arXiv subjects

Xiang Cheng

Publications and source records attributed to Xiang Cheng.

At least 73 records · Page 4Linked to original sources

arXiv2025

LLM4AMC: Adapting Large Language Models for Adaptive Modulation and Coding

Adaptive modulation and coding (AMC) is a key technology in 5G new radio (NR), enabling dynamic link adaptation by balancing transmission efficiency and reliability based on channel conditions. However, traditional methods often suffer from performance degradation due to the aging issues of channel quality indicator (CQI). Recently, the emerging capabilities of large language models (LLMs) in contextual understanding and temporal modeling naturally align with the dynamic channel adaptation requirements of AMC technology. Leveraging pretrained LLMs, we propose a channel quality prediction method empowered by LLMs to optimize AMC, termed LLM4AMC. We freeze most parameters of the LLM and fine-tune it to fully utilize the knowledge acquired during pretraining while better adapting it to the AMC task. We design a network architecture composed of four modules, a preprocessing layer, an embedding layer, a backbone network, and an output layer, effectively capturing the time-varying characteristics of channel quality to achieve accurate predictions of future channel conditions. Simulation experiments demonstrate that our proposed method significantly improves link performance and exhibits potential for practical deployment.

eess.SP↗

arXiv2025

WiCo-MG: Wireless Channel Foundation Model for Multipath Generation via Synesthesia of Machines

Precise modeling of channel multipath is essential for understanding wireless propagation environments and optimizing communication systems. In particular, sixth-generation (6G) artificial intelligence (AI)-native communication systems demand massive and high-quality multipath channel data to enable intelligent model training and performance optimization. In this paper, we propose a wireless channel foundation model (WiCo) for multipath generation (WiCo-MG) via Synesthesia of Machines (SoM). To provide a solid training foundation for WiCo-MG, a new synthetic intelligent sensing-communication dataset for uncrewed aerial vehicle (UAV)-to-ground (U2G) communications is constructed. To overcome the challenges of cross-modal alignment and mapping, a two-stage training framework is proposed. In the first stage, sensing images are embedded into discrete-continuous SoM feature spaces, and multipath maps are embedded into a sensing-initialized discrete SoM space to align the representations. In the second stage, a mixture of shared and routed experts (S-R MoE) Transformer with frequency-aware expert routing learns the mapping from sensing to channel SoM feature spaces, enabling decoupled and adaptive multipath generation. Experimental results demonstrate that WiCo-MG achieves state-of-the-art in-distribution generation performance and superior out-of-distribution generalization, reducing NMSE by more than 2.59 dB over baselines, while exhibiting strong scalability in model and dataset growth and extensibility to new multipath parameters and tasks. Owing to higher accuracy, stronger generalization, and better scalability, WiCo-MG is expected to enable massive and high-fidelity channel data generation for the development of 6G AI-native communication systems.

eess.SP↗

arXiv2025

WiCo-PG: Wireless Channel Foundation Model for Pathloss Map Generation via Synesthesia of Machines

A wireless channel foundation model for pathloss map generation (WiCo-PG) via Synesthesia of Machines (SoM) is developed for the first time. Considering sixth-generation (6G) uncrewed aerial vehicle (UAV)-to-ground (U2G) scenarios, a new multi-modal sensing-communication dataset is constructed for WiCo-PG pre-training, including multiple U2G scenarios, diverse flight altitudes, and diverse frequency bands. Based on the constructed dataset, the proposed WiCo-PG enables cross-modal pathloss map generation by leveraging RGB images from different scenarios and flight altitudes. In WiCo-PG, a novel network architecture designed for cross-modal pathloss map generation based on dual vector quantized generative adversarial networks (VQGANs) and Transformer is proposed. Furthermore, a novel frequency-guided shared-routed mixture of experts (S-R MoE) architecture is designed for cross-modal pathloss map generation. Simulation results demonstrate that the proposed WiCo-PG achieves improved pathloss map generation accuracy through pre-training with a normalized mean squared error (NMSE) of 0.012, outperforming the large language model (LLM)-based scheme, i.e., LLM4PG, and the conventional deep learning-based scheme by more than 6.98 dB. The enhanced generality of the proposed WiCo-PG can further outperform the LLM4PG by at least 1.37 dB using 2.7% samples in few-shot generalization.

