AIWalker

Mar 6, 2026 · Artificial Intelligence

VA‑π: Pixel‑Level Alignment Achieves 50% FID Reduction with 25‑Minute Fine‑Tuning

The paper introduces VA‑π, a lightweight post‑training framework that aligns pixel‑level reconstruction with autoregressive generation using variational inference and reinforcement learning, achieving up to 50% FID reduction after just 25 minutes of fine‑tuning on LlamaGen‑XXL.