arXiv subjects

Kun Yang

Publications and source records attributed to Kun Yang.

At least 19 recordsLinked to original sources

arXiv2026

Smart-TCP: An Agentic AI-based Autonomous and Adaptive TCP Protocol

The Transmission Control Protocol (TCP) relies on deterministic state machines and sequence-number arithmetic to ensure reliable communication. However, hard-coded protocol logic is difficult to adapt to increasingly complex and dynamic network conditions. This paper proposes Smart-TCP, an agentic AI-based transport protocol framework that organizes TCP control logic as a fast/slow model-assisted decision process. Specifically, a feature-aware classifier routes routine segments to a lightweight Small Language Model (SLM) fast path and anomalous or boundary cases to a Large Language Model (LLM) slow path, while an Arithmetic Logic Unit (ALU) handles deterministic computation of sequence and acknowledgment numbers. A state module maintains connection state, packet history, and key control variables, enabling protocol decisions over the full session context. A scoped Protocol Guard checks candidate decisions against RFC-derived rules before execution. We evaluate Smart-TCP through path classification, atomic packet processing, slow-path anomaly response, and end-to-end session interaction. Experimental results show that Smart-TCP achieves 99.14% action accuracy on 700 slow-path anomaly and fallback samples, and a 100% full-lifecycle success rate over 300 ideal fast-path end-to-end session windows. The ordinary 32-KiB transfer tests achieve a 96.5% completion rate at 20% segment loss. These results suggest that separating model-based protocol decisions from deterministic arithmetic improves the reliability of TCP control for network service operation.

cs.NI↗

arXiv2026

Out-of-Plane Oscillating Electric Fields Unlock Low-Temperature Nonequilibrium Superionicity in Quasi-Two-Dimensional AgCrSe2

Superionic conductors enable exceptionally fast ion transport in solids and offer broad technological potential. However, their highly conductive states are typically accessed only above the order-disorder transition of the mobile-ion sublattice, which limits low-temperature operation. Here, electric-field-responsive machine-learning molecular dynamics reveals a nonequilibrium route to superionic transport in quasi-two-dimensional AgCrSe2 driven by an out-of-plane oscillating electric field. At 300 K, far below the transition temperature near 475 K, the field activates fast in-plane Ag+ transport with an ionic conductivity reaching ~1.7 S/cm. This originates from field-driven dynamic disorder of Ag+ across two equivalent sublattices rather than thermally induced disordering. With increasing frequency, the Ag occupation evolves from complete switching to a highly conductive dynamically disordered state and finally to an ordered state with weak field response. These regimes shift to higher frequencies with increasing temperature or field amplitude, consistent with competition between the driving period and Ag-sublattice response time. At strong fields, this timescale is consistent with field-assisted thermal activation, while weak-field deviations suggest additional dynamics beyond single-ion activation. These results suggest timescale-matched periodic driving as a route to transport-active ionic disorder far below an equilibrium superionic transition.

cond-mat.mtrl-sci↗

arXiv2026

PFAdapter: Hierarchical LoRA Decomposition for Personalized Federated MLLMs

Agentic AI systems are reshaping communications and networking by deploying autonomous intelligent agents capable of collaborative learning while maintaining data privacy at network edges. Within distributed network environments, Multimodal Large Language Models (MLLMs) serve as cognitive engines for edge devices, yet federated fine-tuning faces substantial challenges in balancing global knowledge aggregation with local adaptation under heterogeneous network conditions. Conventional federated protocols typically rely on uniform parameter aggregation, which conflates domain-invariant features with client-specific nuances, thereby resulting in suboptimal personalization and excessive communication overhead. To address these challenges, we propose PFAdapter, a communication-efficient framework introducing hierarchical LoRA decomposition to explicitly separate adapter parameters into global-shared and local-private components. Query and key projections are assigned to global synchronization for capturing universal multimodal semantics across the network, while value and output projections remain localized for edge-specific adaptation. Additionally, orthogonality regularization based on the Frobenius norm enforces strict separation between these components, preventing redundant feature learning. Selective aggregation protocols synchronize only global-shared components across the federated network, preserving local expertise and reducing communication costs by nearly 50%. Extensive experiments on VQA-RAD, SLAKE, Hateful Memes, and CrisisMMD datasets demonstrate that PFAdapter consistently outperforms state-of-the-art baselines, achieving accuracy improvements ranging from 2.4% to 4.8% across diverse edge intelligence tasks. Consequently, our framework establishes an efficient solution for agentic AI deployment in resource-constrained communication networks.