eess.SP↗

arXiv2025

SynthSoM-Twin: A Multi-Modal Sensing-Communication Digital-Twin Dataset for Sim2Real Transfer via Synesthesia of Machines

This paper constructs a novel multi-modal sensing-communication digital-twin dataset, named SynthSoM-Twin, which is spatio-temporally consistent with the real world, for Sim2Real transfer via Synesthesia of Machines (SoM). To construct the SynthSoM-Twin dataset, we propose a new framework that can extend the quantity and missing modality of existing real-world multi-modal sensing-communication dataset. Specifically, we exploit multi-modal sensing-assisted object detection and tracking algorithms to ensure spatio-temporal consistency of static objects and dynamic objects across real world and simulation environments. The constructed scenario is imported into three high-fidelity simulators, i.e., AirSim, WaveFarer, and Sionna RT. The SynthSoM-Twin dataset contains spatio-temporally consistent data with the real world, including 66,868 snapshots of synthetic RGB images, depth maps, light detection and ranging (LiDAR) point clouds, millimeter wave (mmWave) radar point clouds, and large-scale and small-scale channel fading data. To validate the utility of SynthSoM-Twin dataset, we conduct Sim2Real transfer investigation by implementing two cross-modal downstream tasks via cross-modal generative models (CMGMs), i.e., cross-modal channel generation model and multi-modal sensing-assisted beam generation model. Based on the downstream tasks, we explore the threshold of real-world data injection that can achieve a decent trade-off between real-world data usage and models' practical performance. Experimental results show that the model training on the SynthSoM-Twin dataset achieves a decent practical performance, and the injection of real-world data further facilitates Sim2Real transferability. Based on the SynthSoM-Twin dataset, injecting less than 15% of real-world data can achieve similar and even better performance compared to that trained with all the real-world data only.

eess.SP↗

arXiv2025

Experimental high-dimensional entanglement certification and quantum steering with time-energy measurements

High-dimensional entanglement provides unique ways of transcending the limitations of current approaches in quantum information processing, quantum communications based on qubits. The generation of time-frequency qudit states offer significantly increased quantum capacities while keeping the number of photons constant, but pose significant challenges regarding the possible measurements for certification of entanglement. Here, we develop a new scheme and experimentally demonstrate the certification of 24-dimensional entanglement and a 9-dimensional quantum steering. We then subject our photon-pairs to dispersion conditions equivalent to the transmission through 600-km of fiber and still certify 21-dimensional entanglement. Furthermore, we use a steering inequality to prove 7-dimensional entanglement in a semi-device independent manner, proving that large chromatic dispersion is not an obstacle in distributing and certifying high-dimensional entanglement and quantum steering. Our approach, leveraging intrinsic large-alphabet nature of telecom-band photons, enables scalable, commercially viable, and field-deployable entangled and steerable quantum sources, providing a pathway towards fully scalable quantum information processer and high-dimensional quantum communication networks.

quant-ph↗

arXiv2025

LLM4PG: Adapting Large Language Model for Pathloss Map Generation via Synesthesia of Machines

In this paper, a novel large language model (LLM)-based pathloss map generation model, termed LLM4PG, is proposed for sixth-generation (6G) AI-native communication systems via Synesthesia of Machines (SoM). To explore the mapping mechanism between sensing images and pathloss maps, a new synthetic intelligent multi-modal sensing-communication dataset, SynthSoM-U2G, is constructed, covering multiple scenarios, frequency bands, and flight altitudes. By adapting the LLM for cross-modal pathloss map generation for the first time, LLM4PG establishes an effective cross-domain alignment between the multi-modal sensing-communication and natural language domains. A task-specific fine-tuning strategy with a tailored layer selection and activation scheme is designed to meet the demands of massive-scale, high-quality generation. Compared with conventional deep learning artificial intelligence generated content (AIGC) models, LLM4PG achieves more accurate pathloss map generation and stronger generalization across diverse conditions. Results show that LLM4PG attains an NMSE of 0.0454, outperforming the conventional AIGC model by over 2.90 dB, while its cross-condition generalization achieves an NMSE of 0.0492, exceeding the baseline by 4.52 dB.

