73 citations · 235 across the 51 of their papers we have counts for
7 papers · 1 filter
Efficient Fréchet Distributional Decoder Alignment for Latent Generative Models
Xianghong Fang, Jiajun Zhu, Esma Aimeur +2
Fréchet Distributional (FD) objectives provide an effective distribution-level signal for post-training generative models. For latent generative models, however, existing FD-based…
A Latent Distribution Perspective on Evaluating and Improving Latent Generative Models
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…
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…
Pre-trained Text-to-Image Diffusion Models Are Versatile Representation Learners for Control
Gunshi Gupta, Karmesh Yadav, Yarin Gal +4
Embodied AI agents require a fine-grained understanding of the physical world mediated through visual and language inputs. Such capabilities are difficult to learn solely from task…
Visual Explanations of Image-Text Representations via Multi-Modal Information Bottleneck Attribution
Ying Wang, Tim G. J. Rudner, Andrew Gordon Wilson
Vision-language pretrained models have seen remarkable success, but their application to safety-critical settings is limited by their lack of interpretability. To improve the inter…
Informative Priors Improve the Reliability of Multimodal Clinical Data Classification
L. Julian Lechuga Lopez, Tim G. J. Rudner, Farah E. Shamout
Machine learning-aided clinical decision support has the potential to significantly improve patient care. However, existing efforts in this domain for principled quantification of…
MultiNet: Segmenting Flooded Buildings via Fusion of Multiresolution, Multisensor, and Multitemporal Satellite Imagery
Tim G. J. Rudner, Marc Rußwurm, Jakub Fil +4
We propose a novel approach for rapid segmentation of flooded buildings by fusing multiresolution, multisensor, and multitemporal satellite imagery in a convolutional neural networ…