AdaPilot: Towards Scene-Adaptive Policy Learning for Cross-Generator Text-to-Image Quality Optimization

arXiv:2609.29517 · cs.CV, cs.CE · Submitted 2026-08-25 · Read on arXiv

cs.CV, cs.CE

Submitted: 2026-08-25

Updated: 2026-08-25

Code: https://github.com/QwenQKing/Ada

Terminology

• GRPO — 27× in this paper · explained in 6 episodes
• Accuracy — 17× in this paper · explained in 1 episode
• Diffusion Model — 17× in this paper · explained in 8 episodes
• Alignment — 15× in this paper · explained in 1 episode
• Diffusion Models — 15× in this paper · explained in 6 episodes
• Reinforcement Learning — 11× in this paper · explained in 4 episodes
• Fine-Tuning — 9× in this paper · explained in 5 episodes
• Benchmark — 8× in this paper · explained in 2 episodes
• Generalization — 8× in this paper · explained in 13 episodes
• Physical Constraints — 7× in this paper · explained in 7 episodes
• Consistency — 6× in this paper · explained in 3 episodes
• Grounding — 6× in this paper · explained in 3 episodes
• Decoupling — 5× in this paper · explained in 2 episodes
• Adaptation — 4× in this paper · explained in 1 episode
• Embeddings — 3× in this paper · explained in 2 episodes
• Iterative Refinement — 3× in this paper · explained in 3 episodes
• Semantic Alignment — 3× in this paper · explained in 3 episodes
• Supervised Fine-Tuning — 3× in this paper
• Verification — 3× in this paper · explained in 2 episodes
• Ablation — 2× in this paper · explained in 1 episode
• Ablation study — 2× in this paper · explained in 1 episode
• Cosine Similarity — 2× in this paper · explained in 3 episodes
• Foundation Model — 2× in this paper · explained in 3 episodes
• Transferability — 2× in this paper · explained in 4 episodes
• Action Space — 1× in this paper · explained in 1 episode
• Adaptability — 1× in this paper · explained in 1 episode
• Aggregation — 1× in this paper · explained in 1 episode
• Chain-of-Thought Prompting — 1× in this paper · explained in 2 episodes
• Evaluation Dimensions — 1× in this paper · explained in 3 episodes
• Failure Modes — 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
• Flow Matching Model — 1× in this paper · explained in 2 episodes
• Hallucination — 1× in this paper · explained in 3 episodes
• Human Preference Score — 1× in this paper
• Multi-objective Optimization — 1× in this paper · explained in 4 episodes
• Multimodal Reasoning — 1× in this paper · explained in 5 episodes
• Provenance — 1× in this paper · explained in 3 episodes
• Regret — 1× in this paper · explained in 3 episodes
• Reinforcement Learning (RL) — 1× in this paper · explained in 25 episodes
• Supervised Fine-Tuning (SFT) — 1× in this paper · explained in 8 episodes
• Test-time Scaling — 1× in this paper · explained in 2 episodes
• Trace — 1× in this paper · explained in 2 episodes
• Transformer — 1× in this paper · explained in 2 episodes
• Zero-Shot Transfer — 1× in this paper · explained in 4 episodes

Sources

• Qwen2.5-VL Technical Report
• Training Diffusion Models with Reinforcement Learning
• Z-Image: An Efficient Image Generation Foundation Model with Single-Stream Diffusion Transformer
• PosterCraft: Rethinking High-Quality Aesthetic Poster Generation in a Unified Framework
• Directly Fine-Tuning Diffusion Models on Differentiable Rewards
• Training-Free Structured Diffusion Guidance for Compositional Text-to-Image Synthesis
• ELLA: Equip Diffusion Models with LLM for Enhanced Semantic Alignment
• Evaluation of Best-of-N Sampling Strategies for Language Model Alignment
• T2I-R1: Reinforcing Image Generation with Collaborative Semantic-level and Token-level CoT
• GenAgent: Scaling Text-to-Image Generation via Agentic Multimodal Reasoning
• Flow-GRPO: Training Flow Matching Models via Online RL
• ShowTable: Unlocking Creative Table Visualization with Collaborative Reflection and Refinement
• Fine-T2I: An Open, Large-Scale, and Diverse Dataset for High-Quality T2I Fine-Tuning
• Improving Text-to-Image Consistency via Automatic Prompt Optimization
• Aligning Text-to-Image Diffusion Models with Reward Backpropagation
• LongCat-Image Technical Report
• Minority-Focused Text-to-Image Generation via Prompt Optimization
• TextAtlas5M: A Large-scale Dataset for Dense Text Image Generation
• Ovis-Image Technical Report
• PromptEnhancer: A Simple Approach to Enhance Text-to-Image Models via Chain-of-Thought Prompt Rewriting

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