Inventor · name-matched record
LIU MING-YU
5 granted patents·19 pending applications·0 citations·filing 2019–2025
60Inventor score
Files withNVIDIA CORP24
This identity is grouped by exact name match (no disambiguated inventor record was available for these filings) — it may combine same-named inventors.
Top patents by PatentIndex Score
24 records- 0187US2026099963A1Image generation using one or more neural networksNVIDIA CORP·Filed 2025·Application pending·0 cites
- 0286US2026030842A1Synthesizing high resolution 3d shapes from lower resolution representations for synthetic data generation systems and applicationsNVIDIA CORP·Filed 2025·Application pending·0 cites
- 0380US2026011082A1Neural networks to generate pixelsNVIDIA CORP·Filed 2025·Application pending·0 cites
- 0476US2026017864A1Speech-driven animation using one or more neural networksNVIDIA CORP·Filed 2025·Application pending·0 cites
- 0566US2026094245A1Laplacian diffusion for generating imagesNVIDIA CORP·Filed 2025·Application pending·0 cites
- 0666US2026094239A1Laplacian diffusion for generating imagesNVIDIA CORP·Filed 2025·Application pending·0 cites
- 0766US2026094374A1High-fidelity 3d mesh generation via neural networksNVIDIA CORP·Filed 2025·Application pending·0 cites
- 0864US12592010B2Neural network-based image lightingNVIDIA CORP·Filed 2022·Granted Mar 31, 2026·0 cites·30 claims
- 0962US12555200B2Image generation using one or more neural networksNVIDIA CORP·Filed 2021·Granted Feb 17, 2026·0 cites·25 claims
- 1061US12591949B2Image generation using one or more neural networksNVIDIA CORP·Filed 2020·Granted Mar 31, 2026·0 cites·31 claims
- 1160US2026065523A1Sampler for a masked diffusion modelNVIDIA CORP·Filed 2025·Application pending·0 cites
- 1260US2026087351A1Video tokenization using channel-split quantization and mamba-based tokenizer modelsNVIDIA CORP·Filed 2025·Application pending·0 cites
- 1359US12530820B2Image generation using one or more neural networksNVIDIA CORP·Filed 2019·Granted Jan 20, 2026·0 cites·35 claims
- 1457US2026080624A1Auto-regressive auto-encoder for artistic mesh generationNVIDIA CORP·Filed 2025·Application pending·0 cites
- 1556US2026073607A1Physics-based skeletal motion generation by video diffusion distillationNVIDIA CORP·Filed 2025·Application pending·0 cites
- 1655US2026101026A1High-quality three dimensional asset generationNVIDIA CORP·Filed 2025·Application pending·0 cites
- 1755US2026038283A1System and method of semantic segmentation and material identification of 3d objectsNVIDIA CORP·Filed 2025·Application pending·0 cites
- 1855US2026084311A1Generating robotic control policies via diffusion distillationNVIDIA CORP·Filed 2025·Application pending·0 cites
- 1954US2026089325A1Video tokenization using channel-split quantization and mamba-based tokenizer modelsNVIDIA CORP·Filed 2025·Application pending·0 cites
- 2054US2026070225A1Visual chain-of-thought reasoning for robot vision-language-action modelsNVIDIA CORP·Filed 2025·Application pending·0 cites
- 2154US2026038190A1Filtering three-dimensional shape data for training text to 3d generative ai systems and applicationsNVIDIA CORP·Filed 2024·Application pending·0 cites
- 2254US2026038213A1Aligning three-dimensional shape data using pose information for training text to 3d generative ai systems and applicationsNVIDIA CORP·Filed 2024·Application pending·0 cites
- 2353US12574571B2Frame selection for streaming applicationsNVIDIA CORP·Filed 2022·Granted Mar 10, 2026·0 cites·20 claims
- 2450US2026038191A1Automatic annotation of three-dimensional shape data for training text to 3d generative ai systems and applicationsNVIDIA CORP·Filed 2024·Application pending·0 cites
Join the waitlist — get patent alerts
Get an alert when LIU MING-YU files or is granted a new patent.
We store only your email — no account needed. See our privacy policy.
Identity basis: exact name match across USPTO filings. How scoring works →