LoGAH: Predicting 774-Million-Parameter Transformers using Graph HyperNetworks with 1/100 Parametersby Xinyu Zhou, Boris Knyazev, Alexia…
The Impact of Geometric Complexity on Neural Collapse in Transfer Learningby Michael Munn, Benoit Dherin,…
Transfer Learning with Informative Priors: Simple Baselines Better than Previously Reportedby Ethan Harvey, Mikhail Petrov,…
Transfer Learning for Spatial Autoregressive Models with Application to U.S. Presidential Election Predictionby Hao Zeng,…
Scalable Optimization in the Modular Normby Tim Large, Yang Liu, Minyoung Huh, Hyojin Bahng, Phillip…
Implicit In-context Learningby Zhuowei Li, Zihao Xu, Ligong Han, Yunhe Gao, Song Wen, Di Liu,…
Prompt-Based Spatio-Temporal Graph Transfer Learningby Junfeng Hu, Xu Liu, Zhencheng Fan, Yifang Yin, Shili Xiang,…
Fully Distributed Fog Load Balancing with Multi-Agent Reinforcement Learningby Maad Ebrahim, Abdelhakim HafidFirst submitted to…
Towards Graph Contrastive Learning: A Survey and Beyondby Wei Ju, Yifan Wang, Yifang Qin, Zhengyang…
Learning More Generalized Experts by Merging Experts in Mixture-of-Expertsby Sejik ParkFirst submitted to arxiv on:…