eess.SP↗

arXiv2025

Towards Agentic Self-Learning LLMs in Search Environment

We study whether self-learning can scale LLM-based agents without relying on human-curated datasets or predefined rule-based rewards. Through controlled experiments in a search-agent setting, we identify two key determinants of scalable agent training: the source of reward signals and the scale of agent task data. We find that rewards from a Generative Reward Model (GRM) outperform rigid rule-based signals for open-domain learning, and that co-evolving the GRM with the policy further boosts performance. Increasing the volume of agent task data-even when synthetically generated-substantially enhances agentic capabilities. Building on these insights, we propose \textbf{Agentic Self-Learning} (ASL), a fully closed-loop, multi-role reinforcement learning framework that unifies task generation, policy execution, and evaluation within a shared tool environment and LLM backbone. ASL coordinates a Prompt Generator, a Policy Model, and a Generative Reward Model to form a virtuous cycle of harder task setting, sharper verification, and stronger solving. Empirically, ASL delivers steady, round-over-round gains, surpasses strong RLVR baselines (e.g., Search-R1) that plateau or degrade, and continues improving under zero-labeled-data conditions, indicating superior sample efficiency and robustness. We further show that GRM verification capacity is the main bottleneck: if frozen, it induces reward hacking and stalls progress; continual GRM training on the evolving data distribution mitigates this, and a small late-stage injection of real verification data raises the performance ceiling. This work establishes reward source and data scale as critical levers for open-domain agent learning and demonstrates the efficacy of multi-role co-evolution for scalable, self-improving agents. The data and code of this paper are released at https://github.com/forangel2014/Towards-Agentic-Self-Learning

cs.AI↗

arXiv2025

LLM4MG: Adapting Large Language Model for Multipath Generation via Synesthesia of Machines

Based on Synesthesia of Machines (SoM), a large language model (LLM) is adapted for multipath generation (LLM4MG) for the first time. Considering a typical sixth-generation (6G) vehicle-to-infrastructure (V2I) scenario, a new multi-modal sensing-communication dataset is constructed, named SynthSoM-V2I, including channel multipath information, millimeter wave (mmWave) radar sensory data, RGB-D images, and light detection and ranging (LiDAR) point clouds. Based on the SynthSoM-V2I dataset, the proposed LLM4MG leverages Large Language Model Meta AI (LLaMA) 3.2 for multipath generation via multi-modal sensory data. The proposed LLM4MG aligns the multi-modal feature space with the LLaMA semantic space through feature extraction and fusion networks. To further achieve general knowledge transfer from the pre-trained LLaMA for multipath generation via multi-modal sensory data, the low-rank adaptation (LoRA) parameter-efficient fine-tuning and propagation-aware prompt engineering are exploited. Simulation results demonstrate that the proposed LLM4MG outperforms conventional deep learning-based methods in terms of line-of-sight (LoS)/non-LoS (NLoS) classification with accuracy of 92.76%, multipath power/delay generation precision with normalized mean square error (NMSE) of 0.099/0.032, and cross-vehicular traffic density (VTD), cross-band, and cross-scenario generalization. The utility of the proposed LLM4MG is validated by real-world generalization. The necessity of high-precision multipath generation for system design is also demonstrated by channel capacity comparison.

eess.SP↗

arXiv2025

Synesthesia of Machines (SoM)-Empowered Wireless Image Transmission over Complex Dynamic Channel

Wireless image transmission underpins diverse networked intelligent services and becomes an increasingly critical issue. Existing works have shown that deep learning-based joint source-channel coding (JSCC) is an effective framework to balance image transmission fidelity and data overhead. However, these studies oversimplify the communication system as a mere pipeline with noise, failing to account for the complex dynamics of wireless channels and concrete physical-layer transmission process. To address these limitations, we propose a Synesthesia of Machines (SoM)-empowered Dynamic Channel Adaptive Transmission (DCAT) scheme, designed for practical implementation in real communication scenarios. Building upon the Swin Transformer backbone, our DCAT scheme demonstrates robust adaptability to time-selective fading and channel aging effects by effectively utilizing the physical-layer transmission characteristics of wireless channels. Comprehensive experimental results confirm that DCAT consistently achieves superior performance compared with JSCC baseline approaches across all conditions. Furthermore, our neural network architecture demonstrates high scalability due to its interpretable design, offering substantial potential for cost-efficient deployment in practical applications.

