跳到正文
研踪PaperTrail
← 研踪 PaperTrail

arXiv:2611.25457 · v1

CANDOR: Contrastive Self-Denoising Rewards for Label-Free Text-to-Image Post-Training

首次提交 2026-11-19 11:37
版本更新 2026-11-19 11:37
雷达观测 2026-11-20 10:50
arXiv ↗PDF ↗

摘要

Post-training text-to-image generators with reinforcement learning usually relies on external reward models that need annotated preferences or auxiliary evaluators and are prone to reward hacking. We show that the generator's own denoising accuracy, used by a recent intrinsic reward, is a poor proxy for prompt fidelity. Within a same-prompt group, this absolute self-confidence is dominated by image complexity and ranks correct samples above incorrect ones near chance. We introduce CANDOR (Contrastive Alignment from Null-referenced Denoising lOg-Ratio), the log-ratio of unconditional to conditional denoising errors under shared noise probes, which measures how much the prompt helps the model denoise its own sample. It cancels prompt-independent difficulty that scales both errors and ranks the better of two same-prompt samples higher in 60% and 63% of pairs on compositional generation and text rendering. As the only Flow-GRPO reward for a flow-matching model, CANDOR improves text rendering, aesthetic and human-preference scores over the base model and a prior absolute self-confidence reward, with text-rendering and preference gains that stronger classifier-free guidance does not reproduce. On public Flow-GRPO adapters trained on external rewards, CANDOR further raises PickScore and ImageReward, so it can complement those rewards. Code is available at https://github.com/jhlee0619/candor.

作者备注:10 pages, 3 figures, 5 tables

AI 论文解读

基于摘要 · 非全文审阅

此版本尚未生成 AI 解读。解读由后台任务生成并按论文版本保存,登录后共享已有结果。

版本差异

目前只收录了一个版本。收录下一版后,可以对照标题、作者、分类和摘要。

观测到的版本

相邻记录可能跳过中间版本;首次发现 v2 及以上也会标为版本更新。

v1 · 2026-11-19 11:37 · 最新观测版本

CANDOR: Contrastive Self-Denoising Rewards for Label-Free Text-to-Image Post-Training

Post-training text-to-image generators with reinforcement learning usually relies on external reward models that need annotated preferences or auxiliary evaluators and are prone to reward hacking. We show that the generator's own denoising accuracy, used by a recent intrinsic reward, is a poor proxy for prompt fidelity. Within a same-prompt group, this absolute self-confidence is dominated by image complexity and ranks correct samples above incorrect ones near chance. We introduce CANDOR (Contrastive Alignment from Null-referenced Denoising lOg-Ratio), the log-ratio of unconditional to conditional denoising errors under shared noise probes, which measures how much the prompt helps the model denoise its own sample. It cancels prompt-independent difficulty that scales both errors and ranks the better of two same-prompt samples higher in 60% and 63% of pairs on compositional generation and text rendering. As the only Flow-GRPO reward for a flow-matching model, CANDOR improves text rendering, aesthetic and human-preference scores over the base model and a prior absolute self-confidence reward, with text-rendering and preference gains that stronger classifier-free guidance does not reproduce. On public Flow-GRPO adapters trained on external rewards, CANDOR further raises PickScore and ImageReward, so it can complement those rewards. Code is available at https://github.com/jhlee0619/candor.

查看此版本解读 →查看此版本原文 ↗