Salvaging Federated Learning by Local Adaptation Permalink
Tao Yu, Eugene Bagdasaryan, Vitaly Shmatikov.
Publications
You can also find most recent publications on Google Scholar.
Manuscripts
Conference Papers
Training LLMs with MXFP4 Permalink
Albert Tseng, Tao Yu, Youngsuk Park.
Published in 28th International Conference on Artificial Intelligence and Statistics (AISTATS 2025), Paper, Code
Stochastic Rounding for LLM Training: Theory and Practice Permalink
Kaan Ozkara, Tao Yu, Youngsuk Park.
Published in 28th International Conference on Artificial Intelligence and Statistics (AISTATS 2025), Paper, Code
Collage: Light-Weight Low-Precision Strategy for LLM Training Permalink
Tao Yu, Gaurav Gupta, Karthick Gopalswamy, Amith R Mamidala, et al.
Published in 41th International Conference on Machine Learning (ICML 2024), Paper, Code
Shadow Cones: Unveiling Partial Orders in Hyperbolic Space Permalink
Tao Yu*, Toni J.B. Liu*, Albert Tseng, Christopher De Sa.
Published in 12th International Conference on Learning Representations (ICLR 2024), Paper, Code
Coneheads: Hierarchy Aware Attention Permalink
Albert Tseng, Tao Yu, Toni J.B. Liu, Christopher De Sa.
Published in 37th Conference on Neural Information Processing Systems (NeurIPS 2023), Paper, Code
Random Laplacian Features For Learning with Hyperbolic Space Permalink
Tao Yu, Christopher De Sa.
Published in 11th International Conference on Learning Representations (ICLR 2023), Paper, Code
Understanding Hyperdimensional Computing for Parallel Single-Pass Learning Permalink
Tao Yu*, Yichi Zhang*, Zhiru Zhang, Christopher De Sa.
Published in 36th Conference on Neural Information Processing Systems (NeurIPS 2022), Paper, Code
Representing Hyperbolic Space Accurately using Multi-Component Floats Permalink
Tao Yu, Christopher De Sa.
Published in 35th Conference on Neural Information Processing Systems (NeurIPS 2021), Paper
Numerically Accurate Hyperbolic Embeddings Using Tiling-Based Models Permalink
Tao Yu, Christopher De Sa.
Published in 33rd Conference on Neural Information Processing Systems (NeurIPS 2019 Spotlight), Paper, Code 1, Code 2
A New Defense Against Adversarial Images: Turning a Weakness into a Strength Permalink
Tao Yu*, Shengyuan Hu*, Chuan Guo, Weilun Chao, Kilian Q. Weinberger.
Published in 33rd Conference on Neural Information Processing Systems (NeurIPS 2019), Paper, Code
Simplifying Graph Convolutional Networks Permalink
Felix Wu*, Tianyi Zhang*, Amauri Holanda de Souza Jr.*, Christopher Fifty, Tao Yu, Kilian Q. Weinberger.
Published in 36th International Conference on Machine Learning (ICML 2019), Paper, Code
Curvature-based Comparison of Two Neural Networks Permalink
Tao Yu, Huan long, John Hopcroft.
Published in 24th International Conference on Pattern Recognition (ICPR 2018), Paper
Workshop Papers
Momentum Approximation in Asynchronous Private Federated Learning Permalink
Tao Yu, Congzheng Song, Jianyu Wang, Mona Chitnis.
Published in International Workshop on Federated Foundation Models (FL@FM-NeurIPS 2024 Oral), Paper
MCTensor: A High-Precision Deep Learning Library with Multi-Component Floating-Point Permalink
Tao Yu, Wentao Guo, Jianan Canal Li, Tiancheng Yuan, Christopher De Sa.
Published in Workshop on Hardware Aware Eļ¬cient Training (HAET-ICML 2022), Paper, Code