cs.LG↗

arXiv2026

VCRE-Fib: View-Conditioned Regional Evidence for Fine-Grained Ultrasound Grading of Schistosoma japonicum-Associated Liver Fibrosis

Accurate assessment of Schistosoma japonicum-associated liver fibrosis is essential for disease management and long-term follow-up in endemic regions. Ultrasound provides non-invasive imaging, but complex local echogenic patterns and anatomical structures make fine-grained grading challenging. Existing deep learning methods can predict fibrosis scores, yet directly incorporating acquisition views and regional cues into grading while retaining spatial information for inspection remains an open problem. Here we present VCRE-Fib, a view-conditioned regional evidence framework that integrates anatomical context, local information, and global image assessment for fine-grained ultrasound grading. The framework forms view-conditioned local grading evidence before spatial pooling, uses weak localization to guide its aggregation, and combines it with global predictions. Image-only inference jointly returns a fibrosis score, acquisition view, and candidate abnormal-region map. We developed and evaluated the method on a re-curated cohort of 108,709 ultrasound images from 6,373 patients across 35 centers. On a patient-disjoint test set of 4,107 images from 240 patients across four centers, VCRE-Fib reduced the prespecified composite grading risk by 7.115% relative to SFibAI trained and evaluated on the same data split. Image-level mean absolute error decreased from 0.391 to 0.378, alongside lower patient-max, patient-median, and center-balanced risks. The full model also achieved lower composite grading risk than variants that separately removed view conditioning or weak localization. These results support incorporating anatomical context and regional evidence into ultrasound grading while exposing spatial predictions for inspection alongside severity estimates.

cs.CV↗

arXiv2026

FlashSAM: Lightweight Vision Model for Multi-UAV Token Communication in Low-Latitude Wireless Networks

Token Communication (TokenCom) is a promising paradigm for low-altitude wireless networks, as it focuses on transmitting task-relevant core information, particularly in environments with uncertainty, noise, and stringent bandwidth constraints. However, existing TokenCom systems still face several challenges, including inefficient knowledge base construction, ineffective token encoding, and limited support for multi-user token sharing. To address these issues, we propose a Lightweight Vision Model-based Multi-Unmanned Aerial Vehicle (UAV) Token Communication (LVM-MTC) system. First, we develop a lightweight Segment Anything Model (SAM), termed FlashSAM, which incorporates a set of lightweight convolutional modules to significantly reduce the number of model parameters. Building on FlashSAM, we construct a Lightweight Knowledge Base (LKB) to enable efficient object-level perception. Next, we design an Efficient Token Codec (ETC) based on the Masked Autoencoder (MAE) architecture. ETC improves compression efficiency at both the pixel and token levels, and provides lightweight token decoding tailored for resource-constrained UAVs. Furthermore, we propose a Multi-UAV Token Sharing (MTS) scheme for multi-UAV TokenCom. By measuring token similarity across UAVs, MTS consolidates similar tokens and transmits them through broadcast transmission, thereby further improving transmission efficiency. Finally, simulation results validate the feasibility and effectiveness of the proposed LVM-MTC system.

