9 citations · 9 across the 6 of their papers we have counts for
7 papers
Bridging Reconstruction and Generation: A Latent Distribution Perspective on Evaluation and Improvement
Xianghong Fang, Wenjie Shu, Tongda Xu +3
In latent generative models, reconstruction quality is often assumed to correlate with generative performance. However, reconstruction FID (rFID) can exhibit weak or even negative…
A Unified Rate-Distortion Perspective on Vector, Product, and Scalar Quantization
Xianghong Fang, Wenlong Mou, Yuan Yuan +2
Discrete visual tokenization, predominantly driven by vector, scalar, and product quantization, lacks a unified conceptual framework for understanding quantization tradeoffs. In th…
VQ-Transplant: Efficient VQ-Module Integration for Pre-trained Visual Tokenizers
Xianghong Fang, Yuan Yuan, Dehan Kong +1
Vector Quantization (VQ) underpins modern discrete visual tokenization. However, training quantization modules for state-of-the-art VQ-based models requires significant computation…
Rethinking The Uniformity Metric in Self-Supervised Learning
Xianghong Fang, Jian Li, Qiang Sun +1
Uniformity plays an important role in evaluating learned representations, providing insights into self-supervised learning. In our quest for effective uniformity metrics, we pinpoi…
Discrete Auto-regressive Variational Attention Models for Text Modeling
Xianghong Fang, Haoli Bai, Jian Li +3
Variational autoencoders (VAEs) have been widely applied for text modeling. In practice, however, they are troubled by two challenges: information underrepresentation and posterior…
Discrete Variational Attention Models for Language Generation
Xianghong Fang, Haoli Bai, Zenglin Xu +2
Variational autoencoders have been widely applied for natural language generation, however, there are two long-standing problems: information under-representation and posterior col…