Memory-efficient draft machine learning model
US-2026099673-A1 · Apr 9, 2026 · US
This page is not indexed by search engines while we improve data quality.
Lee Mingu patents
Lee Mingu is listed as an inventor on 34 patents in our database. Major assignees and classification codes are summarized below.
| Metric | Value |
|---|---|
| Inventor | Lee Mingu |
| Total patents | 34 |
| First publication | Nov 23, 2023 |
| Latest publication | Apr 9, 2026 |
Notable patents
Publications ranked by popularity score, then publication date.
Memory-efficient draft machine learning model
US-2026099683-A1 · Apr 9, 2026 · US
Efficient machine learning caching via attention output-based token eviction
US-12579063-B2 · Mar 17, 2026 · US
Self-speculative decoding using forecasted embeddings in autoregressive generative artificial intelligence models
US-2026065048-A1 · Mar 5, 2026 · US
Entropy-based early stopping for speculative decoding in generative machine learning models
US-2026065143-A1 · Mar 5, 2026 · US
Efficient attention in transformer neural networks using state space models
US-2026050766-A1 · Feb 19, 2026 · US
Memory-constrained attention in machine learning models
US-2026044745-A1 · Feb 12, 2026 · US
Efficient machine learning caching via attention output-based token eviction
US-2026044449-A1 · Feb 12, 2026 · US
Efficient machine learning caching via attention output-based token eviction
US-2026017192-A1 · Jan 15, 2026 · US
Using grounded rationales to improve visual reasoning
US-12482253-B2 · Nov 25, 2025 · US
Recent patents
Latest publications not already listed above.
Positional embedding generation for machine learning models
US-2025356184-A1 · Nov 20, 2025 · US
Teaching algorithmic reasoning to generative models via execution traces
US-2025355632-A1 · Nov 20, 2025 · US
Token selection in transformer neural networks for efficient inferencing
US-2025322275-A1 · Oct 16, 2025 · US
Adaptive length speculative decoding in autoregressive generative artificial intelligence models
US-2025245530-A1 · Jul 31, 2025 · US
Efficient speculative decoding in autoregressive generative artificial intelligence models
US-2025245430-A1 · Jul 31, 2025 · US
Speculative decoding in autoregressive generative artificial intelligence models
US-12373494-B2 · Jul 29, 2025 · US
Speculative decoding in autoregressive generative artificial intelligence models
US-2025231989-A1 · Jul 17, 2025 · US
Reinforced total variation distance loss for machine learning models
US-2025225374-A1 · Jul 10, 2025 · US
Hybrid generative artificial intelligence models
US-2025200358-A1 · Jun 19, 2025 · US
Code generation using machine learning models
US-2025173127-A1 · May 29, 2025 · US
Speculative decoding in autoregressive generative artificial intelligence models
US-2025148015-A1 · May 8, 2025 · US
Practical activation range restriction for neural network quantization
US-2025124265-A1 · Apr 17, 2025 · US
RE-ARRANGING FEED FORWARD NETWORKS (FFNs) IN TRANSFORMER-BASED MODELS
US-2025094793-A1 · Mar 20, 2025 · US
Speculative decoding in autoregressive generative artificial intelligence models
US-12229192-B2 · Feb 18, 2025 · US
Accelerating inferencing in generative artificial intelligence models
US-2025021761-A1 · Jan 16, 2025 · US
Transformer with multi-scale multi-context attentions
US-2024428576-A1 · Dec 26, 2024 · US
Teaching language models to draw sketches
US-2024394936-A1 · Nov 28, 2024 · US
Using grounded rationales to improve visual reasoning
US-2024386712-A1 · Nov 21, 2024 · US
Hybrid generative artificial intelligence models
US-2024362468-A1 · Oct 31, 2024 · US
Speculative decoding in autoregressive generative artificial intelligence models
US-2024354346-A1 · Oct 24, 2024 · US
Major assignees
Companies most often associated with this inventor's publications.
| Assignee | Patents |
|---|---|
| Qualcomm Inc | 32 |
| Qualcomm Incorporated | 2 |
Top CPC classifications
Most common classification codes across this inventor's patents.
| CPC | Patents |
|---|---|
| G06N3/0475 | 19 |
| G06N3/045 | 19 |
| G06N3/047 | 13 |
| G06F40/284 | 13 |
| G06N3/084 | 10 |