Wei Ying Cheng

7816353, Oct 19, 2010

Oct 22, 2004

10/576653

Wei Cheng - Edison NJ, US
Erick Wang Co - San Diego CA, US
Moon Hwan Kim - Palo Alto CA, US
Rhett Ronald Klein - Chicago IL, US
Donna T. Le - San Jose CA, US
Amy Lew Tsuhako - Milpitas CA, US
John M. Nuss - Danville CA, US
Wei Xu - Danville CA, US

Exelixis, Inc. - South San Francisco CA

C07D 239/38
C07D 413/04
C07D 413/12
C07D 403/12
A61K 31/505
A61K 31/5355
A61K 31/506
A61K 31/496
A61K 31/501
C07D 211/88
C07D 251/38
C07D 487/04
C07D 491/048
A61K 31/44
A61K 31/53
A61K 31/519
A61K 31/4355

5142358, 514272, 51425214, 514344, 514245, 5142621, 514302, 544321, 544122, 544238, 544295, 544262, 546288, 546115

Compounds of formula III:.

20110021525, Jan 27, 2011

Jul 20, 2010

12/839925

Wei Cheng - Edison NJ, US
Erick Wang Co - San Diego CA, US
Moon Hwan Kim - Palo Alto CA, US
Rhett Ronald Klein - Chicago IL, US
Donna T. Le - San Jose CA, US
Amy Lew Tsuhako - Milpitas CA, US
John M. Nuss - Danville CA, US
Wei Xu - Danville CA, US

EXELIXIS, INC. - South San Francisco CA

A61K 31/5377
A61K 31/505
A61P 35/00
A61P 37/06
A61P 19/02
A61P 17/06
A61P 9/10
A61P 3/10
A61P 3/04
A61P 29/00
A61P 27/02
A61P 35/04
C12N 5/00
A61K 31/506

5142358, 514272, 435375, 51425214

The invention provides compounds and methods for inhibition of kinases, more specifically p70S6 kinases. The invention provides compounds for modulating protein kinase enzymatic activity for modulating cellular activities such as proliferation, differentiation, programmed cell death, migration, chemoinvasion and metabolism. Compounds of the invention inhibit, regulate and/or modulate kinase receptor signal transduction pathways related to the changes in cellular activities as mentioned above, and the invention includes compositions which contain these compounds, and methods of using them to treat kinase-dependent diseases and conditions.

51124009, May 12, 1992

Mar 6, 1990

7/489195

Hemi N. Nae - Princeton NJ
Wei M. Cheng - Piscataway NJ
Michael A. DeSesa - Fair Haven NJ

Rheox, Inc. - Hightstown NJ

C09D10102

1061971

The present invention relates to a thickener composition comprising clay deposits and modified cellulose. It has now been discovered that a combination of a clay deposit and a modified cellulosic material provides thickening in water-based systems and particularly, in joint compound formulations. The composition shows a surprising thickening effect when added to water-based systems which would not be expected from the performance of these compounds individually as thickeners.

20220374232, Nov 24, 2022

May 9, 2022

17/739727

- Princeton NJ, US
Haifeng Chen - West Windsor NJ, US
Wei Cheng - Princeton Junction NJ, US

G06F 8/72
G06F 8/30

Systems and methods are provided for automated computer code editing. The method includes training a code-editing neural network model using a corpus of code editing data samples, including the pre-editing samples and post-editing samples, and parsing the pre-editing samples and post-editing samples into an Abstract Syntax Tree (AST). The method further includes using a grammar specification to transform the AST tree into a unified Abstract Syntax Description Language (ASDL) graph for different programming languages, and using a gated graph neural network (GGNN) to compute a vector representation for each node in the unified Abstract Syntax Description Language (ASDL) graph. The method further includes selecting and aggregating support samples based on a query code with a multi-extent ensemble method, and altering the query code iteratively using the pattern learned from the pre- and post-editing samples.

20220318593, Oct 6, 2022

Apr 1, 2022

17/711553

- Princeton NJ, US
Cristian Lumezanu - Princeton Junction NJ, US
Wei Cheng - Princeton Junction NJ, US
Takehiko Mizoguchi - West Windsor NJ, US
Masanao Natsumeda - Princeton Junction NJ, US
Haifeng Chen - West Windsor NJ, US

G06N 3/04
G06N 3/063
G06N 3/08
G06F 40/284

A method for explaining sensor time series data in natural language is presented. The method includes training a neural network model with text-annotated time series data, the neural network model including a time series encoder and a text generator, allowing a human operator to select a time series segment from the text-annotated time series data, the time series segment processed by the time series encoder, outputting, from the time series encoder, a sequence of hidden state vectors, one for each timestep, and generating readable explanatory texts for the human operator based on the selected time series segment, the readable explanatory texts being a set of comment texts explaining and interpreting the selected time series segment in a plurality of different ways.

20220318624, Oct 6, 2022

Feb 22, 2022

17/676944

- Princeton NJ, US
Wei Cheng - Princeton Junction NJ, US
Takehiko Mizoguchi - Princeton NJ, US
Haifeng Chen - West Windsor NJ, US

G06N 3/08
G06N 3/04
G06K 9/62

Methods and systems for training a neural network include training models for respective sensor groups in a cyber-physical system. Combinations of sensor groups and operational modes are sampled. A combination model is trained for each of the sampled combinations. A best combination model is determined based on performance measured during training. The best combination model is fine-tuned.

20230130188, Apr 27, 2023

Oct 19, 2022

17/969349

- Princeton NJ, US
Liang Tong - Lawrenceville NJ, US
Wei Cheng - Princeton Junction NJ, US
Haifeng Chen - West Windsor NJ, US

G06N 3/08

Methods and systems for training a model include collecting unlabeled training data during operation of a device. A model is adapted to operational conditions of the device using the unlabeled training data. The model includes a shared encoder that is trained on labeled training data from multiple devices and further includes a device-specific decoder that is trained on labeled training data corresponding to the device.

20230112441, Apr 13, 2023

Oct 6, 2022

17/961169

- Princeton NJ, US
- Tokyo, JP
Wei Cheng - Princeton Junction NJ, US
Zhengzhang Chen - Princeton Junction NJ, US
Haifeng Chen - West Windsor NJ, US
Yuji Kobayashi - Tokyo, JP
Yuxiang Ren - Tallahassee FL, US

B60W 40/09
G06K 9/62

Systems and methods for data fusion and analysis of vehicle sensor data, including receiving a multiple modality input data stream from a plurality of different types of vehicle sensors, determining latent features by extracting modality-specific features from the input data stream, and aligning a distribution of the latent features of different modalities by feature-level data fusion. Classification probabilities can be determined for the latent features using a fused modality scene classifier. A tree-organized neural network can be trained to determine path probabilities and issue driving pattern judgments, with the tree-organized neural network including a soft tree model and a hard decision leaf. One or more driving pattern judgments can be issued based on a probability of possible driving patterns derived from the modality-specific features.