RED-CT: A Systems Design Methodology for Using LLM-labeled Data to Train and Deploy Edge Classifiers…
Enhancing Sharpness-Aware Minimization by Learning Perturbation Radiusby Xuehao Wang, Weisen Jiang, Shuai Fu, Yu ZhangFirst…
Derivative-Free Guidance in Continuous and Discrete Diffusion Models with Soft Value-Based Decodingby Xiner Li, Yulai…
Explaining an Agent’s Future Beliefs through Temporally Decomposing Future Reward Estimatorsby Mark Towers, Yali Du,…
Snuffy: Efficient Whole Slide Image Classifierby Hossein Jafarinia, Alireza Alipanah, Danial Hamdi, Saeed Razavi, Nahal…
GSVD-NMF: Recovering Missing Features in Non-negative Matrix Factorizationby Youdong Guo, Timothy E. HolyFirst submitted to…
BAM! Just Like That: Simple and Efficient Parameter Upcycling for Mixture of Expertsby Qizhen Zhang,…
Absence of Closed-Form Descriptions for Gradient Flow in Two-Layer Narrow Networksby Yeachan ParkFirst submitted to…
SLCA++: Unleash the Power of Sequential Fine-tuning for Continual Learning with Pre-trainingby Gengwei Zhang, Liyuan…
Benchmarking the Capabilities of Large Language Models in Transportation System Engineering: Accuracy, Consistency, and Reasoning…