- South Korean scientists created Concretesc, a new way of improving wireless communication
- Concretesc avoids large code books, improves image transmission and reduces errors
- The team believes it can help flow 6G networks, smart factories and health units
Researchers in South Korea have developed a new approach to semantic communication that can make future wireless systems faster and more efficient.
The new Concretesc method was created by a team led by Dr. Dong Jin Ji, Associate Professor at Seoul National University of Science and Technology, and was published on June 19, 2025 in IEEE Wireless Communications Letters.
Semantic communication is a shift in wireless technology where meaning is sent rather than raw data. For example, when transmitting an image, the system prioritizes what the image represents instead of sending each pixel exactly. This saves both time and bandwidth and can be particularly useful for artificial intelligence and connected devices.
Potential for 6g
Existing systems often depend on vector quantization, a process that uses gigantic “code books” to store possible signal patterns. These code books are not only heavy to control, but struggle with errors and noise.
Concretesc solves this with another mathematical idea.
Despite its name, it has nothing to do with the material used in buildings. Instead, “concrete” here refers to a special probability distribution in machine learning.
This tool allows continuous information to be transformed into digital signals more smoothly, allowing the system to generate the bitstreams it needs directly, without the burden by managing large code books.
“Unlike Vector Quantization (VQ) -A Advanced Digitization Technique, which suffers from channel noise and code book divergence during training-offering our framework a completely differential solution for quantization, allowing end-to-end-training even under channel noise,” Dr. Ji.
“Especially because of the nature of the concrete who directly generates the required bitstream, it is possible to train a multi-feedback length model pair with a relatively simple masking scheme,” he added.
In simulations, the researchers say Concretesc exceeded VQ-based methods in both structural equality and the maximum signal-to-noise ratio. It also reduced the complexity as its operations grow only by bit length instead of exponentially exponentially with code book size.
The researchers believe this frame could play a valuable role in the next generation wireless systems, such as 6g.
They cite other potential uses, such as in smart factories with ultra-dense machine communication, as well as healthcare and lifestyle monitoring systems driven by small AI-activated devices.
