Extracting Explanations, Justification, and Uncertainty from Black-Box Deep Neural Networksby Paul Ardis, Arjuna FlennerFirst submitted…
Zero-shot and Few-shot Generation Strategies for Artificial Clinical Recordsby Erlend Frayling, Jake Lever, Graham McDonaldFirst…
When can we Approximate Wide Contrastive Models with Neural Tangent Kernels and Principal Component Analysis?by…
Implicit Regularization of Gradient Flow on One-Layer Softmax Attentionby Heejune Sheen, Siyu Chen, Tianhao Wang,…
Ambient Diffusion Posterior Sampling: Solving Inverse Problems with Diffusion Models trained on Corrupted Databy Asad…
Prompting Fairness: Integrating Causality to Debias Large Language Modelsby Jingling Li, Zeyu Tang, Xiaoyu Liu,…
Neural reproducing kernel Banach spaces and representer theorems for deep networksby Francesca Bartolucci, Ernesto De…
DAM: Dynamic Adapter Merging for Continual Video QA Learningby Feng Cheng, Ziyang Wang, Yi-Lin Sung,…
Efficient Combinatorial Optimization via Heat Diffusionby Hengyuan Ma, Wenlian Lu, Jianfeng FengFirst submitted to arxiv…
Simple and Scalable Strategies to Continually Pre-train Large Language Modelsby Adam Ibrahim, Benjamin Thérien, Kshitij…