arXiv subjects

Ning Wang

Publications and source records attributed to Ning Wang.

At least 109 records · Page 6Linked to original sources

arXiv2025

Towards Practical Operation of Deep Reinforcement Learning Agents in Real-World Network Management at Open RAN Edges

Deep Reinforcement Learning (DRL) has emerged as a powerful solution for meeting the growing demands for connectivity, reliability, low latency and operational efficiency in advanced networks. However, most research has focused on theoretical analysis and simulations, with limited investigation into real-world deployment. To bridge the gap and support practical DRL deployment for network management, we first present an orchestration framework that integrates ETSI Multi-access Edge Computing (MEC) with Open RAN, enabling seamless adoption of DRL-based strategies across different time scales while enhancing agent lifecycle management. We then identify three critical challenges hindering DRL's real-world deployment, including (1) asynchronous requests from unpredictable or bursty traffic, (2) adaptability and generalization across heterogeneous topologies and evolving service demands, and (3) prolonged convergence and service interruptions due to exploration in live operational environments. To address these challenges, we propose a three-fold solution strategy: (a) advanced time-series integration for handling asynchronized traffic, (b) flexible architecture design such as multi-agent DRL and incremental learning to support heterogeneous scenarios, and (c) simulation-driven deployment with transfer learning to reduce convergence time and service disruptions. Lastly, the feasibility of the MEC-O-RAN architecture is validated on an urban-wide testing infrastructure, and two real-world use cases are presented, showcasing the three identified challenges and demonstrating the effectiveness of the proposed solutions.

cs.NI↗

arXiv2025

An Energy Efficient Design of Hybrid NOMA Based on Hybrid SIC with Power Adaptation

Recently, hybrid non-orthogonal multiple access (H-NOMA) technology, which effectively utilizes both NOMA and orthogonal multiple access (OMA) technologies through flexible resource allocation in a single transmission, has demonstrated immense potential for enhancing the performance of wireless communication systems. To further release the potential of HNOMA, this paper proposes a novel design of H-NOMA which jointly incorporates hybrid successive interference cancellation (HSIC) and power adaptation (PA) in the NOMA transmission phase. To reveal the potential of the proposed HSIC-PA aided H-NOMA scheme, closed-form expression for the probability of the event that H-NOMA can achieve a higher data rate than pure OMA by consuming less energy is rigorously derived. Furthermore, the asymptotic analysis demonstrates that the probability of the proposed H-NOMA scheme approaches 1 in the high signal-to-noise ratio (SNR) regime without any constraints on either users' target rates or transmit power ratios. This represents a significant improvement over conventional H-NOMA schemes, which require specific restrictive conditions to achieve probability 1 at high SNRs as shown in existing work. The above observation indicates that with less energy consumption, the proposed HSIC-PA aided H-NOMA can achieve a higher data rate than pure OMA with probability 1 at high SNRs, and hence a higher energy efficiency. Finally, numerical results are provided to verify the accuracy of the analysis and also demonstrate the superior performance of the proposed H-NOMA scheme.

eess.SP↗

arXiv2025

Artificial intelligence in drug discovery: A comprehensive review with a case study on hyperuricemia, gout arthritis, and hyperuricemic nephropathy

This paper systematically reviews recent advances in artificial intelligence (AI), with a particular focus on machine learning (ML), across the entire drug discovery pipeline. Due to the inherent complexity, escalating costs, prolonged timelines, and high failure rates of traditional drug discovery methods, there is a critical need to comprehensively understand how AI/ML can be effectively integrated throughout the full process. Currently available literature reviews often narrowly focus on specific phases or methodologies, neglecting the dependence between key stages such as target identification, hit screening, and lead optimization. To bridge this gap, our review provides a detailed and holistic analysis of AI/ML applications across these core phases, highlighting significant methodological advances and their impacts at each stage. We further illustrate the practical impact of these techniques through an in-depth case study focused on hyperuricemia, gout arthritis, and hyperuricemic nephropathy, highlighting real-world successes in molecular target identification and therapeutic candidate discovery. Additionally, we discuss significant challenges facing AI/ML in drug discovery and outline promising future research directions. Ultimately, this review serves as an essential orientation for researchers aiming to leverage AI/ML to overcome existing bottlenecks and accelerate drug discovery.

