Summary of Approximate Nullspace Augmented Finetuning For Robust Vision Transformers, by Haoyang Liu et al.
Approximate Nullspace Augmented Finetuning for Robust Vision Transformersby Haoyang Liu, Aditya Singh, Yijiang Li, Haohan…
Approximate Nullspace Augmented Finetuning for Robust Vision Transformersby Haoyang Liu, Aditya Singh, Yijiang Li, Haohan…
Improving Medical Multi-modal Contrastive Learning with Expert Annotationsby Yogesh Kumar, Pekka MarttinenFirst submitted to arxiv…
NLP Verification: Towards a General Methodology for Certifying Robustnessby Marco Casadio, Tanvi Dinkar, Ekaterina Komendantskaya,…
Functional Graph Convolutional Networks: A unified multi-task and multi-modal learning framework to facilitate health and…
Unlocking the Multi-modal Potential of CLIP for Generalized Category Discoveryby Enguang Wang, Zhimao Peng, Zhengyuan…
Linear optimal transport subspaces for point set classificationby Mohammad Shifat E Rabbi, Naqib Sad Pathan,…
Logits of API-Protected LLMs Leak Proprietary Informationby Matthew Finlayson, Xiang Ren, Swabha SwayamdiptaFirst submitted to…
EquiAV: Leveraging Equivariance for Audio-Visual Contrastive Learningby Jongsuk Kim, Hyeongkeun Lee, Kyeongha Rho, Junmo Kim,…
Federated Knowledge Graph Unlearning via Diffusion Modelby Bingchen Liu, Yuanyuan FangFirst submitted to arxiv on:…
Sketching the Heat Kernel: Using Gaussian Processes to Embed Databy Anna C. Gilbert, Kevin O'NeillFirst…