arXiv subjects

Yuyang Du

Publications and source records attributed to Yuyang Du.

30 records · Page 2Linked to original sources

arXiv2025

The Dual-use Dilemma in LLMs: Do Empowering Ethical Capacities Make a Degraded Utility?

Recent years have witnessed extensive efforts to enhance Large Language Models (LLMs) across various domains, alongside growing attention to their ethical implications. However, a critical challenge remains largely overlooked: LLMs must balance between rejecting harmful requests for safety and accommodating legitimate ones for utility. This paper presents a Direct Preference Optimization (DPO) based alignment framework that achieves better overall performance by addressing this ethical-utility trade-off, using chemical domain applications as a proof-of-concept. Our alignment pipeline starts with a GPT-assisted three-phase data generation scheme, in which we create LibraChemQA, a chemical question-answering dataset comprising 31.6k triplet instances. By incorporating an innovative balanced seed in the data generation process, our framework systematically considers both legitimate and illegitimate requests. The framework also introduces a rephrasing mechanism for efficient data augmentation that enhances the model's chemical comprehension. We further develop a novel hybrid evaluation scheme with LLM judges for precise assessment of both safety and utility. Experimental results demonstrate our model's substantial improvements in overall performance where both safety and utility are considered - the resulting model outperforms leading LLMs including Claude-3, GPT-4o, and LLaMA-3 by margins of 13.44%, 7.16%, and 7.10% respectively on our released benchmark. At the end of this paper, we analyze experimental results obtained from testing DeepSeek-R1 on our benchmark and reveal the critical ethical concerns raised by this highly acclaimed model. We highlight that the long Chain-of-Thought (CoT) reasoning process employed by DeepSeek-R1, as well as other LLMs distilled from it, introduces significant ethical vulnerabilities when exposed to users.

cs.CL↗

arXiv2024

LLM-Assisted Multi-Teacher Continual Learning for Visual Question Answering in Robotic Surgery

Visual question answering (VQA) is crucial for promoting surgical education. In practice, the needs of trainees are constantly evolving, such as learning more surgical types, adapting to different robots, and learning new surgical instruments and techniques for various surgeries. However, patient data privacy often restricts the availability of old data when updating the model, necessitating an exemplar-free continual learning (CL) setup. Prior CL studies overlooked two vital problems in the surgical domain: 1) large domain shifts from diverse surgical operations collected from multiple sources, and 2) severe data imbalance arising from the uneven presence of surgical instruments or activities. This paper proposes addressing these problems with a multimodal large language model (LLM) and an adaptive weight assignment methodology. We first develop a new multi-teacher CL framework that leverages a multimodal LLM as the additional teacher. The strong generalization ability of the LLM can bridge the knowledge gap when domain shifts and data imbalances occur. We then put forth a novel data processing method that transforms complex LLM embeddings into logits compatible with our CL framework. We further design an adaptive weight assignment approach that balances the generalization ability of the LLM and the domain expertise of the old CL model. Finally, to comprehensively test the effectiveness of our proposed method, we have also constructed two new surgical VQA datasets that are largely different from existing ones and could be valuable resources for future research. Extensive experimental results on the tested datasets demonstrate the superiority of our method to other advanced CL schemes.

cs.IR↗

arXiv2024

Rephrase and Contrast: Fine-Tuning Language Models for Enhanced Understanding of Communication and Computer Networks

Large language models (LLMs) are being widely researched across various disciplines, with significant recent efforts focusing on adapting LLMs for understanding of how communication networks operate. However, over-reliance on prompting techniques hinders the full exploitation of the generalization ability of these models, and the lack of efficient fine-tuning methods prevents the full realization of lightweight LLMs' potential. This paper addresses these challenges by introducing our Rephrase and Contrast (RaC) framework, an efficient fine-tuning framework. RaC enhances LLMs' comprehension and critical thinking abilities by incorporating question reformulation and contrastive analysis of correct and incorrect answers during the fine-tuning process. Experimental results demonstrate a 63.73% accuracy improvement over the foundational model when tested on a comprehensive networking problem set. Moreover, to efficiently construct the dataset for RaC fine-tuning, we develop a GPT-assisted data mining method for generating high-quality question-answer (QA) pairs; furthermore, we introduce ChoiceBoost, a data augmentation technique that expands dataset size while reducing answer-order bias. Apart from these technical innovations, we contribute to the networking community by open-sourcing valuable research resources, including: 1) the fine-tuned networking model referred to as RaC-Net, 2) the training dataset used for fine-tuning the model, 3) three testing problem sets of different difficulties to serve as benchmarks for future research, and 4) code associated with the above resources.

