Artykuły udostępnione publicznie: - Zhaozhuo XuWięcej informacji
Dostępne w jakimś miejscu: 16
Scissorhands: Exploiting the persistence of importance hypothesis for llm kv cache compression at test time
Z Liu, A Desai, F Liao, W Wang, V Xie, Z Xu, A Kyrillidis, A Shrivastava
Advances in Neural Information Processing Systems 36, 2023
Upoważnienia: US National Science Foundation, US Department of Defense
SAR-to-optical image translation using supervised cycle-consistent adversarial networks
L Wang, X Xu, Y Yu, R Yang, R Gui, Z Xu, F Pu
IEEE Access 7, 129136-129149, 2019
Upoważnienia: National Natural Science Foundation of China
Detection, tracking, and geolocation of moving vehicle from uav using monocular camera
X Zhao, F Pu, Z Wang, H Chen, Z Xu
IEEE Access 7, 101160-101170, 2019
Upoważnienia: National Natural Science Foundation of China
Mongoose: A learnable lsh framework for efficient neural network training
B Chen, Z Liu, B Peng, Z Xu, JL Li, T Dao, Z Song, A Shrivastava, C Re
International Conference on Learning Representations, 2020
Upoważnienia: US National Science Foundation, US Department of Defense, US National …
Breaking the Linear Iteration Cost Barrier for Some Well-known Conditional Gradient Methods Using MaxIP Data-structures
Z Xu, Z Song, A Shrivastava
Advances in Neural Information Processing Systems 34, 5576-5589, 2021
Upoważnienia: US National Science Foundation, US Department of Defense
Locality Sensitive Teaching
Z Xu, B Chen, C Li, W Liu, L Song, Y Lin, A Shrivastava
Advances in Neural Information Processing Systems 34, 2021
Upoważnienia: US National Science Foundation, US Department of Defense
Winner-take-all column row sampling for memory efficient adaptation of language model
Z Liu, G Wang, SH Zhong, Z Xu, D Zha, RR Tang, ZS Jiang, K Zhou, ...
Advances in Neural Information Processing Systems 36, 3402-3424, 2023
Upoważnienia: US National Science Foundation
DRAGONN: Distributed Randomized Approximate Gradients of Neural Networks
Z Wang, Z Xu, X Wu, A Shrivastava, TSE Ng
International Conference on Machine Learning, 23274-23291, 2022
Upoważnienia: US National Science Foundation, US Department of Defense
One-pass distribution sketch for measuring data heterogeneity in federated learning
Z Liu, Z Xu, B Coleman, A Shrivastava
Advances in Neural Information Processing Systems 36, 15660-15679, 2023
Upoważnienia: US National Science Foundation, US Department of Defense
Cupcake: A compression scheduler for scalable communication-efficient distributed training
Z Wang, X Wu, Z Xu, TS Ng
Proceedings of Machine Learning and Systems 5, 373-386, 2023
Upoważnienia: US National Science Foundation
Raw Nav-merge Seismic Data to Subsurface Properties with MLP based Multi-Modal Information Unscrambler
A Desai, Z Xu, M Gupta, A Chandran, A Vial-Aussavy, A Shrivastava
Advances in Neural Information Processing Systems 34, 8740-8752, 2021
Upoważnienia: US National Science Foundation, US Department of Defense
A Tale of Two Efficient Value Iteration Algorithms for Solving Linear MDPs with Large Action Space
Z Xu, Z Song, A Shrivastava
International Conference on Artificial Intelligence and Statistics, 788-836, 2023
Upoważnienia: US National Science Foundation, US Department of Defense
GNNs Also Deserve Editing, and They Need It More Than Once
S Zhong, D Le, Z Liu, Z Jiang, A Ye, J Zhang, J Yuan, K Zhou, Z Xu, J Ma, ...
Forty-first International Conference on Machine Learning, 2024
Upoważnienia: US National Science Foundation
Soft Prompt Recovers Compressed LLMs, Transferably
Z Xu, Z Liu, B Chen, S Zhong, Y Tang, W Jue, K Zhou, X Hu, ...
Forty-first International Conference on Machine Learning, 2024
Upoważnienia: US National Science Foundation, US Department of Transportation
Knowledge Graphs Can be Learned with Just Intersection Features
D Le, S Zhong, Z Liu, S Xu, V Chaudhary, K Zhou, Z Xu
Forty-first International Conference on Machine Learning, 2024
Upoważnienia: US National Science Foundation
HALOS: Hashing Large Output Space for Cheap Inference
Z Liu, Z Xu, A Ji, J Zhang, J Li, B Chen, A Shrivastava
Proceedings of Machine Learning and Systems 4, 110-125, 2022
Upoważnienia: US National Science Foundation, US Department of Defense
Informacje na temat publikacji i finansowania automatycznie określa program komputerowy