UnfoldIPThemes

Company patents

UNTETHER AI CORPORATION

UNTETHER AI CORPORATION's patent strategy reveals a strong, albeit fluctuating, focus on foundational computing hardware, with Computer Hardware Architecture representing 60.0% of its portfolio. While Machine Learning & AI saw a significant 50.0% YoY growth in 2024, its subsequent sharp decline of 66.7% in 2025 and complete absence so far in 2026, alongside a 133.3% surge in Memory & Storage (Static) in 2025 followed by a 100.0% decline so far in 2026, suggests a highly dynamic and potentially shifting set of priorities within its core technology development.

Patent Trend by Technology Area

Yearly patent publications since 2023

Product themes

Product-level themes inferred from filings since 2023, with category chips showing where each theme appears. Select a theme to filter the patents below.

55 US filings (since 2023) · 6 categories · 8 themes

Specialized Compute Architectures

Novel hardware designs and processing pipelines tailored for specific computational tasks, such as graphics rendering, neural network operations, or matrix transformations, often involving custom circuits, memory arrays, or data flow mechanisms.

Computer Hardware Architecture
Who else files here? →
35since 2023
-30.8%YoY
AI/ML Hardware Acceleration

Specialized hardware, architectural designs, and computational methods to improve the speed, efficiency, and security of artificial intelligence and machine learning model execution, particularly for inference and data processing.

Computer Hardware ArchitectureMachine Learning & AIHardware Platform (Cooling, Power, Packaging)
Who else files here? →
29since 2023
-53.8%YoY
Memory System Performance & Reliability

Hardware and control techniques for optimizing memory access latency, ensuring data integrity, and managing storage resources efficiently. This includes error correction, read/write voltage control, and intelligent data placement or in-memory computation.

Computer Hardware ArchitectureMemory & Storage (Static)
Who else files here? →
7since 2023
new
Advanced Memory Cell Structures

Focuses on the physical design, materials, and manufacturing processes for individual memory cells, including transistor structures, interconnects, and multi-layered (3D) architectures to enhance density and performance.

Memory & Storage (Static)
Who else files here? →
6since 2023
+200.0%YoY
Quantum Machine Learning

Developing and applying machine learning algorithms that leverage quantum computing principles, such as quantum circuits or autoencoders, for tasks like simulation or data processing.

Machine Learning & AI
Who else files here? →
2since 2023
new
High-Speed Data Interconnects

Technologies for establishing and managing high-bandwidth, low-latency communication pathways between computing components, peripherals, or systems, focusing on signal integrity, synchronization, and interface standards.

Computer Hardware Architecture
Who else files here? →
2since 2023
new
Advanced Channel Coding & Decodingfiltered

Development of encoding and decoding algorithms and apparatuses for robust data transmission and storage, focusing on techniques like LDPC, polar codes, and iterative decoding methods to minimize bit errors and improve communication reliability.

Coding & Decoding
Who else files here? →
2since 2023
new
System Resource & Power Optimization

Methods and systems for efficiently allocating computing resources, balancing workloads, and managing power states to improve performance, reduce energy consumption, or enhance reliability in computing platforms.

Operating Systems & Program Control
Who else files here? →
1since 2023
new

Patents

Showing 1-2 of 2

Advanced Channel Coding & Decoding
Page 1 of 1
US 12587212 B2GRANTED
H03M7/30

Multipart numerical encoding

Filed:2024-05-28Pub:2026-03-24
Applicant:UNTETHER AI CORPORATION

A multipart encoded representation or data type may be particularly useful for limited-capacity processors, such as those used in at-memory or single-instruction, multiple data (SIMD) devices. To encode a source number, the source number is quantized as a first binary representation defined by a first set of exponent bits and a first set of mantissa bits to obtain a first encoded part. A difference between the source number and a nearest dequantization of the first encoded part is computed. The difference is quantized as a second binary representation defined by a second set of exponent bits and a second set of mantissa bits to obtain a second encoded part. The first encoded part and the second encoded part are stored as an encoded representation of the source number. A computational operation may be performed using the encoded representation. The encoded representation may be decoded using an inverse process.

US 20250373268 A1APPLICATION
H03M7/30

MULTIPART NUMERICAL ENCODING

Filed:2024-05-28Pub:2025-12-04
Applicant:UNTETHER AI CORPORATION

A multipart encoded representation or data type may be particularly useful for limited-capacity processors, such as those used in at-memory or single-instruction, multiple data (SIMD) devices. To encode a source number, the source number is quantized as a first binary representation defined by a first set of exponent bits and a first set of mantissa bits to obtain a first encoded part. A difference between the source number and a nearest dequantization of the first encoded part is computed. The difference is quantized as a second binary representation defined by a second set of exponent bits and a second set of mantissa bits to obtain a second encoded part. The first encoded part and the second encoded part are stored as an encoded representation of the source number. A computational operation may be performed using the encoded representation. The encoded representation may be decoded using an inverse process.

1