cs.CL↗

arXiv2024

LLMind: Orchestrating AI and IoT with LLM for Complex Task Execution

Task-oriented communications are an important element in future intelligent IoT systems. Existing IoT systems, however, are limited in their capacity to handle complex tasks, particularly in their interactions with humans to accomplish these tasks. In this paper, we present LLMind, an LLM-based task-oriented AI agent framework that enables effective collaboration among IoT devices, with humans communicating high-level verbal instructions, to perform complex tasks. Inspired by the functional specialization theory of the brain, our framework integrates an LLM with domain-specific AI modules, enhancing its capabilities. Complex tasks, which may involve collaborations of multiple domain-specific AI modules and IoT devices, are executed through a control script generated by the LLM using a Language-Code transformation approach, which first converts language descriptions to an intermediate finite-state machine (FSM) before final precise transformation to code. Furthermore, the framework incorporates a novel experience accumulation mechanism to enhance response speed and effectiveness, allowing the framework to evolve and become progressively sophisticated through continuing user and machine interactions.

cs.IT↗

arXiv2024

Addressing Out-of-Distribution Challenges in Image Semantic Communication Systems with Multi-modal Large Language Models

Semantic communication is a promising technology for next-generation wireless networks. However, the out-of-distribution (OOD) problem, where a pre-trained machine learning (ML) model is applied to unseen tasks that are outside the distribution of its training data, may compromise the integrity of semantic compression. This paper explores the use of multi-modal large language models (MLLMs) to address the OOD issue in image semantic communication. We propose a novel "Plan A - Plan B" framework that leverages the broad knowledge and strong generalization ability of an MLLM to assist a conventional ML model when the latter encounters an OOD input in the semantic encoding process. Furthermore, we propose a Bayesian optimization scheme that reshapes the probability distribution of the MLLM's inference process based on the contextual information of the image. The optimization scheme significantly enhances the MLLM's performance in semantic compression by 1) filtering out irrelevant vocabulary in the original MLLM output; and 2) using contextual similarities between prospective answers of the MLLM and the background information as prior knowledge to modify the MLLM's probability distribution during inference. Further, at the receiver side of the communication system, we put forth a "generate-criticize" framework that utilizes the cooperation of multiple MLLMs to enhance the reliability of image reconstruction.

eess.SP↗

arXiv2024

The Power of Large Language Models for Wireless Communication System Development: A Case Study on FPGA Platforms

Large language models (LLMs) have garnered significant attention across various research disciplines, including the wireless communication community. There have been several heated discussions on the intersection of LLMs and wireless technologies. While recent studies have demonstrated the ability of LLMs to generate hardware description language (HDL) code for simple computation tasks, developing wireless prototypes and products via HDL poses far greater challenges because of the more complex computation tasks involved. In this paper, we aim to address this challenge by investigating the role of LLMs in FPGA-based hardware development for advanced wireless signal processing. We begin by exploring LLM-assisted code refactoring, reuse, and validation, using an open-source software-defined radio (SDR) project as a case study. Through the case study, we find that an LLM assistant can potentially yield substantial productivity gains for researchers and developers. We then examine the feasibility of using LLMs to generate HDL code for advanced wireless signal processing, using the Fast Fourier Transform (FFT) algorithm as an example. This task presents two unique challenges: the scheduling of subtasks within the overall task and the multi-step thinking required to solve certain arithmetic problem within the task. To address these challenges, we employ in-context learning (ICL) and Chain-of-Thought (CoT) prompting techniques, culminating in the successful generation of a 64-point Verilog FFT module. Our results demonstrate the potential of LLMs for generalization and imitation, affirming their usefulness in writing HDL code for wireless communication systems. Overall, this work contributes to understanding the role of LLMs in wireless communication and motivates further exploration of their capabilities.

