South Korean telecom operator LG U+ announced that two of its research papers on AI Token optimization technology have been accepted for the NeurIPS 2026 On-Device Intelligence workshop. This technology targets devices with limited computational resources, such as smartphones, by reducing the computational overhead of AI models to improve processing speed and decrease power consumption. Specifically, the optimization scheme for a small language model used in call services achieves approximately 4.5 times the processing speed compared to traditional methods, with battery consumption reduced by about 77%.
When processing information, AI models break down content such as text into tokens, which are the basic units for computation. As on-device AI capabilities increase, smartphones must run models with limited memory, processing power, and battery capacity, making computational efficiency directly impact response speed and battery life. LG U+'s research focuses on token processing efficiency, aiming to reduce latency and energy consumption during the model inference process to enhance the efficiency of AI functions running locally on smartphones.
LG U+'s AI Token Optimization Technology Significantly Enhances Mobile Performance
In the context of call services, LG U+ applied model lightweighting and inference acceleration technology to small language models (sLM). Compared to relying directly on large cloud models, small language models have relatively lower computational resource demands, making them more suitable for operation on devices like smartphones. LG U+ has released test results showing that after optimization, the processing speed of the relevant models reached approximately 4.5 times that of the original methods, while battery consumption decreased by about 77%.
Additionally, LG U+ has developed technology that allows AI models to continue training within smartphones. Traditional AI training typically requires data to be transferred to a server for processing, but this technology reduces computational load and memory usage, enabling models to learn from user data locally on the device. LG U+ stated that in actual smartphone tests, locally trained models achieved accuracy rates comparable to those trained on servers, and user data remained on the device, improving the model's adaptability to individual usage environments.
Item Specification Processing Speed Improvement Approximately 4.5 times Battery Consumption Reduction Approximately 77%
Disclosure: This article contains links to products from partner merchants. If you purchase through these links, TechRitual may earn a commission, but this does not affect product evaluations and recommendations. For more details, please refer to our privacy policy.