242 citations · 1.1k across the 27 of their papers we have counts for
27 papers
Investigating the Catastrophic Forgetting in Multimodal Large Language Models
Yuexiang Zhai, Shengbang Tong, Xiao Li +4
Following the success of GPT4, there has been a surge in interest in multimodal large language model (MLLM) research. This line of research focuses on developing general-purpose LL…
Robust Physics-based Deep MRI Reconstruction Via Diffusion Purification
Ismail Alkhouri, Shijun Liang, Rongrong Wang +2
Deep learning (DL) techniques have been extensively employed in magnetic resonance imaging (MRI) reconstruction, delivering notable performance enhancements over traditional non-DL…
Solving Inverse Problems with Latent Diffusion Models via Hard Data Consistency
Bowen Song, Soo Min Kwon, Zecheng Zhang +3
Diffusion models have recently emerged as powerful generative priors for solving inverse problems. However, training diffusion models in the pixel space are both data-intensive and…
The Law of Parsimony in Gradient Descent for Learning Deep Linear Networks
Can Yaras, Peng Wang, Wei Hu +3
Over the past few years, an extensively studied phenomenon in training deep networks is the implicit bias of gradient descent towards parsimonious solutions. In this work, we inves…
Hidden State Variability of Pretrained Language Models Can Guide Computation Reduction for Transfer Learning
Shuo Xie, Jiahao Qiu, Ankita Pasad +3
While transferring a pretrained language model, common approaches conventionally attach their task-specific classifiers to the top layer and adapt all the pretrained layers. We inv…
Are All Losses Created Equal: A Neural Collapse Perspective
Jinxin Zhou, Chong You, Xiao Li +4
While cross entropy (CE) is the most commonly used loss to train deep neural networks for classification tasks, many alternative losses have been developed to obtain better empiric…