cs.IT↗

arXiv2026

CoFi-CLM: A Coarse-to-Fine Channel Language Model for Finite-Bit CSI Feedback

In frequency-division duplex massive multiple-input multiple-output (MIMO) systems, the user equipment (UE) must convey high-dimensional downlink channel state information (CSI) under a stringent finite-bit feedback budget. Deep learning (DL) has emerged as a powerful tool for CSI compression due to its ability to capture complex channel correlations and learn compact CSI representations. However, recovering fine-scale channel structure from limited feedback remains challenging. To address this challenge, we propose the Coarse-to-Fine Channel Language Model (CoFi-CLM), a large AI model deployed at the base station (BS) that explicitly learns dependencies between coarse and fine CSI representations. Specifically, the UE reports coarse-token indices from a learned codebook, while CoFi-CLM predicts distributions over unreported fine-token indices conditioned on this feedback in a single Transformer forward pass. A dual-path decoder fuses the direct coarse reconstruction with the generated fine-scale reconstruction. Concentrating fine-token prediction and fusion at the BS allows the CLM capacity to scale without increasing the computational or storage cost at the UE. Across 64 to 160 feedback bits, CoFi-CLM consistently outperforms the compared methods on both seen and unseen scenarios. At 128 bits, it improves the normalized mean square error (NMSE) over the recent large AI model baseline by approximately 1 dB on both sets. The performance gap between seen and unseen scenarios further supports its generalization under the considered channel model. The source code is publicly available at https://github.com/doovvv/CoFi-CLM.

eess.SP↗

arXiv2026

When Do Pilots Matter for OFDM Sensing? Pilot-Data Resource Design for ISAC

Practical OFDM-based integrated sensing and communication (ISAC) signals contain deterministic pilots and random data payloads, yet how these two types of resources jointly affect matched-filter sensing performance remains insufficiently understood. This paper establishes an analytical and optimization framework for pilot-data (P-D) OFDM sensing. We first derive a closed-form mean-square periodic autocorrelation function (MS P-ACF), which characterizes the respective contributions of the average subcarrier power spectrum and data-symbol randomness to sensing sidelobes. Based on this result, we reveal that pilot placement has no impact on normalized sidelobes under uniform power allocation or on the normalized global expected integrated sidelobe level (EISL), whereas it becomes an effective design degree of freedom for reshaping sidelobes under nonuniform power allocation. We further derive the globally optimal two-level pilot-data power allocation for global EISL minimization and characterize pilot placement for peak sidelobe suppression. For region-of-interest (ROI) sensing, we jointly optimize pilot placement and subcarrier power allocation to minimize the normalized ROI-EISL. A strictly uniform pilot placement is proved globally optimal under specified conditions, while a bisection-and-branch-and-bound algorithm is developed for general resource configurations. Numerical results validate the theoretical analysis and demonstrate that the proposed design reduces the ROI sidelobe level by up to 2.19 dB compared with optimized uniform-pilot OFDM, while improving ranging accuracy at an SNR of -10 dB by 84.3$\%$. These results reveal when and how pilot placement can be exploited to regulate the sensing behavior of random OFDM communication signals, providing practical resource-design principles for OFDM-based ISAC.

cs.IT↗

arXiv2026

PACE: Perceived-Latency-Aware Cascading Service Routing and Filler Control for QoE-Efficient Retrieval-Augmented Dialogue Serving

We present the PACE, a framework for retrieval-augmented dialogue serving that formalizes Perceived Time-to-First-Response (PTFR) as a QoE objective and minimizes it under quality/cost constraints. Unlike prior work on cascaded routing, semantic caching, or adaptive retrieval, PACE jointly controls which answer source composes the response and what fills the waiting window. Deployed on a humanoid-robot sales service, it combines three mechanisms: a load-adaptive cascading router, a joint path-filler controller, and volatility-aware cache admission. On 75k CarQA requests, the cascade halves pure-LLM PTFR at P95 (0.29 vs 0.53s at c16). The adaptive controller reaches 0.41s P95, outperforming RAG by 2.4 times at high load with equal quality. The filler controller cuts calls by 94% with zero conflict. Volatility-aware admission reduces stale answers from 86% to 0%. A gating rule ensures the controller never worse than the baseline, with exposure bounded by one hold period. This is the first quantification of filler-answer conflict risk in deployed services.