cs.AI↗

arXiv2025

Advancing Embodied Agent Security: From Safety Benchmarks to Input Moderation

Embodied agents exhibit immense potential across a multitude of domains, making the assurance of their behavioral safety a fundamental prerequisite for their widespread deployment. However, existing research predominantly concentrates on the security of general large language models, lacking specialized methodologies for establishing safety benchmarks and input moderation tailored to embodied agents. To bridge this gap, this paper introduces a novel input moderation framework, meticulously designed to safeguard embodied agents. This framework encompasses the entire pipeline, including taxonomy definition, dataset curation, moderator architecture, model training, and rigorous evaluation. Notably, we introduce EAsafetyBench, a meticulously crafted safety benchmark engineered to facilitate both the training and stringent assessment of moderators specifically designed for embodied agents. Furthermore, we propose Pinpoint, an innovative prompt-decoupled input moderation scheme that harnesses a masked attention mechanism to effectively isolate and mitigate the influence of functional prompts on moderation tasks. Extensive experiments conducted on diverse benchmark datasets and models validate the feasibility and efficacy of the proposed approach. The results demonstrate that our methodologies achieve an impressive average detection accuracy of 94.58%, surpassing the performance of existing state-of-the-art techniques, alongside an exceptional moderation processing time of merely 0.002 seconds per instance.

cs.AI↗

arXiv2025

Quantitative Analysis of Performance Drop in DeepSeek Model Quantization

Recently, there is a high demand for deploying DeepSeek-R1 and V3 locally, possibly because the official service often suffers from being busy and some organizations have data privacy concerns. While single-machine deployment offers infrastructure simplicity, the models' 671B FP8 parameter configuration exceeds the practical memory limits of a standard 8-GPU machine. Quantization is a widely used technique that helps reduce model memory consumption. However, it is unclear what the performance of DeepSeek-R1 and V3 will be after being quantized. This technical report presents the first quantitative evaluation of multi-bitwidth quantization across the complete DeepSeek model spectrum. Key findings reveal that 4-bit quantization maintains little performance degradation versus FP8 while enabling single-machine deployment on standard NVIDIA GPU devices. We further propose DQ3_K_M, a dynamic 3-bit quantization method that significantly outperforms traditional Q3_K_M variant on various benchmarks, which is also comparable with 4-bit quantization (Q4_K_M) approach in most tasks. Moreover, DQ3_K_M supports single-machine deployment configurations for both NVIDIA H100/A100 and Huawei 910B. Our implementation of DQ3\_K\_M is released at https://github.com/UnicomAI/DeepSeek-Eval, containing optimized 3-bit quantized variants of both DeepSeek-R1 and DeepSeek-V3.

cs.LG↗

arXiv2025

FR-Mamba: Time-Series Physical Field Reconstruction Based on State Space Model

Physical field reconstruction (PFR) aims to predict the state distribution of physical quantities (e.g., velocity, pressure, and temperature) based on limited sensor measurements. It plays a critical role in domains such as fluid dynamics and thermodynamics. However, existing deep learning methods often fail to capture long-range temporal dependencies, resulting in suboptimal performance on time-evolving physical systems. To address this, we propose FR-Mamba, a novel spatiotemporal flow field reconstruction framework based on state space modeling. Specifically, we design a hybrid neural network architecture that combines Fourier Neural Operator (FNO) and State Space Model (SSM) to capture both global spatial features and long-range temporal dependencies. We adopt Mamba, a recently proposed efficient SSM architecture, to model long-range temporal dependencies with linear time complexity. In parallel, the FNO is employed to capture non-local spatial features by leveraging frequency-domain transformations. The spatiotemporal representations extracted by these two components are then fused to reconstruct the full-field distribution of the physical system. Extensive experiments demonstrate that our approach significantly outperforms existing PFR methods in flow field reconstruction tasks, achieving high-accuracy performance on long sequences.

cs.LG↗

arXiv2025

Investigating and Enhancing the Robustness of Large Multimodal Models Against Temporal Inconsistency

Large Multimodal Models (LMMs) have recently demonstrated impressive performance on general video comprehension benchmarks. Nevertheless, for broader applications, the robustness of their temporal analysis capability needs to be thoroughly investigated yet predominantly ignored. Motivated by this, we propose a novel temporal robustness benchmark (TemRobBench), which introduces temporal inconsistency perturbations separately at the visual and textual modalities to assess the robustness of models. We evaluate 16 mainstream LMMs and find that they exhibit over-reliance on prior knowledge and textual context in adversarial environments, while ignoring the actual temporal dynamics in the video. To mitigate this issue, we design panoramic direct preference optimization (PanoDPO), which encourages LMMs to incorporate both visual and linguistic feature preferences simultaneously. Experimental results show that PanoDPO can effectively enhance the model's robustness and reliability in temporal analysis.