eess.SP↗

arXiv2025

Multi-Modal Intelligent Channel Modeling Framework for 6G-Enabled Networked Intelligent Systems

The design and technology development of 6G-enabled networked intelligent systems needs an accurate real-time channel model as the cornerstone. However, with the new requirements of 6G-enabled networked intelligent systems, the conventional channel modeling methods face many limitations. Fortunately, the multi-modal sensors equipped on the intelligent agents bring timely opportunities, i.e., the intelligent integration and mutually beneficial mechanism between communications and multi-modal sensing could be investigated based on the artificial intelligence (AI) technologies. In this case, the mapping relationship between physical environment and electromagnetic channel could be explored via Synesthesia of Machines (SoM). This article presents a novel multi-modal intelligent channel modeling (MMICM) framework for 6G-enabled networked intelligent systems, which establishes a nonlinear model between multi-modal sensing and channel characteristics, including large-scale and small-scale channel characteristics. The architecture and features of proposed intelligent modeling framework are expounded and the key technologies involved are also analyzed. Finally, the system-engaged applications and potential research directions of MMICM framework are outlined.

eess.SP↗

arXiv2025

Synesthesia of Machines (SoM)-Aided LiDAR Point Cloud Transmission for Collaborative Perception

Collaborative perception enables more accurate and comprehensive scene understanding by learning how to share information between agents, with LiDAR point clouds providing essential precise spatial data. Due to the substantial data volume generated by LiDAR sensors, efficient point cloud transmission is essential for low-latency multi-agent collaboration. In this work, we propose an efficient, robust and applicable LiDAR point cloud transmission system via the Synesthesia of Machines (SoM), termed LiDAR Point Cloud Feature Transmission (LPC-FT), to support collaborative perception among multiple agents. Specifically, we employ a density-preserving deep point cloud compression method that encodes the complete point cloud into a downsampled efficient representation. To mitigate the effects of the wireless channel, we design a channel encoder module based on self-attention to enhance LiDAR point cloud features and a feature fusion module based on cross-attention to integrate features from transceivers. Furthermore, we utilize the nonlinear activation layer and transfer learning to improve the training of deep neural networks in the presence the digital channel noise. Experimental results demonstrate that the proposed LPC-FT is more robust and effective than traditional octree-based compression followed by channel coding, and outperforms state-of-the-art deep learning-based compression techniques and existing semantic communication methods, reducing the Chamfer Distance by 30% and improving the PSNR by 1.9 dB on average. Owing to its superior reconstruction performance and robustness against channel variations, LPC-FT is expected to support collaborative perception tasks.

eess.SP↗

arXiv2025

LLM4SG: Adapting Large Language Model for Scatterer Generation via Synesthesia of Machines

In this paper, a novel large language model (LLM)-based method for scatterer generation (LLM4SG) is proposed for sixth-generation (6G) artificial intelligence (AI)-native communications. To provide a solid data foundation, we construct a new synthetic intelligent sensing-communication dataset for Synesthesia of Machines (SoM) in vehicle-to-vehicle (V2V) communications, named SynthSoM-V2V, covering multiple V2V scenarios with multiple frequency bands and multiple vehicular traffic densities (VTDs). Leveraging the powerful cross-modal representation capabilities of LLMs, LLM4SG is designed to capture the general mapping relationship from light detection and ranging (LiDAR) point clouds to electromagnetic scatterers via SoM. To address the inherent and significant differences across multi-modal data, synergistically optimized four-module architecture, i.e., preprocessor, embedding, backbone, and output modules, are designed by considering sensing characteristics and electromagnetic propagation. The embedding module achieves effective cross-domain alignment of the sensing-communication domain and the natural language domain.The backbone network is adapted in a task-guided manner with low rank adaptation (LoRA), where a carefully selected subset of layers is fine tuned to preserve general knowledge and reduce training cost. The proposed LLM4SG is evaluated for scatterer generation by benchmarking against ray-tracing (RT) and conventional deep learning models. Simulation results demonstrate that the proposed LLM4SG achieves superior performance in both full-sample and cross-condition generalization testing. It significantly outperforms conventional deep learning models across different frequency bands, scenarios, and VTDs, and demonstrates the capability to provide the massive and high-quality channel small-scale fading data required by AI-native 6G systems.

