AI Briefing#samsung-research
The latest AI and developer news about #samsung-research, with the original source and a short summary.
The latest AI and developer news about #samsung-research, with the original source and a short summary.
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 article defines Ambient IoT as a RAT-independent interface for devices consuming 1–100 microwatts, enabling network-managed inventory without dedicated readers.
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.
Samsung Research proposed a technology that uses AI to predict and proactively control individual user quality degradation in 5G-Advanced and 6G 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 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.
6G ISAC extends the value of mobile networks beyond connectivity by integrating sensing capabilities that perceive the surrounding environment using existing communication infrastructure.
This paper proposes an AI traffic classification framework combining clustering-based pseudo-labeling with lightweight inference for efficient operation of next-generation RAN.
Developed an AI inference compiler that automatically generates AVX-512 SIMD-optimized code to meet the real-time constraints of 5G RAN.
D-MIMO is a technology that enhances uplink performance and suppresses interference through cooperative reception across multiple TRPs.
By decomposing self-attention weights, editing directions for diffusion were found without any additional training.
Samsung achieved 3.06Gbps on a single 100MHz channel with 8-layer MIMO in an outdoor demonstration of the 7GHz band.
**CSA Aliro 1.0** standardizes access communication between mobile devices and door locks.
The analysis details how 6G expands protection to the MAC layer and adopts 256-bit algorithms to counter quantum threats and fake base stations.
JSCM-based semantic audio achieved similar sound quality at roughly 10dB lower power/SNR than conventional methods.