Ji, Xu

7 publications

AAAI 2023 Adaptive Discrete Communication Bottlenecks with Dynamic Vector Quantization for Heterogeneous Representational Coarseness Dianbo Liu, Alex Lamb, Xu Ji, Pascal Tikeng Notsawo Jr., Michael Mozer, Yoshua Bengio, Kenji Kawaguchi

ICLR 2023 GFlowNets and Variational Inference Nikolay Malkin, Salem Lahlou, Tristan Deleu, Xu Ji, Edward J Hu, Katie E Everett, Dinghuai Zhang, Yoshua Bengio

ICML 2023 GFlowOut: Dropout with Generative Flow Networks Dianbo Liu, Moksh Jain, Bonaventure F. P. Dossou, Qianli Shen, Salem Lahlou, Anirudh Goyal, Nikolay Malkin, Chris Chinenye Emezue, Dinghuai Zhang, Nadhir Hassen, Xu Ji, Kenji Kawaguchi, Yoshua Bengio

ICML 2023 How Does Information Bottleneck Help Deep Learning? Kenji Kawaguchi, Zhun Deng, Xu Ji, Jiaoyang Huang

CoLLAs 2022 Test Sample Accuracy Scales with Training Sample Density in Neural Networks Xu Ji, Razvan Pascanu, R. Devon Hjelm, Balaji Lakshminarayanan, Andrea Vedaldi

CVPR 2020 There and Back Again: Revisiting Backpropagation Saliency Methods Sylvestre-Alvise Rebuffi, Ruth Fong, Xu Ji, Andrea Vedaldi

ICCV 2019 Invariant Information Clustering for Unsupervised Image Classification and Segmentation Xu Ji, Joao F. Henriques, Andrea Vedaldi