cs.CV↗

arXiv2026

Shaping Delay-Doppler Ambiguity in Practical OFDM-ISAC

Orthogonal frequency-division multiplexing (OFDM) is a key waveform for integrated sensing and communication (ISAC). Existing OFDM ambiguity analyses, however, typically assume fully occupied data-only waveforms, whereas practical frames contain direct-current and edge-guard nulls, fixed pilots, and random payload symbols. This mixed resource structure reshapes the self-ambiguity function and induces prominent sidelobes in the sensing region of interest (ROI). We therefore propose ROI-oriented deep block-unitary precoded OFDM (DBU-OFDM), which combines resource-specific trainable unitary transformations with dedicated sensing subcarriers to suppress ROI sidelobes while preserving the prescribed resource support. We develop a constraint-preserving parameterization capable of representing arbitrary unitary matrices and an ROI-aware sensing-support initialization. We prove periodic autocorrelation function (P-ACF) invariance under phase-only optimization and zero-delay Doppler-cut invariance under arbitrary unitary transformations. Numerical results corroborate the P-ACF optimality of cyclic-prefix OFDM (CP-OFDM) and provide numerical support for the conjecture that conventional OFDM is globally optimal in the considered aperiodic autocorrelation function (A-ACF) setting. Unitary pilot optimization improves the ROI peak-to-sidelobe ratio by over 2 dB, while combining it with dedicated sensing subcarriers yields gains ranging from several to tens of dB. Under the considered configuration, the A-ACF mode also provides substantially greater ROI ambiguity-shaping capability than the P-ACF mode.

eess.SP↗

arXiv2026

Hybrid Offline-Online Multi-Agent Decision Transformers for Wireless Resource Management

This paper develops a hybrid offline-online multi-agent reinforcement learning framework based on decision transformers. The policy is first pretrained offline via supervised sequence modeling of trajectories generated by existing policies, providing a safe and sample-efficient initialization. It is then fine-tuned online using a hybrid objective that incorporates critic-guided gradients, enabling performance improvements beyond the offline policy. To facilitate stable offline-to-online transfer and effective multi-agent coordination, the framework incorporates return-weighted sampling, a critic conditioned on neighbors' actions, and neighborhood-correlated exploration. The approach is fully distributed: both training and execution rely only on local observations and limited information exchange among neighboring agents. Evaluations with dynamic traffic arrivals in two settings: (i) joint scheduling and power allocation and (ii) coordinated beamforming, show that the proposed method achieves quality-of-service (QoS) performance comparable to centralized methods. Moreover, when pretrained on lower-quality datasets, online fine-tuning is also observed to surpass the initial offline policy. These results demonstrate a promising learning-based alternative for wireless resource management.

eess.SY↗

arXiv2026

InjecMEM: Memory Injection Attack on LLM Agent Memory Systems

Memory is becoming a default subsystem in deployed LLM agents to provide persistent personalization and continuity. This naturally prompts a question: will memory system introduce new vulnerabilities into agents? Thus we propose InjecMEM, a novel memory injection attack paradigm that requires only a single interaction (no read/edit access to memory store) to steer later responses of related queries toward a pre-specified output. Guided by the retrieval-then-generate mechanism of memory systems, we craft the injection with a retriever-agnostic anchor and an adversarial command. The anchor contains high-recall topical cues so that downstream retrieval consistently associates the record with the target topic. The command is a short sequence optimized to remain effective under uncertain fused contexts, variable placements, and long prompts so that it reliably steers outputs once retrieved. We learn the command via gradient-based coordinate search, averaging over synthetic prompt templates and insertion positions, and extend it to joint optimization across backbones to study transfer. Evaluated across multiple memory systems and backbone models, InjecMEM achieves reliable topic-conditioned retrieval and targeted generation, remains effective under memory drift, and leaves non-target queries unaffected. Our results underscore the need to harden memory systems and provide a reproducible framework for studying agent memory.

