Rubric-CEPR: Self-Evolving Image Editing via Reward-Verified Self-Distillation

arXiv:2610.12469 · cs.CV · Submitted 2026-10-08 · Read on arXiv

cs.CV

Submitted: 2026-10-08

Updated: 2026-10-08

Code: https://github.com/riteshthawkar/Rubric-CEPR

Project page: https://riteshthawkar.github.io/Rubric-CEPR/unlabeled

Terminology

• Distillation — 29× in this paper · explained in 2 episodes
• Verifier — 26× in this paper · explained in 2 episodes
• Self-distillation — 25× in this paper · explained in 6 episodes
• Benchmark — 19× in this paper · explained in 2 episodes
• Diffusion Model — 8× in this paper · explained in 8 episodes
• Consistency — 7× in this paper · explained in 3 episodes
• Diffusion Models — 7× in this paper · explained in 6 episodes
• Grounding — 7× in this paper · explained in 3 episodes
• Ablation — 5× in this paper · explained in 1 episode
• Verification — 5× in this paper · explained in 2 episodes
• Adaptation — 4× in this paper · explained in 1 episode
• Fine-Tuning — 4× in this paper · explained in 5 episodes
• Reinforcement Learning — 4× in this paper · explained in 4 episodes
• Trace — 4× in this paper · explained in 2 episodes
• Verifiability — 4× in this paper · explained in 2 episodes
• alpha — 3× in this paper · explained in 1 episode
• AUC — 2× in this paper · explained in 2 episodes
• Accuracy — 2× in this paper · explained in 1 episode
• Adam — 2× in this paper · explained in 2 episodes
• Alignment — 2× in this paper · explained in 1 episode
• Contrastive Edit-Preservation Reward — 2× in this paper
• Ablation Studies — 1× in this paper · explained in 1 episode
• Benchmarking — 1× in this paper · explained in 3 episodes
• Fidelity — 1× in this paper · explained in 2 episodes
• Flow Matching — 1× in this paper · explained in 8 episodes
• Generalization — 1× in this paper · explained in 13 episodes
• LoRA Adapters — 1× in this paper · explained in 3 episodes
• Online Reinforcement Learning — 1× in this paper · explained in 2 episodes
• Pseudo-labels — 1× in this paper · explained in 2 episodes
• Reasoning Traces — 1× in this paper · explained in 3 episodes
• Robustness — 1× in this paper · explained in 5 episodes
• Scaling Laws — 1× in this paper · explained in 4 episodes
• Self-consistency — 1× in this paper · explained in 2 episodes

Sources

• UniEdit-I: Training-free Image Editing for Unified VLM via Iterative Understanding, Editing and Verifying
• FLUX.1 Kontext: Flow Matching for In-Context Image Generation and Editing in Latent Space
• UniCorn: Towards Self-Improving Unified Multimodal Models through Self-Generated Supervision
• SUDER: Self-Improving Unified Large Multimodal Models for Understanding and Generation with Dual Self-Rewards
• Aligning Text-to-Image Models using Human Feedback
• Uniworld-V2: Reinforce Image Editing with Diffusion Negative-aware Finetuning and MLLM Implicit Feedback
• JarvisEvo: Towards a Self-Evolving Photo Editing Agent with Synergistic Editor-Evaluator Optimization
• Step1X-Edit: A Practical Framework for General Image Editing
• Inference-Time Scaling for Diffusion Models beyond Scaling Denoising Steps
• Ask, Solve, Generate: Self-Evolving Unified Multimodal Understanding and Generation via Self-Consistency Rewards
• Qwen-Image Technical Report
• Human Preference Score v2: A Solid Benchmark for Evaluating Human Preferences of Text-to-Image Synthesis
• $\texttt{Complex-Edit}$: CoT-Like Instruction Generation for Complexity-Controllable Image Editing Benchmark
• ImgEdit: A Unified Image Editing Dataset and Benchmark
• On-Policy Self-Distillation for Multi-Turn Image Editing
• ImageEdit-R1: Boosting Multi-Agent Image Editing via Reinforcement Learning

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