arXiv subjects

Yunseong Lee

Publications and source records attributed to Yunseong Lee.

8 recordsLinked to original sources

arXiv2026

Improving 5G AI-RAN MCS Selection by Predicting Retransmissions

Link Adaptation (LA) in 5G NR is inherently reactive, relying on channel measurements and HARQ feedback that may become quickly obsolete when the channel changes quickly. This data is also noisy, making it hard to track accurately, and has to be fed to real-time controllers with feedback-loop effects which are hard to troubleshoot. This explains why most practical deployments select simple but robust algorithms, which accept that the lag can leave the scheduler operating at overly aggressive or unnecessarily conservative rates, trading spectrum efficiency for predictable performance. In this paper, we improve on this status-quo with NOSTRAdAMUS, a predictive LA framework which adds foresight to existing algorithms without replacing or redesigning them. NOSTRAdAMUS predicts whether a retransmission will occur in the next radio frame from recent HARQ history, and applies corrections to the Modulation and Coding Scheme (MCS) selected by the underlying policy. We benchmark several ML models and show that Gradient Boosting achieves 82.9% accuracy overall with high-confidence interventions that are correct 94.2% of the time, and an inference latency of 5.5 μs. We train the model based on data collected Over-the-Air (OTA) on the X5G testbed, using the open-source OpenAirInterface (OAI) 5G stack, NVIDIA Aerial, and COTS O-RAN Radio Units and User Equipments. The model is then deployed as a dApp, which we evaluate OTA as well as on various channels with hardware-in-the-loop channel emulators. This includes 3GPP TDL and CDL channels, SISO and MIMO configurations, and pedestrian and vehicular mobility. Our evaluation shows that without retraining, and across this variety of scenarios, the dApp augments two SOTA LA algorithms, and increases goodput by up to 71.5% while reducing retransmissions by up to 71.8%. This demonstrates the robustness and generalization capabilities of our approach.

cs.NI↗

arXiv2026

AUGUSTE: Online-Learning dApp for Predictive URLLC Scheduling

Ultra Reliable and Low Latency Communications (URLLC) was one of the main motivations behind 5G, with 3GPP advertising 1-10 ms latency targets for applications such as industrial automation, Vehicle-To-Everything (V2X), tactical edge networking, and unmanned-system control. Years on, real 5G Time Division Duplexing (TDD) networks still show median Uplink (UL) round-trip times in the 50-70 ms range, largely because of the Scheduling Request (SR) procedure that a User Equipment (UE) must complete before transmitting UL data. Existing remedies, primarily Configured Grant (CG) scheduling, only eliminate this overhead for strictly periodic traffic and require cross-layer synchronization, which has limited their adoption. We propose AUGUSTE (Anticipatory Uplink Grants for URLLC via Self-Adapting Temporal Estimation), a learning-based Medium Access Control (MAC) scheduling framework that embeds online Machine Learning (ML) models in the UL scheduler to predict packet arrivals and proactively allocate resources before an SR is issued. An adaptive state machine alternates between a learning phase that collects unbiased arrival statistics and a confident phase that exploits the learned predictions to schedule only when traffic is expected. We evaluate AUGUSTE on a real 5G testbed running OpenAirInterface across three URLLC traffic patterns (request-response, ML edge inference, and periodic autonomous reporting), and show that it operates at the best achievable point on the latency-overhead trade-off: it matches always-on scheduling's median Round Trip Time (RTT) (around 10 ms, halving the 20 ms SR-based baseline) at roughly one-tenth its resource cost (7-10 percent overhead).

cs.NI↗

arXiv2026

ARCHES: Adaptive Real-Time Switching of AI Models for the RAN

Artificial Intelligence (AI) has become a powerful tool for model-free Radio Access Network (RAN) signal processing and optimization. However, designing a single model that generalizes across all radio environments is challenging. Specialized AI models outperform conventional algorithms only under specific conditions, while their higher compute and energy cost makes unconditional execution impractical at the base station. This creates a need for real-time expert switching: dynamically activating the most appropriate AI or conventional expert based on current network conditions. To address this, we propose ARCHES (Adaptive Real-time CUDA Hot-swapping of Experts in the RAN Stack), a framework hosting multiple AI-based and conventional signal processing experts within a GPU-accelerated PHY pipeline, dynamically selecting the most appropriate expert at slot-boundary granularity without dropping or corrupting in-flight data. ARCHES includes a lightweight CUDA switch kernel for zero-gap output selection, a dApp-based control plane that collects cross-layer telemetry and drives the switching policy, and a reusable process for policy design based on controlled perturbation, monotonicity filtering, and hierarchical clustering. We validate ARCHES on UL channel estimation, switching between an AI-based and a Minimum Mean Square Error (MMSE) estimator under changing propagation and interference conditions. Implemented on the X5G platform with NVIDIA Aerial and OpenAirInterface (OAI), ARCHES achieves median UL PHY throughput gains of 5.32% and 7.23% under good and poor conditions, with a control-loop latency of ~140 us and sub-microsecond decision inference. Under good conditions, defaulting to MMSE saves 15.8 W of GPU power (9.6%) and 17 percentage points of GPU utilization versus unconditional AI execution, validating the performance-per-watt tradeoff that motivates adaptive expert selection.