cs.CR↗

arXiv2026

An Interactive Agent for Requirement-Driven Candidate Sourcing

Finding people from a natural-language description (``ML engineers transitioning to research roles in biotech'') is increasingly delegated to LLM agents and framed as information retrieval. We argue that it is fundamentally a requirements engineering task: such a request is an under-determined requirement with implicit constraints, many valid answers, and no acceptance criterion, so useful answers require eliciting, validating, and verifying the requirement before search can matter. We present \sys{}, to our knowledge the first interactive, requirements-driven candidate-sourcing agent (it elicits, validates, retrieves, and verifies a vague people-request into a justified slate through bounded elicitation, workflow templates, a two-stage commit protocol, and bidirectional termination guards) and \bench{}, a benchmark that runs the requirements lifecycle (criteria-anchored validation, multi-model evidence-grounded oracle construction, and cost-aware verification). Across $21$ systems and all $691$ requirements, \sys{} dominates breadth ($100%$ coverage at $2.5\times$ the yield) and is \emph{near-orthogonal} to the field, with $90%$ of the people it returns are surfaced by \emph{none} of $20$ strong LLM-plus-web baselines combined. Beyond breadth, an evidence-grounded judging of every system shows \sys{} \emph{recalls} the most relevant real people: $0.241$ of the union pool, $1.9\times$ the next system, with a bootstrap $95%$ interval disjoint from every baseline. \sys{} is thus the strongest \emph{sourcing} engine (the deepest real, reachable candidate pool), while precision-ranking LLMs serve as~complementary verifiers.

cs.SE↗

arXiv2026

Constitutional On-Policy Safe Distillation

On-policy self-distillation (OPSD) has emerged as an efficient post-training paradigm by using a teacher conditioned on privileged information to provide dense token-level supervision. Prior work has shown that OPSD can collapse in verifiable reasoning tasks, while safety alignment differs in that it is guided by high-level constitutions rather than explicit target answers. However, pilot studies reveals that safety OPSD nonetheless suffers from severe collapse, where constitutional conditioning contracts the teacher distribution toward short and overly conservative responses and Reverse KL further amplifies this contraction into reduced expressiveness. We formalize this effect as geometric leakage under safety boundaries in a non-orthogonal semantic space, where safety pressure transfers into the expressiveness dimension. Based on this analysis, we propose Constitutional On-Policy Safety Distillation (COPSD), which first calibrates the teacher through a Cross-SFT cold-start and then performs constitution-conditioned on-policy distillation. Experiments across 3 multimodal large language models (MLLMs) on 12 safety and general benchmarks show that COPSD improves both safety and helpfulness over baselines while reducing the safety tax on general reasoning.

cs.LG↗

arXiv2026

Characterizing the Quality Profile of AI-Generated C++ in Production

The widespread integration of AI coding assistants offers undeniable boosts to engineering velocity. Yet, recent studies point to a growing trade-off, revealing persistent challenges with code quality and maintainability. Industry leaders, including frontier AI labs, echo these concerns. As large language models are increasingly relied upon to author production code, understanding their impact on shipped software quality has become a critical priority. However, assessing these effects in industrial workflows remains difficult due to observability barriers. We study the impact of AI-generated code on production quality within a large enterprise operating global products relied upon by billions of users daily. Driven by this scale and user trust, the organization values code quality and has built thorough observability for every line of code deployed into production, enabling us to overcome measurement barriers to assess these effects. This study presents a large-scale empirical analysis of AI-generated C++ code from April 2025 to April 2026, tracking 3.52 million code changes across this enterprise's brownfield codebase. The core purpose is to understand the quality, performance, and maintenance characteristics of AI-generated code compared to human-written code in a production environment at scale. We find that AI-generated C++ code has a distinct quality profile, showing higher rates of interface and coupling burdens, copy and allocation overheads, and a reliance on explicit loops over optimized standard APIs. These issues translate into tangible downstream costs, including increased review effort and a 5-8% increase in compute resource consumption. However, we demonstrate that providing models with targeted, taxonomy-informed feedback can mitigate these effects, leading to an 11.1% reduction in targeted static analysis warnings and improved computational efficiency.

cs.SE↗

arXiv2026

Waveform Design for OTFS Assisted Simultaneous Acoustic Information and Power Transfer