eess.SP↗

arXiv2024

Nonlinear Multi-Carrier System with Signal Clipping: Measurement, Analysis, and Optimization

Signal clipping is a classic technique for reducing peak-to-average power ratio (PAPR) in orthogonal frequency division multiplexing (OFDM) systems. It has been widely applied in consumer electronic devices owing to its low complexity and high efficiency. Although clipping reduces the nonlinear distortion caused by power amplifiers (PAs), it induces additional clipping distortion. Optimizing the joint system performance with consideration of both PA nonlinearity and clipping distortion remains an open problem due to the complex PA modeling. In this paper, we analyze the PA nonlinearity through the Bessel-Fourier PA (BFPA) model and simplify its power expression using inter-modulation product (IMP) analysis. We derive expressions of the receiver signal-to-noise ratio (SNR) and system symbol error rate (SER) for the nonlinear clipped OFDM system. With the derivations, we investigate the optimal system setting to achieve the SER lower bound in a practical OFDM system that considers both PA nonlinearity and clipping distortion. The methods and results presented in this paper can serve as a useful reference for the system-level optimization of clipped OFDM systems with nonlinear PA.

eess.SP↗

arXiv2023

AMD-DBSCAN: An Adaptive Multi-density DBSCAN for datasets of extremely variable density

DBSCAN has been widely used in density-based clustering algorithms. However, with the increasing demand for Multi-density clustering, previous traditional DSBCAN can not have good clustering results on Multi-density datasets. In order to address this problem, an adaptive Multi-density DBSCAN algorithm (AMD-DBSCAN) is proposed in this paper. An improved parameter adaptation method is proposed in AMD-DBSCAN to search for multiple parameter pairs (i.e., Eps and MinPts), which are the key parameters to determine the clustering results and performance, therefore allowing the model to be applied to Multi-density datasets. Moreover, only one hyperparameter is required for AMD-DBSCAN to avoid the complicated repetitive initialization operations. Furthermore, the variance of the number of neighbors (VNN) is proposed to measure the difference in density between each cluster. The experimental results show that our AMD-DBSCAN reduces execution time by an average of 75% due to lower algorithm complexity compared with the traditional adaptive algorithm. In addition, AMD-DBSCAN improves accuracy by 24.7% on average over the state-of-the-art design on Multi-density datasets of extremely variable density, while having no performance loss in Single-density scenarios. Our code and datasets are available at https://github.com/AlexandreWANG915/AMD-DBSCAN.

cs.DB↗

arXiv2023

Reliable Packet Detection for Random Access Networks: Analysis, Benchmark, and Optimization

This paper reexamines and fundamentally improves the Schmidl-and-Cox (S&C) algorithm, which is extensively used for packet detection in wireless networks, and enhances its adaptability for multi-antenna receivers. First, we introduce a new "compensated autocorrelation" metric, providing a more analytically tractable solution with precise expressions for false-alarm and missed-detection probabilities. Second, this paper proposes the Pareto comparison principle for fair benchmarking packet-detection algorithms, considering both false alarms and missed detections simultaneously. Third, with the Pareto benchmarking scheme, we experimentally confirm that the performance of S&C can be greatly improved by taking only the real part and discarding the imaginary part of the autocorrelation, leading to the novel real-part S&C (RP-S&C) scheme. Fourth, and perhaps most importantly, we utilize the compensated autocorrelation metric we newly put forth to extend the single-antenna algorithm to multi-antenna scenarios through a weighted-sum approach. Two optimization problems, minimizing false-alarm and missed-detection probabilities respectively, are formulated and solutions are provided. Our experimental results reveal that the optimal weights for false alarms (WFA) scheme is more desirable than the optimal weights for missed detections (WMD) due to its simplicity, reliability, and superior performance. This study holds considerable implications for the design and deployment of packet-detection schemes in random-access networks.

