Identifiable Exchangeable Mechanisms for Causal Structure and Representation Learningby Patrik Reizinger, Siyuan Guo, Ferenc Huszár,…
Adaptive Adversarial Cross-Entropy Loss for Sharpness-Aware Minimizationby Tanapat Ratchatorn, Masayuki TanakaFirst submitted to arxiv on:…
Semi Supervised Heterogeneous Domain Adaptation via Disentanglement and Pseudo-Labellingby Cassio F. Dantas, Raffaele Gaetano, Dino…
Measuring Sample Importance in Data Pruning for Language Models based on Information Entropyby Minsang Kim,…
MEAT: Median-Ensemble Adversarial Training for Improving Robustness and Generalizationby Zhaozhe Hu, Jia-Li Yin, Bin Chen,…
Information Guided Regularization for Fine-tuning Language Modelsby Mandar Sharma, Nikhil Muralidhar, Shengzhe Xu, Raquib Bin…
Optimal deep learning of holomorphic operators between Banach spacesby Ben Adcock, Nick Dexter, Sebastian MoragaFirst…
Communication-Efficient Adaptive Batch Size Strategies for Distributed Local Gradient Methodsby Tim Tsz-Kit Lau, Weijian Li,…
Improving Zero-Shot Cross-Lingual Transfer via Progressive Code-Switchingby Zhuoran Li, Chunming Hu, Junfan Chen, Zhijun Chen,…
Efficient Sharpness-Aware Minimization for Molecular Graph Transformer Modelsby Yili Wang, Kaixiong Zhou, Ninghao Liu, Ying…