cs.CV↗

arXiv2025

Quantifying the Capability Boundary of DeepSeek Models: An Application-Driven Performance Analysis

DeepSeek-R1, known for its low training cost and exceptional reasoning capabilities, has achieved state-of-the-art performance on various benchmarks. However, detailed evaluations for DeepSeek Series models from the perspective of real-world applications are lacking, making it challenging for users to select the most suitable DeepSeek models for their specific needs. To address this gap, we presents the first comprehensive evaluation of the DeepSeek and its related models (including DeepSeek-V3, DeepSeek-R1, DeepSeek-R1-Distill-Qwen series, DeepSeek-R1-Distill-Llama series, their corresponding 4-bit quantized models, and the reasoning model QwQ-32B) using our enhanced A-Eval benchmark, A-Eval-2.0. Our systematic analysis reveals several key insights: (1) Given identical model architectures and training data, larger parameter models demonstrate superior performance, aligning with the scaling law. However, smaller models may achieve enhanced capabilities when employing optimized training strategies and higher-quality data; (2) Reasoning-enhanced model show significant performance gains in logical reasoning tasks but may underperform in text understanding and generation tasks; (3) As the data difficulty increases, distillation or reasoning enhancements yield higher performance gains for the models. Interestingly, reasoning enhancements can even have a negative impact on simpler problems; (4) Quantization impacts different capabilities unevenly, with significant drop on logical reasoning and minimal impact on text generation. Based on these results and findings, we design an model selection handbook enabling users to select the most cost-effective models without efforts.

cs.AI↗

arXiv2025

Safety Evaluation and Enhancement of DeepSeek Models in Chinese Contexts

DeepSeek-R1, renowned for its exceptional reasoning capabilities and open-source strategy, is significantly influencing the global artificial intelligence landscape. However, it exhibits notable safety shortcomings. Recent research conducted by Robust Intelligence, a subsidiary of Cisco, in collaboration with the University of Pennsylvania, revealed that DeepSeek-R1 achieves a 100\% attack success rate when processing harmful prompts. Furthermore, multiple security firms and research institutions have identified critical security vulnerabilities within the model. Although China Unicom has uncovered safety vulnerabilities of R1 in Chinese contexts, the safety capabilities of the remaining distilled models in the R1 series have not yet been comprehensively evaluated. To address this gap, this study utilizes the comprehensive Chinese safety benchmark CHiSafetyBench to conduct an in-depth safety evaluation of the DeepSeek-R1 series distilled models. The objective is to assess the safety capabilities of these models in Chinese contexts both before and after distillation, and to further elucidate the adverse effects of distillation on model safety. Building on these findings, we implement targeted safety enhancements for the entire DeepSeek-R1 model series. Evaluation results indicate that the enhanced models achieve significant improvements in safety while maintaining reasoning capabilities without notable degradation. We open-source the safety-enhanced models at https://github.com/UnicomAI/DeepSeek-R1-Safe to serve as a valuable resource for future research and optimization of DeepSeek models.

cs.CL↗

arXiv2025

Demonstration of low-overhead quantum error correction codes

Quantum computers hold the potential to surpass classical computers in solving complex computational problems. However, the fragility of quantum information and the error-prone nature of quantum operations make building large-scale, fault-tolerant quantum computers a prominent challenge. To combat errors, pioneering experiments have demonstrated a variety of quantum error correction codes. Yet, most of these codes suffer from low encoding efficiency, and their scalability is hindered by prohibitively high resource overheads. Here, we report the demonstration of two low-overhead quantum low-density parity-check (qLDPC) codes, a distance-4 bivariate bicycle code and a distance-3 qLDPC code, on our latest superconducting processor, Kunlun, featuring 32 long-range-coupled transmon qubits. Utilizing a two-dimensional architecture with overlapping long-range couplers, we demonstrate simultaneous measurements of all nonlocal weight-6 stabilizers via the periodic execution of an efficient syndrome extraction circuit. We achieve a logical error rate per logical qubit per cycle of $(8.91 \pm 0.17)\%$ for the distance-4 bivariate bicycle code with four logical qubits and $(7.77 \pm 0.12)\%$ for the distance-3 qLDPC code with six logical qubits. Our results establish the feasibility of implementing various qLDPC codes with long-range coupled superconducting processors, marking a crucial step towards large-scale low-overhead quantum error correction.