eess.SP↗

arXiv2025

Synesthesia of Machines (SoM)-Based Task-Driven MIMO System for Image Transmission

To support cooperative perception (CP) of networked mobile agents in dynamic scenarios, the efficient and robust transmission of sensory data is a critical challenge. Deep learning-based joint source-channel coding (JSCC) has demonstrated promising results for image transmission under adverse channel conditions, outperforming traditional rule-based codecs. While recent works have explored to combine JSCC with the widely adopted multiple-input multiple-output (MIMO) technology, these approaches are still limited to the discrete-time analog transmission (DTAT) model and simple tasks. Given the limited performance of existing MIMO JSCC schemes in supporting complex CP tasks for networked mobile agents with digital MIMO communication systems, this paper presents a Synesthesia of Machines (SoM)-based task-driven MIMO system for image transmission, referred to as SoM-MIMO. By leveraging the structural properties of the feature pyramid for perceptual tasks and the channel properties of the closed-loop MIMO communication system, SoM-MIMO enables efficient and robust digital MIMO transmission of images. Experimental results have shown that compared with two JSCC baseline schemes, our approach achieves average mAP improvements of 6.30 and 10.48 across all SNR levels, while maintaining identical communication overhead.

eess.SP↗

arXiv2025

WiFo-CF: Wireless Foundation Model for CSI Feedback

Deep learning-based channel state information (CSI) feedback schemes demonstrate strong compression capabilities but are typically constrained to fixed system configurations, limiting their generalization and flexibility. To address this challenge, WiFo-CF, a novel wireless foundation model tailored for CSI feedback, is proposed, uniquely accommodating heterogeneous configurations such as varying channel dimensions, feedback rates, and data distributions within a unified framework through its key innovations: (1) a multi-user, multi-rate self-supervised pre-training strategy; and (2) a Mixture of Shared and Routed Expert (S-R MoE) architecture. Supporting the large-scale pre-training of WiFo-CF is the first heterogeneous channel feedback dataset, whose diverse patterns enable the model to achieve superior performance on both in-distribution and out-of-distribution data across simulated and real-world scenarios. Furthermore, the learned representations effectively facilitate adaptation to downstream tasks such as CSI-based indoor localization, validating WiFo-CF's scalability and deployment potential.

eess.SP↗

arXiv2025

Quantum teleportation of an elemental silicon nanophotonic CNOT gate

Large-scale quantum computers possess the capacity to effectively tackle practical problems that can be insurmountable for classical computers. The main challenge in building these quantum computers is to realize scalable modules for remote qubits and entanglement. By assembling small, specialized parts into a larger architecture, the modular approach mitigates complexity and uncertainty. Such a distributed architecture requires non-local quantum gate operations between remote qubits. An essential method for implementing such operations, known as quantum gate teleportation, requires only local operations, classical communication, and shared entanglement. Till today, the quantum gate teleportation using a photonic chip has remained elusive. Here we experimentally demonstrate the quantum teleportation of an on-chip controlled-NOT (CNOT) gate, assisted with the scalable silicon chip platform, high-fidelity local quantum logic gates, linear optical components, post-selected entanglement, and coincidence measurements from photonic qubits. First, we measure and characterize our teleported chip-scale CNOT gate with an average truth table fidelity of 93.1 +- 0.3%. Second, for different input polarization states, we obtain an average quantum state fidelity of 87.0 +- 2.2% with our teleported on-chip CNOT gate. Third, we use our non-local CNOT gate for remote entanglement creation of four Bell states, with an average quantum state fidelity of 86.2 +- 0.8%. Fourthly, we fully characterize our teleported on-chip CNOT gate with a quantum process fidelity 83.1 +- 2.0%, and an average non-local CNOT gate fidelity of 86.5 +- 2.2%. Our teleported photonic on-chip quantum logic gate could be extended both to multiple qubits and chip-scale modules towards fault-tolerant and large-scale distributed quantum computation.

