Samsung Research proposes Systematic Probabilistic Shaping (S-PS), which shapes the second-most-significant bit of QAM symbols to improve spectral efficiency while reusing existing 5G NR LDPC coding and modulation hardware.
The system reuses existing uplink reference signals to distinguish four presence states without additional hardware, reducing data volume by over 10x.
The framework improves reasoning accuracy in 1.5B parameter models by integrating In-Context Learning into Test-Time Reinforcement Learning.
The article defines Ambient IoT as a RAT-independent interface for devices consuming 1–100 microwatts, enabling network-managed inventory without dedicated readers.
The open-source library implements the Graph of Agentic Thoughts framework to capture decision reasoning and rejected alternatives in LangGraph applications.
The standard targets geostationary satellites with a new ultra-low bitrate codec operating at 1.0 and 1.4 kbps.
Samsung Electronics has released an AI framework that analyzes lyrics and musical structure together to evaluate songs at a human-expert level.
Samsung Electronics has released AnySimLite, an ultra-lightweight voice classification encoder capable of sub-30ms inference on smartphones with a size of 700KB.
Samsung Electronics defines 6G NTN not as a replacement for terrestrial networks but as a service continuity layer, presenting a technical foundation to ensure essential mobile services remain uninterrupted outside terrestrial coverage.
The 6G user plane will maximize latency and energy efficiency by simplifying the existing hierarchical structure and introducing intelligent processing.
Samsung Research proposed a technology that uses AI to predict and proactively control individual user quality degradation in 5G-Advanced and 6G networks.
Samsung proposed a method to improve uplink efficiency using compressed CSI and AI-based precoding.
Samsung improved bit recovery efficiency for Ambient-IoT tags using FDMA and Hopfield Neural Networks.
LittleBit-2 improves the quantization performance of sub-1-bit LLMs through latent geometric alignment.
NanoQuant compresses a 70B LLM to below 1 bit using a single H100 GPU.
RaBiT is proposed as a binarization training technique that leverages residuals to improve accuracy while maximizing the efficiency of LLMs.
Samsung R&D has proposed SOGeCE, a low-complexity AI channel estimation technique that leverages Special Orthogonal Group (SOG) equivariant structure to simultaneously handle phase errors and additive noise.
Samsung Research America proposed xMAE, a cross-modal pretraining framework that uses ECG as a training aid signal to enhance PPG representational power.
Samsung Research proposed a two-stage AI CSI feedback training method for extreme compression in 256-port X-MIMO environments.
We propose the K-Merge framework, which continually expands an LLM's capabilities without data even in storage-constrained on-device environments.
By analyzing ITU-R's IMT-2030 requirements, this piece presents the standardization direction and evaluation guidelines for next-generation 6G communication technology.
CSA has released Matter version 1.6, which includes ambient sensing and enhanced control features.
To address the complex network management demands of the 6G era, autonomous network management based on AI agents that can judge and act on their own is emerging, going beyond existing rule-based automation.
Samsung R&D Institute has proposed PIX-TAB, a highly efficient pixel-precise table structure recognition technology capable of on-device execution.
AI Briefing