VA-$\pi$: Variational Policy Alignment for Pixel-Aware Autoregressive Generation

TL;DR

VA-$\pi$ is a novel framework that directly optimizes autoregressive image generators in pixel space, improving image quality and consistency without retraining tokenizers, using a variational approach and reinforcement learning.

Contribution

It introduces VA-$\pi$, a post-training method that aligns tokenization with pixel-level quality through a variational objective and reinforcement-based policy optimization.

Findings

Reduces FID from 14.36 to 7.65 on ImageNet-1K

Improves IS from 86.55 to 116.70 on ImageNet-1K

Enhances visual and multi-modal generation metrics with minimal data and time

Abstract

Autoregressive (AR) visual generation relies on tokenizers to map images to and from discrete sequences. However, tokenizers are trained to reconstruct clean images from ground-truth tokens, while AR generators are optimized only for token likelihood. This misalignment leads to generated token sequences that may decode into low-quality images, without direct supervision from the pixel space. We propose VA-$\pi$, a lightweight post-training framework that directly optimizes AR models with a principled pixel-space objective. VA-$\pi$ formulates the generator-tokenizer alignment as a variational optimization, deriving an evidence lower bound (ELBO) that unifies pixel reconstruction and autoregressive modeling. To optimize under the discrete token space, VA-$\pi$ introduces a reinforcement-based alignment strategy that treats the AR generator as a policy, uses pixel-space reconstruction quality as its intrinsic reward. The reward is measured by how well the predicted token sequences can reconstruct the original image under teacher forcing, giving the model direct pixel-level guidance without expensive free-running sampling. The regularization term of the ELBO serves as a natural regularizer, maintaining distributional consistency of tokens. VA-$\pi$ enables rapid adaptation of existing AR generators, without neither tokenizer retraining nor external reward models. With only 1% ImageNet-1K data and 25 minutes of tuning, it reduces FID from 14.36 to 7.65 and improves IS from 86.55 to 116.70 on LlamaGen-XXL, while also yielding notable gains in the text-to-image task on GenEval for both visual generation model (LlamaGen: from 0.306 to 0.339) and unified multi-modal model (Janus-Pro: from 0.725 to 0.744). Code is available at https://github.com/Lil-Shake/VA-Pi.