Get the newsletter
Samsung · AI / ML · Filed Dec 29, 2025 · USPTO published Aug 13, 2026 · Aug 13 release

Samsung Patents Technology That Shrinks AI Programs Without Sacrificing Their Accuracy

Running a full-size AI model on a phone chip is like trying to pour a river through a garden hose. Samsung's new patent describes a system that figures out exactly where to squeeze the pipe without losing what matters.

Flowchart outlining the step-by-step process for optimizing and shrinking artificial intelligence models. Drawing from patent filing US 2026/0236809 A1.
Flowchart outlining the step-by-step process for optimizing and shrinking artificial intelligence models.All 5 drawings ↓
Publication number
US 2026/0236809 A1(US20260236809A1)
Applicant
SAMSUNG ELECTRONICS CO., LTD.
Filed · Published
Dec 29, 2025 · Aug 13, 2026
Inventors
Meng HUANG, Miao ZHANG, Jong Hoon YOON, Feng ZHU, Yunhao ZHANG, Zhenxin YANG, Sung-Jae CHO, Chang Yong SON
Status when we published
Waiting for an examiner
Document
20 claims
US classification
706/46

How Samsung shrinks AI without breaking what it does

You're recording a video and your Galaxy phone is running AI features in real time: background blur, scene recognition, auto-framing. All of that takes serious computing power, and phone chips have limits.

To run these AI models without killing performance or battery life, engineers shrink them through a process called quantization, which reduces the precision of the math the model does. The tricky part is that not every section of an AI model tolerates shrinking equally well. Squeezing the wrong part too hard degrades the output.

Samsung's patent describes a system that first measures how sensitive each layer of a model is to compression. Layers that are fragile get gentle compression; layers that can take it get squeezed harder. The result is a leaner model that still performs well, without a human engineer having to hand-tune every decision.

From the filing · CLAIM 1
determine quantization sensitivity estimates (QSEs) of one or more convolutional layers included in a model to be quantized; according to a corresponding QSE, determine probabilities of selecting predetermined candidate quantization bit widths in each of the one or more convolutional layers …

Translation: The system calculates how much each part of an AI model can be compressed without losing its ability to perform accurately.

How sensitivity scores drive the bit-width selection

The patent covers a method for mixed-precision quantization of neural networks, meaning different parts of the model get compressed to different levels of numeric precision rather than applying one blunt setting across the whole thing.

Here is how the process works:

  • The system calculates a quantization sensitivity estimate (QSE) for each convolutional layer (a convolutional layer is a building block in image-processing AI that detects visual patterns). The QSE is essentially a score for how much a layer's output degrades when you reduce its precision.
  • Based on that score, the system assigns probabilities to a set of candidate bit widths (8-bit, 4-bit, 2-bit, and so on) for each layer. A sensitive layer gets a high probability of keeping more precision; a resilient layer gets a high probability of being compressed further.
  • The system then generates multiple candidate quantization models by sampling from those probability distributions, producing a range of compressed versions of the original model.
  • Finally, it evaluates those candidates against a predetermined condition (such as a target accuracy or memory budget) and selects the best one.

The key insight is replacing brute-force search across every possible bit-width combination with a probability-driven sampling approach, which is far faster to compute.

From the filing · THE ABSTRACT
… based on the determined probabilities for the one or more convolutional layers, determine candidate quantization models for the model by quantizing the one or more convolutional layers, and based on a predetermined condition for the candidate quantization models, quantize the model by selecting a quantization model from the candidate quantization models.

Translation: The device creates several smaller versions of the AI and automatically picks the best one that meets its performance goals.

What this means for on-device AI on Samsung phones

On-device AI is only useful if it actually fits on the device. As Samsung pushes Galaxy AI features deeper into its phones and tablets, the gap between what a large model can do and what a mobile chip can handle becomes a real engineering bottleneck. A smarter compression pipeline means Samsung can potentially ship more capable AI features without requiring its highest-end Exynos or Snapdragon silicon.

The broader context matters too: automated model compression is becoming a standard part of how chip-level AI gets deployed, and Samsung filing in this space signals it wants to own the tooling, not just license it. Coverage of new Big Tech patents in on-device AI compression shows this is a crowded area, with Apple, Qualcomm, and others all staking claims to how models get squeezed before they reach your pocket.

Source: US 2026/0236809 A1 at the USPTO (PDF). Full patent text and figures are in the official publication.

Get our take in your Top Stories

Liked this breakdown? Add Patentlyze as a preferred source on Google, and our plain-English take shows up more often in your Top Stories the next time Samsung patent news breaks.

There are more where this came from

We read every patent application Big Tech publishes and send you the ones worth knowing. Plain English, free, every week.

The drawings · 5 sheets

5 drawing sheets from US 2026/0236809 A1 · click any drawing to enlarge

Overall model compression workflow, drawing sheet 1 from US 2026/0236809 A1
Sheet 1 Overall model compression workflow
Neural network layer analysis, drawing sheet 2 from US 2026/0236809 A1
Sheet 2 Neural network layer analysis
Quantization bit width probability distribution, drawing sheet 3 from US 2026/0236809 A1
Sheet 3 Quantization bit width probability distribution
Candidate model selection pool, drawing sheet 4 from US 2026/0236809 A1
Sheet 4 Candidate model selection pool
Device processing component architecture, drawing sheet 5 from US 2026/0236809 A1
Sheet 5 Device processing component architecture
Patent filing page

More in AI training & infrastructure

All 323 AI training & infrastructure patents →

Watchlists this filing belongs to

All watchlists →