Yuanzhong Xu

Person

Mountain View, CA, US

People

Patents Grantslast 30 patents

Information Patent Grant
Training of large neural networks
- Patent number 12,353,981
- Issue date Jul 8, 2025
- Google LLC
- Slav Petrov
- G06 - COMPUTING CALCULATING COUNTING
Information Patent Grant
Propagating reduced-precision on computation graphs
- Patent number 11,972,238
- Issue date Apr 30, 2024
- Google LLC
- Yuanzhong Xu
- G06 - COMPUTING CALCULATING COUNTING
Information Patent Grant
Propagating reduced-precision on computation graphs
- Patent number 11,385,875
- Issue date Jul 12, 2022
- Google LLC
- Yuanzhong Xu
- G06 - COMPUTING CALCULATING COUNTING
Information Patent Grant
Optimizing hardware FIFO instructions
- Patent number 11,221,879
- Issue date Jan 11, 2022
- Google LLC
- Yuanzhong Xu
- G06 - COMPUTING CALCULATING COUNTING
Information Patent Grant
Optimizing hardware FIFO instructions
- Patent number 10,733,016
- Issue date Aug 4, 2020
- Google LLC
- Yuanzhong Xu
- G06 - COMPUTING CALCULATING COUNTING

Patents Applicationslast 30 patents

Information Patent Application
MEMORY EFFICIENT SEQUENCE GENERATION NEURAL NETWORKS
- Publication number 20250021800
- Publication date Jan 16, 2025
- Google LLC
- Yuanzhong Xu
- G06 - COMPUTING CALCULATING COUNTING
Information Patent Application
LARGE LANGUAGE MODEL (LLM) QUANTIZATION
- Publication number 20240428006
- Publication date Dec 26, 2024
- Google LLC
- Jian Li
- G06 - COMPUTING CALCULATING COUNTING
Information Patent Application
Vector-Quantized Image Modeling
- Publication number 20240404238
- Publication date Dec 5, 2024
- Google LLC
- Jiahui Yu
- G06 - COMPUTING CALCULATING COUNTING
Information Patent Application
TRAINING OF LARGE NEURAL NETWORKS
- Publication number 20240378427
- Publication date Nov 14, 2024
- Google LLC
- Slav Petrov
- G06 - COMPUTING CALCULATING COUNTING
Information Patent Application
TRAINING OF LARGE NEURAL NETWORKS
- Publication number 20240378441
- Publication date Nov 14, 2024
- Google LLC
- Slav Petrov
- G06 - COMPUTING CALCULATING COUNTING
Information Patent Application
STREAMING OF NATURAL LANGUAGE (NL) BASED OUTPUT GENERATED USING A L...
- Publication number 20240311402
- Publication date Sep 19, 2024
- Google LLC
- Martin Baeuml
- G06 - COMPUTING CALCULATING COUNTING
Information Patent Application
Implementing and Training Computational Efficient Neural Network Ar...
- Publication number 20240303464
- Publication date Sep 12, 2024
- Google LLC
- Nan Du
- G06 - COMPUTING CALCULATING COUNTING
Information Patent Application
Vector-Quantized Image Modeling
- Publication number 20240112088
- Publication date Apr 4, 2024
- Google LLC
- Jiahui Yu
- G06 - COMPUTING CALCULATING COUNTING
Information Patent Application
ATTENTION NEURAL NETWORKS WITH CONDITIONAL COMPUTATION
- Publication number 20230222318
- Publication date Jul 13, 2023
- Google LLC
- Dmitry Lepikhin
- G06 - COMPUTING CALCULATING COUNTING
Information Patent Application
PROPAGATING REDUCED-PRECISION ON COMPUTATION GRAPHS
- Publication number 20220365763
- Publication date Nov 17, 2022
- Google LLC
- Yuanzhong Xu
- G06 - COMPUTING CALCULATING COUNTING
Information Patent Application
OPTIMIZING HARDWARE FIFO INSTRUCTIONS
- Publication number 20200341807
- Publication date Oct 29, 2020
- Google LLC
- Yuanzhong Xu
- G06 - COMPUTING CALCULATING COUNTING
Information Patent Application
PROPAGATING REDUCED-PRECISION ON COMPUTATION GRAPHS
- Publication number 20200249924
- Publication date Aug 6, 2020
- Google LLC
- Yuanzhong Xu
- G06 - COMPUTING CALCULATING COUNTING

Yuanzhong Xu

Person

Patents Grantslast 30 patents

Training of large neural networks

Propagating reduced-precision on computation graphs

Propagating reduced-precision on computation graphs

Optimizing hardware FIFO instructions

Optimizing hardware FIFO instructions

Patents Applicationslast 30 patents

MEMORY EFFICIENT SEQUENCE GENERATION NEURAL NETWORKS

LARGE LANGUAGE MODEL (LLM) QUANTIZATION

Vector-Quantized Image Modeling

TRAINING OF LARGE NEURAL NETWORKS

TRAINING OF LARGE NEURAL NETWORKS

STREAMING OF NATURAL LANGUAGE (NL) BASED OUTPUT GENERATED USING A L...

Implementing and Training Computational Efficient Neural Network Ar...

Vector-Quantized Image Modeling

ATTENTION NEURAL NETWORKS WITH CONDITIONAL COMPUTATION

PROPAGATING REDUCED-PRECISION ON COMPUTATION GRAPHS

OPTIMIZING HARDWARE FIFO INSTRUCTIONS

PROPAGATING REDUCED-PRECISION ON COMPUTATION GRAPHS