cs.NI↗

arXiv2022

Consistency of Implicit and Explicit Features Matters for Monocular 3D Object Detection

Low-cost autonomous agents including autonomous driving vehicles chiefly adopt monocular 3D object detection to perceive surrounding environment. This paper studies 3D intermediate representation methods which generate intermediate 3D features for subsequent tasks. For example, the 3D features can be taken as input for not only detection, but also end-to-end prediction and/or planning that require a bird's-eye-view feature representation. In the study, we found that in generating 3D representation previous methods do not maintain the consistency between the objects' implicit poses in the latent space, especially orientations, and the explicitly observed poses in the Euclidean space, which can substantially hurt model performance. To tackle this problem, we present a novel monocular detection method, the first one being aware of the poses to purposefully guarantee that they are consistent between the implicit and explicit features. Additionally, we introduce a local ray attention mechanism to efficiently transform image features to voxels at accurate 3D locations. Thirdly, we propose a handcrafted Gaussian positional encoding function, which outperforms the sinusoidal encoding function while retaining the benefit of being continuous. Results show that our method improves the state-of-the-art 3D intermediate representation method by 3.15%. We are ranked 1st among all the reported monocular methods on both 3D and BEV detection benchmark on KITTI leaderboard as of th result's submission time.

cs.CV↗

arXiv2022

Efficient FFT Computation in IFDMA Transceivers

Interleaved Frequency Division Multiple Access (IFDMA) has the salient advantage of lower Peak-to-Average Power Ratio (PAPR) than its competitors like Orthogonal FDMA (OFDMA). A recent research effort put forth a new IFDMA transceiver design significantly less complex than conventional IFDMA transceivers. The new IFDMA transceiver design reduces the complexity by exploiting a certain correspondence between the IFDMA signal processing and the Cooley-Tukey IFFT/FFT algorithmic structure so that IFDMA streams can be inserted/extracted at different stages of an IFFT/FFT module according to the sizes of the streams. Although the prior work has laid down the theoretical foundation for the new IFDMA transceiver's structure, the practical realization of the transceiver on specific hardware with resource constraints has not been carefully investigated. This paper is an attempt to fill the gap. Specifically, this paper puts forth a heuristic algorithm called multi-priority scheduling (MPS) to schedule the execution of the butterfly computations in the IFDMA transceiver with the constraint of a limited number of hardware processors. The resulting FFT computation, referred to as MPS-FFT, has a much lower computation time than conventional FFT computation when applied to the IFDMA signal processing. Importantly, we derive a lower bound for the optimal IFDMA FFT computation time to benchmark MPS-FFT. Our experimental results indicate that when the number of hardware processors is a power of two: 1) MPS-FFT has near-optimal computation time; 2) MPS-FFT incurs less than 44.13\% of the computation time of the conventional pipelined FFT.

eess.SP↗

arXiv2021

Flow Sampling: Network Monitoring in Large-Scale Software-Defined IoT Networks

Software-defined Internet-of-Things networking (SDIoT) greatly simplifies the network monitoring in large-scale IoT networks by per-flow sampling, wherein the controller keeps track of all the active flows in the network and samples the IoT devices on each flow path to collect real-time flow statistics. There is a tradeoff between the controller's sampling preference and the balancing of loads among devices. On the one hand, the controller may prefer to sample some of the IoT devices on the flow path because they yield more accurate flow statistics. On the other hand, it is desirable to sample the devices uniformly so that their energy consumptions and lifespan are balanced. This paper formulates the flow sampling problem in large-scale SDIoT networks by means of a Markov decision process and devises policies that strike a good balance between these two goals. Three classes of policies are investigated: the optimal policy, the state-independent policies, and the index policies (including the Whittle index and a second-order index policies). The second-order index policy is the most desired policy among all: 1) in terms of performance, it is on an equal footing with the Whittle index policy, and outperforms the state-independent policies by much; 2) in terms of complexity, it is much simpler than the optimal policy, and is comparable to state-independent policies and the Whittle index policy; 3) in terms of realizability, it requires no prior information on the network dynamics, hence is much easier to implement in practice.

eess.SY↗