日本フィジカルAI新聞

世界のフィジカルAIを、日本語で。

週刊ニュースレター購読
生成モデル/アライメントarXiv:2605.26552

サンプルベース変分推論の償却による少数ステップ生成モデルのアライメント

Aligning Few-Step Generative Models by Amortizing Sample-based Variational Inference

シェア:XThreadsFacebookLINEはてブBluesky

生成器と参照分布へのサンプルアクセスのみで少数ステップ生成モデルを整列させる一般的な枠組みFAVを提案し、ロボット操作のポリシー整列と画像生成器の整列で有効性を示した。

著者: Jaewoo Lee, Hyeongyu Kang, Dohyun Kim, Kyuil Sim, Woocheol Shin, Minsu Kim, Taeyoung Yun, Jeongjae Lee, Sanghyeok Choi, Tabitha Edith Lee, Jong Chul Ye, Jinkyoo Park

分類: cs.LG, cs.AI

原文アブストラクト

Aligning a few-step generative model is challenging, since existing alignment frameworks typically rely on restrictive assumptions: a tractable likelihood, a specific ODE/SDE solver, or a particular model family. We introduce FAV, Few-step Generative Models Alignment via Sample-based Variational Inference, a general alignment framework that requires only sample access to the generator and the reference distribution. We cast alignment as sampling from a reward-tilted distribution anchored to a reference distribution. We leverage Stein Variational Gradient Descent as a sample-based variational inference scheme and amortize its particle updates into the generator parameters via fixed-point regression. We evaluate FAV on two domains: robotics manipulation and image generator alignment. On generative policy alignment for robotic manipulation, FAV outperforms prevailing policy extraction baselines across 56 offline and 30 offline-to-online RL tasks. For image generator alignment, FAV fine-tunes diverse few-step backbones, including GAN, drifting model, consistency models, and flow maps, scaling from ImageNet-$256$ to 1024$^2$ text-to-image synthesis. Code is available at https://github.com/Jaewoopudding/FAV.