In latent generative models, reconstruction quality is often assumed to correlate with generative performance. However, reconstruction FID (rFID) can exhibit weak or even negative correlation with generation FID (gFID). We attribute this misalignment to a latent distribution mismatch: reconstruction evaluates the decod...
Xianghong Fang, Wenjie Shu, Tong Xu et al.· 1 citation
Generator-Agent-Verifier (GAV), a scientific experimentation environment that makes new PDE problems verifiable by construction verifiable by construction, is introduced and a theoretical analysis of evaluation reliability and guided development is provided.
Control-Variate Zeroth-Order Descent (CV-ZOD) is introduced, a new framework that refines the classical zeroth-order gradient estimator with a control variate that can be set based on the directional hints to leverage these hints adaptively while maintaining robustness to their quality.
Alexander Ryabchenko, Jian Qian, Wenlong Mou· 0 citations
Discrete visual tokenization, predominantly driven by vector, scalar, and product quantization, lacks a unified conceptual framework for understanding quantization tradeoffs. In this paper, we propose a unified rate--distortion perspective on modern discrete visual tokenization. By viewing quantization as lossy compres...
Xianghong Fang, Wenlong Mou, Yuan Yuan et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