quant-ph↗

arXiv2025

Safety Evaluation of DeepSeek Models in Chinese Contexts

Recently, the DeepSeek series of models, leveraging their exceptional reasoning capabilities and open-source strategy, is reshaping the global AI landscape. Despite these advantages, they exhibit significant safety deficiencies. Research conducted by Robust Intelligence, a subsidiary of Cisco, in collaboration with the University of Pennsylvania, revealed that DeepSeek-R1 has a 100\% attack success rate when processing harmful prompts. Additionally, multiple safety companies and research institutions have confirmed critical safety vulnerabilities in this model. As models demonstrating robust performance in Chinese and English, DeepSeek models require equally crucial safety assessments in both language contexts. However, current research has predominantly focused on safety evaluations in English environments, leaving a gap in comprehensive assessments of their safety performance in Chinese contexts. In response to this gap, this study introduces CHiSafetyBench, a Chinese-specific safety evaluation benchmark. This benchmark systematically evaluates the safety of DeepSeek-R1 and DeepSeek-V3 in Chinese contexts, revealing their performance across safety categories. The experimental results quantify the deficiencies of these two models in Chinese contexts, providing key insights for subsequent improvements. It should be noted that, despite our efforts to establish a comprehensive, objective, and authoritative evaluation benchmark, the selection of test samples, characteristics of data distribution, and the setting of evaluation criteria may inevitably introduce certain biases into the evaluation results. We will continuously optimize the evaluation benchmark and periodically update this report to provide more comprehensive and accurate assessment outcomes. Please refer to the latest version of the paper for the most recent evaluation results and conclusions.

cs.CL↗

arXiv2025

Direct evidence of intrinsic Mott state and its layer-parity oscillation in a breathing kagome crystal down to monolayer

We report direct spectroscopic evidence of correlation-driven Mott states in layered Nb$_3$Cl$_8$ through combining scanning tunneling microscopy (STM) and dynamical mean-field theory. The Hubbard bands persist down to monolayer, providing the definitive evidence for the Mottness in Nb$_3$Cl$_8$. While the size of the Mott gap remains almost constant across all layers, a striking layer-parity-dependent oscillation emerges in the local density of states (LDOS) between even (n = 2,4,6) and odd layers (n = 1,3,5), which arises from the dimerization and correlation modulation of the obstructed atomic states, respectively. Our conclusions are supported by a critical technical advance in atomic-scale LDOS mapping for highly insulating systems. This work provides the definitive experimental verification of correlation-driven Mott ground states in Nb3Cl8 while establishing a general protocol for investigating the interplay of electronic correlation and interlayer coupling in layered insulators by using low-temperature STM technique.

cond-mat.str-el↗

arXiv2025

Self-supervised surface-related multiple suppression with multidimensional convolution

Surface-related multiples pose significant challenges in seismic data processing, often obscuring primary reflections and reducing imaging quality. Traditional methods rely on computationally expensive algorithms, the prior knowledge of subsurface model, or accurate wavelet estimation, while supervised learning approaches require clean labels, which are impractical for real data. Thus, we propose a self-supervised learning framework for surface-related multiple suppression, leveraging multi-dimensional convolution to generate multiples from the observed data and a two-stage training strategy comprising a warm-up and an iterative data refinement stage, so the network learns to remove the multiples. The framework eliminates the need for labeled data by iteratively refining predictions using multiples augmented inputs and pseudo-labels. Numerical examples demonstrate that the proposed method effectively suppresses surface-related multiples while preserving primary reflections. Migration results confirm its ability to reduce artifacts and improve imaging quality.

physics.geo-ph↗

arXiv2025

VeriDebug: A Unified LLM for Verilog Debugging via Contrastive Embedding and Guided Correction

Large Language Models (LLMs) have demonstrated remarkable potential in debugging for various programming languages. However, the application of LLMs to Verilog debugging remains insufficiently explored. Here, we present VeriDebug, an approach that integrates contrastive representation and guided correction capabilities for automated Verilog debugging. Unlike existing methods, VeriDebug employs an embedding-based technique to accurately retrieve internal information, followed by bug-fixing. VeriDebug unifies Verilog bug detection and correction through a shared parameter space. By simultaneously learning bug patterns and fixes, it streamlines debugging via contrastive embedding and guided correction. Empirical results show the efficacy of VeriDebug in enhancing Verilog debugging. Our VeriDebugLoc, Type model achieves 64.7 accuracy in bug fixing (Acc1), a significant improvement from the existing open-source SOTAs 11.3. This performance not only outperforms open-source alternatives but also exceeds larger closed-source models like GPT-3.5-turbo (36.6), offering a more accurate alternative to conventional debugging methods.

