this paper · explained in 7 episodes
• Robustness — 15× in this paper · explained in 5 episodes
• Benchmark — 13× in this paper · explained in 2 episodes
• Consistency — 12× in this paper · explained in 3 episodes
• Diffusion Model — 7× in this paper · explained in 8 episodes
• Diffusion Models — 7× in this paper · explained in 6 episodes
• Ablation — 6× in this paper · explained in 1 episode
• International Conference on Learning Representations — 6× in this paper
• Flow Matching — 5× in this paper · explained in 8 episodes
• On-Policy Distillation — 4× in this paper · explained in 3 episodes
• Computer Vision and Pattern Recognition — 3× in this paper
• Latent Space — 3× in this paper · explained in 7 episodes
• Reinforcement Learning — 3× in this paper · explained in 4 episodes
• Transformer — 3× in this paper · explained in 2 episodes
• Adaptation — 2× in this paper · explained in 1 episode
• Exposure Bias — 2× in this paper · explained in 2 episodes
• On-policy Self-Distillation (OPSD) — 2× in this paper · explained in 2 episodes
• Ablation study — 1× in this paper · explained in 1 episode
• Accuracy — 1× in this paper · explained in 1 episode
• Adam — 1× in this paper · explained in 2 episodes
• Alignment — 1× in this paper · explained in 1 episode
• Fidelity — 1× in this paper · explained in 2 episodes
• Generative Modeling — 1× in this paper · explained in 3 episodes
• Latent Diffusion Model — 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
• Temporal consistency — 1× in this paper · explained in 2 episodes

Sources

• Z-Image: An Efficient Image Generation Foundation Model with Single-Stream Diffusion Transformer
• Emerging Properties in Unified Multimodal Pretraining
• Flow-OPD: On-Policy Distillation for Flow Matching Models
• Prompt-to-Prompt Image Editing with Cross Attention Control
• MT-EditFlow: Reinforcement Learning for Multi-Turn Image Editing with Flow Matching
• D-OPSD: On-Policy Self-Distillation for Continuously Tuning Step-Distilled Diffusion Models
• FLUX.1 Kontext: Flow Matching for In-Context Image Generation and Editing in Latent Space
• DiffusionOPD: A Unified Perspective of On-Policy Distillation in Diffusion Models
• OPSD-V: On-Policy Self-Distillation for Post-Training Few-Step Autoregressive Video Generators
• Step1X-Edit: A Practical Framework for General Image Editing
• Privileged Information Distillation for Language Models
• FireRed-Image-Edit-1.0 Technical Report
• Why Do DiT Editors Drift? Plug-and-Play Low Frequency Alignment in VAE Latent Space
• Qwen-Image Technical Report
• OmniGen2: Towards Instruction-Aligned Multimodal Generation
• Show-o: One Single Transformer to Unify Multimodal Understanding and Generation
• AnchorEdit: Maintaining Temporal Consistency in Multi-turn Image Editing via Causal Memory
• Edit-R2: Context-Aware Reinforcement Learning for Multi-Turn Image Editing
• From Statics to Dynamics: Physics-Aware Image Editing with Latent Transition Priors
• Self-Distilled Reasoner: On-Policy Self-Distillation for Large Language Models

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