Simultaneous acoustic information and power transfer (SAIPT) is a promising technique for supporting self-sustainable Internet of Underwater Things (IoUT) networks through concurrent data transmission and energy supplement. However, existing OFDM-based SAIPT studies are vulnerable to severe multipath propagation and Doppler effects in dynamic underwater acoustic channels. To address this issue, this paper proposes an orthogonal time frequency space (OTFS)-based SAIPT waveform design for dynamic underwater acoustic channels. The acoustic information transfer (AIT) and acoustic power transfer (APT) symbols are jointly designed, while the transducer conversion efficiencies and nonlinear rectifier characteristics are incorporated into the system model. Based on the derived achievable data rate and DC output expressions, a waveform optimization problem is formulated to maximize the harvested DC output under transmit power and minimum data-rate constraints. To solve the resulting non-convex problem, a successive convex approximation (SCA)-based algorithm is developed. Simulation results show that the proposed OTFS-based design outperforms the OFDM-based scheme in terms of DC output in the dynamic transmission scenarios. The effects of key system parameters are also analyzed, confirming the effectiveness of the proposed design in improving acoustic energy transfer efficiency.

eess.SP↗

arXiv2026

A Unified Fully Reconfigurable Architecture for Wireless Powered Communication Networks

Wireless powered communication networks (WPCNs) are a key enabler for sustainable Internet of Things (IoT) systems, yet their practical performance is constrained by inefficient wireless energy transfer, limited spatial adaptability, and fragile uplink connectivity in blockage-prone and dynamic environments. Emerging reconfigurable antenna technologies, including pinching antenna systems (PASSs), fluid antenna systems (FASs), movable antennas (MAs), and reconfigurable intelligent surfaces (RISs), provide new opportunities to overcome these limitations, but have mostly been studied separately. In this article, we propose a unified architecture for fully reconfigurable WPCNs by jointly integrating PASS-enabled power beacons, FAS-based IoT devices, MA-assisted base stations, and RIS-aided propagation environments. The proposed framework enables end-to-end reconfigurability across downlink energy transfer, device-side spatial adaptation, base-station reception, and uplink information transmission. We further discuss the integration motivation, system architecture, design and optimization framework, illustrative performance evaluation, implementation tradeoffs, and major practical challenges. This article provides a new perspective for designing next-generation fully reconfigurable WPCNs.

eess.SY↗

arXiv2026

AI-RAN on NPUs: Baseband Processing Without Baseband Chips

AI-RAN aims to unify artificial intelligence and radio access network workloads on a shared compute substrate. While this paradigm has so far been demonstrated primarily on Graphics Processing Units (GPUs), it remains unclear whether Neural Processing Units (NPUs), which are AI accelerators optimized for inference, can also support wireless baseband processing. Here, we provide the first affirmative answer by resolving the fundamental mismatch between baseband workloads and NPU architecture. A computational isomorphism exists: matrix and vector engines NPUs dedicate to inference inherently cover physical-layer operations. Yet NPU architectures are natively shaped for dense-tensor AI inference, not baseband. This architectural mismatch surfaces as opposing optimization objectives: traditional baseband minimizes arithmetic operations, whereas NPU performance demands maximizing engine utilization. We close this gap by reconstructing communication algorithms onto AI compute primitives, prioritizing engine utilization over arithmetic count. We validate this with a complete OFDM transceiver on an Ascend 310B1 edge NPU, demonstrating end-to-end over-the-air transmission via USRP X300 at 3.0 GHz.

eess.SP↗

arXiv2026

Waveform Design for Underwater Simultaneous Acoustic Information and Power Transfer

Simultaneous acoustic information and power transfer (SAIPT) plays a crucial role in enabling self-sustainable and maintenance-free Internet of Underwater Things (IoUT) networks. This paper studies a multicarrier underwater SAIPT system that jointly considers the frequency-dependent characteristics of acoustic transducers and the nonlinear behavior of rectifier circuits. The waveform vector is firstly optimized using the successive convex approximation (SCA) method under constraints on average and peak transmit power for acoustic power transfer (APT). Then, in the SAIPT scenario, both the power splitting factor and waveform vectors are jointly optimized through an alternating optimization (AO) framework based on SCA, subject to transmit power and achievable rate constraints. Simulation results demonstrate that incorporating the transducer's frequency response, rectifier nonlinearity, and the high peak-to-average power ratio (PAPR) of multicarrier waveforms leads to a significant improvement in acoustic energy transfer efficiency. The results also show that the energy harvesting DC output can be further enhanced by properly choosing system parameters, such as the number of subcarriers and subcarrier spacing.

eess.SP↗