cs.NI↗

arXiv2026

AgentRAN: An Agentic AI Architecture for Autonomous Control of Open 6G Networks

Despite the programmable architecture of Open RAN, today's deployments still rely heavily on static control and manual operations. To move beyond this limitation, we introduce AgentRAN, an AI-native, Open RAN-aligned agentic framework that generates and orchestrates a fabric of distributed AI agents based on natural language intents. Unlike traditional approaches that require explicit programming, AgentRAN's LLM-powered agents interpret natural language intents, negotiate strategies through structured conversations, and orchestrate control loops across the network. AgentRAN instantiates a self-organizing hierarchy of agents that decompose complex intents across time scales (from sub-millisecond to minutes), spatial domains (cell to network-wide), and protocol layers (PHY/MAC to RRC). A central innovation is the AI-RAN Factory, which continuously generates improved agents and algorithms from operational data, transforming the network into a system that evolves its own intelligence. We validate AgentRAN through live 5G experiments, demonstrating dynamic adaptation to changing operator intents across power control and scheduling. Key benefits include transparent decision-making (all agent reasoning is auditable), bootstrapped intelligence (no initial training data required), and continuous self-improvement via the AI-RAN Factory.

cs.AI↗

arXiv2025

Puzzle: Scheduling Multiple Deep Learning Models on Mobile Device with Heterogeneous Processors

As deep learning models are increasingly deployed on mobile devices, modern mobile devices incorporate deep learning-specific accelerators to handle the growing computational demands, thus increasing their hardware heterogeneity. However, existing works on scheduling deep learning workloads across these processors have significant limitations: most studies focus on single-model scenarios rather than realistic multi-model scenarios, overlook performance variations from different hardware/software configurations, and struggle with accurate execution time estimation. To address these challenges, we propose a novel genetic algorithm-based methodology for scheduling multiple deep learning networks on heterogeneous processors by partitioning the networks into multiple subgraphs. Our approach incorporates three different types of chromosomes for partition/mapping/priority exploration, and leverages device-in-the-loop profiling and evaluation for accurate execution time estimation. Based on this methodology, our system, Puzzle, demonstrates superior performance in extensive evaluations with randomly generated scenarios involving nine state-of-the-art networks. The results demonstrate Puzzle can support 3.7 and 2.2 times higher request frequency on average compared to the two heuristic baselines, NPU Only and Best Mapping, respectively, while satisfying the equivalent level of real-time requirements.

cs.LG↗

arXiv2025

A Novel Analysis Framework for Microstructural Characterization of Ferroelectric Hafnia: Experimental Validation and Application

Herein, we present a novel analysis framework for grain size profile of ferroelectric hafnia to tackle critical shortcomings inherent in the current microstructural analysis. We vastly enhanced visibility of grains with ion beam treatment and performed accurate grain segmentation using deep neural network (DNN). By leveraging our new method, we discovered unexpected discrepancies that contradict previous results, such as deposition temperature (Tdep) and post-metallization annealing (PMA) dependence of grain size statistics, prompting us to reassess earlier interpretations. Combining microstructural analysis with electrical tests, we found that grain size reduction had both positive and negative outcomes: it caused significant diminishing of die-to-die variation (~68 % decrease in standard deviation) in coercive field (Ec), while triggering an upsurge in leakage current. These uncovered results signify robustness of our method in characterization of ferroelectric hafnia for in-depth examination of both device variability and reliability.

cond-mat.mtrl-sci↗

arXiv2020

Accelerating Multi-Model Inference by Merging DNNs of Different Weights

Standardized DNN models that have been proved to perform well on machine learning tasks are widely used and often adopted as-is to solve downstream tasks, forming the transfer learning paradigm. However, when serving multiple instances of such DNN models from a cluster of GPU servers, existing techniques to improve GPU utilization such as batching are inapplicable because models often do not share weights due to fine-tuning. We propose NetFuse, a technique of merging multiple DNN models that share the same architecture but have different weights and different inputs. NetFuse is made possible by replacing operations with more general counterparts that allow a set of weights to be associated with only a certain set of inputs. Experiments on ResNet-50, ResNeXt-50, BERT, and XLNet show that NetFuse can speed up DNN inference time up to 3.6x on a NVIDIA V100 GPU, and up to 3.0x on a TITAN Xp GPU when merging 32 model instances, while only using up a small additional amount of GPU memory.

cs.LG↗

arXiv2018

PRETZEL: Opening the Black Box of Machine Learning Prediction Serving Systems

Machine Learning models are often composed of pipelines of transformations. While this design allows to efficiently execute single model components at training time, prediction serving has different requirements such as low latency, high throughput and graceful performance degradation under heavy load. Current prediction serving systems consider models as black boxes, whereby prediction-time-specific optimizations are ignored in favor of ease of deployment. In this paper, we present PRETZEL, a prediction serving system introducing a novel white box architecture enabling both end-to-end and multi-model optimizations. Using production-like model pipelines, our experiments show that PRETZEL is able to introduce performance improvements over different dimensions; compared to state-of-the-art approaches PRETZEL is on average able to reduce 99th percentile latency by 5.5x while reducing memory footprint by 25x, and increasing throughput by 4.7x.

cs.LG↗