2 papers indexed here
We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.
Not the right person? Other researchers publish under this name.
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.
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...
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