quant-ph↗

arXiv2025

Evaluation of Geolocation Capabilities of Multimodal Large Language Models and Analysis of Associated Privacy Risks

Objectives: The rapid advancement of Multimodal Large Language Models (MLLMs) has significantly enhanced their reasoning capabilities, enabling a wide range of intelligent applications. However, these advancements also raise critical concerns regarding privacy and ethics. MLLMs are now capable of inferring the geographic location of images -- such as those shared on social media or captured from street views -- based solely on visual content, thereby posing serious risks of privacy invasion, including doxxing, surveillance, and other security threats. Methods: This study provides a comprehensive analysis of existing geolocation techniques based on MLLMs. It systematically reviews relevant litera-ture and evaluates the performance of state-of-the-art visual reasoning models on geolocation tasks, particularly in identifying the origins of street view imagery. Results: Empirical evaluation reveals that the most advanced visual large models can successfully localize the origin of street-level imagery with up to $49\%$ accuracy within a 1-kilometer radius. This performance underscores the models' powerful capacity to extract and utilize fine-grained geographic cues from visual data. Conclusions: Building on these findings, the study identifies key visual elements that contribute to suc-cessful geolocation, such as text, architectural styles, and environmental features. Furthermore, it discusses the potential privacy implications associated with MLLM-enabled geolocation and discuss several technical and policy-based coun-termeasures to mitigate associated risks. Our code and dataset are available at https://github.com/zxyl1003/MLLM-Geolocation-Evaluation.

cs.CV↗

arXiv2025

Synesthesia of Machines (SoM)-Enhanced Sub-THz ISAC Transmission for Air-Ground Network

Integrated sensing and communication (ISAC) within sub-THz frequencies is crucial for future air-ground networks, but unique propagation characteristics and hardware limitations present challenges in optimizing ISAC performance while increasing operational latency. This paper introduces a multi-modal sensing fusion framework inspired by synesthesia of machine (SoM) to enhance sub-THz ISAC transmission. By exploiting inherent degrees of freedom in sub-THz hardware and channels, the framework optimizes the radio-frequency environment. Squint-aware beam management is developed to improve air-ground network adaptability, enabling three-dimensional dynamic ISAC links. Leveraging multi-modal information, the framework enhances ISAC performance and reduces latency. Visual data rapidly localizes users and targets, while a customized multi-modal learning algorithm optimizes the hybrid precoder. A new metric provides comprehensive performance evaluation, and extensive experiments demonstrate that the proposed scheme significantly improves ISAC efficiency.

eess.SP↗

arXiv2025

Foundation Model Empowered Synesthesia of Machines (SoM): AI-native Intelligent Multi-Modal Sensing-Communication Integration

To support future intelligent multifunctional sixth-generation (6G) wireless communication networks, Synesthesia of Machines (SoM) is proposed as a novel paradigm for artificial intelligence (AI)-native intelligent multi-modal sensing-communication integration. However, existing SoM system designs rely on task-specific AI models and face challenges such as scarcity of massive high-quality datasets, constrained modeling capability, poor generalization, and limited universality. Recently, foundation models (FMs) have emerged as a new deep learning paradigm and have been preliminarily applied to SoM-related tasks, but a systematic design framework is still lacking. In this paper, we for the first time present a systematic categorization of FMs for SoM system design, dividing them into general-purpose FMs, specifically large language models (LLMs), and SoM domain-specific FMs, referred to as wireless foundation models. Furthermore, we derive key characteristics of FMs in addressing existing challenges in SoM systems and propose two corresponding roadmaps, i.e., LLM-based and wireless foundation model-based design. For each roadmap, we provide a framework containing key design steps as a guiding pipeline and several representative case studies of FM-empowered SoM system design. Specifically, we propose LLM-based path loss generation (LLM4PG) and scatterer generation (LLM4SG) schemes, and wireless channel foundation model (WiCo) for SoM mechanism exploration, LLM-based wireless multi-task SoM transceiver (LLM4WM) and wireless foundation model (WiFo) for SoM-enhanced transceiver design, and wireless cooperative perception foundation model (WiPo) for SoM-enhanced cooperative perception, demonstrating the significant superiority of FMs over task-specific models. Finally, we summarize and highlight potential directions for future research.

eess.SP↗