cs.SE↗

arXiv2025

Highly integrated broadband entropy source for quantum random number generators based on vacuum fluctuations

In this work, we designed and experimentally verified a highly integrated broadband entropy source for a quantum random number generator (QRNG) based on vacuum fluctuations. The core of the entropy source is a hybrid laser-and-silicon-photonics chip, which is only 6.3 $ \times $ 2.6 $ \times $ 1.5 mm$^{3}$ in size. A balanced homodyne detector based on cascaded radio-frequency amplifiers in the entropy source achieves a 3 dB bandwidth of 2.4 GHz and a common-mode rejection ratio above 25 dB. The quantum-to-classical-noise ratio is 9.51 dB at a photoelectron current of 1 mA. The noise equivalent power and equivalent transimpedance are 8.85$\,\text{pW}/\sqrt{\text{Hz}}$ , and 22.8 k$Ω$, respectively. After optimization using equalizer technology that eliminates the dependence of adjacent samples, the quantum random number generation rate reaches 67.9 Gbps under average conditional minimum entropy and 61.9 Gbps under the worst-case conditional minimum entropy. The developed hybrid chip enhances the integrability and speed of QRNG entropy sources based on vacuum fluctuations.

quant-ph↗

arXiv2025

RepNet-VSR: Reparameterizable Architecture for High-Fidelity Video Super-Resolution

As a fundamental challenge in visual computing, video super-resolution (VSR) focuses on reconstructing highdefinition video sequences from their degraded lowresolution counterparts. While deep convolutional neural networks have demonstrated state-of-the-art performance in spatial-temporal super-resolution tasks, their computationally intensive nature poses significant deployment challenges for resource-constrained edge devices, particularly in real-time mobile video processing scenarios where power efficiency and latency constraints coexist. In this work, we propose a Reparameterizable Architecture for High Fidelity Video Super Resolution method, named RepNet-VSR, for real-time 4x video super-resolution. On the REDS validation set, the proposed model achieves 27.79 dB PSNR when processing 180p to 720p frames in 103 ms per 10 frames on a MediaTek Dimensity NPU. The competition results demonstrate an excellent balance between restoration quality and deployment efficiency. The proposed method scores higher than the previous champion algorithm of MAI video super-resolution challenge.

eess.IV↗

arXiv2025

Insights from Verification: Training a Verilog Generation LLM with Reinforcement Learning with Testbench Feedback

Large language models (LLMs) have shown strong performance in Verilog generation from natural language description. However, ensuring the functional correctness of the generated code remains a significant challenge. This paper introduces a method that integrates verification insights from testbench into the training of Verilog generation LLMs, aligning the training with the fundamental goal of hardware design: functional correctness. The main obstacle in using LLMs for Verilog code generation is the lack of sufficient functional verification data, particularly testbenches paired with design specifications and code. To address this problem, we introduce an automatic testbench generation pipeline that decomposes the process and uses feedback from the Verilog compiler simulator (VCS) to reduce hallucination and ensure correctness. We then use the testbench to evaluate the generated codes and collect them for further training, where verification insights are introduced. Our method applies reinforcement learning (RL), specifically direct preference optimization (DPO), to align Verilog code generation with functional correctness by training preference pairs based on testbench outcomes. In evaluations on VerilogEval-Machine, VerilogEval-Human, RTLLM v1.1, RTLLM v2, and VerilogEval v2, our approach consistently outperforms state-of-the-art baselines in generating functionally correct Verilog code. We open source all training code, data, and models at https://anonymous.4open.science/r/VeriPrefer-E88B.

cs.AR↗

arXiv2025

Large Language Model for Verilog Generation with Code-Structure-Guided Reinforcement Learning

Recent advancements in large language models (LLMs) have sparked significant interest in the automatic generation of Register Transfer Level (RTL) designs, particularly using Verilog. Current research on this topic primarily focuses on pre-training and instruction tuning, but the effectiveness of these methods is constrained by the limited availability of training data, as public Verilog code is far less abundant than software code. In particular, these methods struggle to effectively capture Verilog parallel code structures, which fundamentally differ from the imperative, sequential control flow typical in most software programming languages. This paper introduces VeriSeek, an LLM enhanced by reinforcement learning using a limited amount of high-quality training data to achieve high Verilog code generation performance. Our reinforcement learning approach employs code structure information as feedback signals to refine the pre-trained model, enabling it to effectively learn important patterns from Verilog code with parallel structures. Experiments show that VeriSeek outperforms state-of-the-art methods across multiple benchmarks.

cs.AR↗