arXiv subjects

Zihan Chen

Publications and source records attributed to Zihan Chen.

At least 55 records · Page 3Linked to original sources

arXiv2026

Federated Inference for Heterogeneous LLM Communication and Collaboration

Given the limited performance and efficiency of on-device Large Language Models (LLMs), the collaborations between multiple LLMs enable desirable performance enhancements, in which data, tokens, and model weights could be shared across LLMs. This process is constrained by task-oriented QoS demands, privacy requirements, and inherent system heterogeneity. In view of the above challenge and to fully exploit the on-device inference capabilities, we present a novel federated inference framework in this position paper, termed federated refinement \texttt{FedRefine}. This framework presents a new paradigm for heterogeneous LLMs collaboratively performing inference with communicating KV caches in a privacy-preserving manner. Some numerical results are provided to highlight the superiority of \texttt{FedRefine}. Several interesting topics are also highlighted for future research. By exploring the LLM-native communications, we wish to provide a new paradigm for this broad area.

cs.DC↗

arXiv2026

Lean Clients, Full Accuracy: Hybrid Zeroth- and First-Order Split Federated Learning

Split Federated Learning (SFL) enables collaborative training between resource-constrained edge devices and a compute-rich server. Communication overhead is a central issue in SFL and can be mitigated with auxiliary networks. Yet, the fundamental client-side computation challenge remains, as back-propagation requires substantial memory and computation costs, severely limiting the scale of models that edge devices can support. To enable more resource-efficient client computation and reduce the client-server communication, we propose HERON-SFL, a novel hybrid optimization framework that integrates zeroth-order (ZO) optimization for local client training while retaining first-order (FO) optimization on the server. With the assistance of auxiliary networks, ZO updates enable clients to approximate local gradients using perturbed forward-only evaluations per step, eliminating memory-intensive activation caching and avoiding explicit gradient computation in the traditional training process. Leveraging the low effective rank assumption, we theoretically prove that HERON-SFL's convergence rate is independent of model dimensionality, addressing a key scalability concern common to ZO algorithms. Empirically, on ResNet training and language model (LM) fine-tuning tasks, HERON-SFL matches benchmark accuracy while reducing client peak memory by up to 64% and client-side compute cost by up to 33% per step, substantially expanding the range of models that can be trained or adapted on resource-limited devices.

cs.LG↗

arXiv2026

Machine Learning-Driven Creep Law Discovery Across Alloy Compositional Space

Hihg-temperature creep characterization of structural alloys traditionally relies on serial uniaxial tests, which are highly inefficient for exploring the large search space of alloy compositions and for material discovery. Here, we introduce a machine-learning-assisted, high-throughput framework for creep law identification based on a dimple array bulge instrument (DABI) configuration, which enables parallel creep testing of 25 dimples, each fabricated from a different alloy, in a single experiment. Full-field surface displacements of dimples undergoing time-dependent creep-induced bulging under inert gas pressure are measured by 3D digital image correlation. We train a recurrent neural network (RNN) as a surrogate model, mapping creep parameters and loading conditions to the time-dependent deformation response of DABI. Coupling this surrogate with a particle swarm optimization scheme enables rapid and global inverse identification with sparsity regularization of creep parameters from experiment displacement-time histories. In addition, we propose a phenomenological creep law with a time-dependent stress exponent that captures the sigmoidal primary creep observed in wrought INCONEL 625 and extracts its temperature dependence from DABI test at multiple temperatures. Furthermore, we employ a general creep law combining several conventional forms together with regularized inversion to identify the creep laws for 47 additional Fe-, Ni-, and Co-rich alloys and to automatically select the dominant functional form for each alloy. This workflow combined with DABI experiment provides a quantitative, high-throughput creep characterization platform that is compatible with data mining, composition-property modeling, and nonlinear structural optimization with creep behavior across a large alloy design space.

cond-mat.mtrl-sci↗

arXiv2025

Toward Intelligent and Secure Cloud: Large Language Model Empowered Proactive Defense

The rapid evolution of cloud computing technologies and the increasing number of cloud applications have provided numerous benefits in our daily lives. However, the diversity and complexity of different components pose a significant challenge to cloud security, especially when dealing with sophisticated and advanced cyberattacks such as Denial of Service (DoS). Recent advancements in the large language models (LLMs) offer promising solutions for security intelligence. By exploiting the powerful capabilities in language understanding, data analysis, task inference, action planning, and code generation, we present LLM-PD, a novel defense architecture that proactively mitigates various DoS threats in cloud networks. LLM-PD can efficiently make decisions through comprehensive data analysis and sequential reasoning, as well as dynamically create and deploy actionable defense mechanisms. Furthermore, it can flexibly self-evolve based on experience learned from previous interactions and adapt to new attack scenarios without additional training. Our case study on three distinct DoS attacks demonstrates its remarkable ability in terms of defense effectiveness and efficiency when compared with other existing methods.

cs.CR↗

arXiv2025

Hyperion: Hierarchical Scheduling for Parallel LLM Acceleration in Multi-tier Networks

LLMs are increasingly executed in edge where limited GPU memory and heterogeneous computation jointly constrain deployment which motivates model partitioning and request scheduling. In this setting, minimizing latency requires addressing the tight coupling between model placement and request scheduling across heterogeneous nodes, as suboptimal decisions in one domain can negate benefits in the other. In this paper, we propose Hyperion, a hierarchical two-stage framework that jointly optimizes partitioning and scheduling for pipelined LLM inference. Hyperion minimizes latency by balancing resources across tiers without requiring model retraining or incurring significant runtime overhead. Leveraging the timescale difference between partitioning and request arrivals, Stage 1 performs offline, inter-tier partitioning via a Hyperion Split with Dynamic Programming (HypSplit-DP) procedure to produce balanced stage times under tier capacity and memory constraints; to adapt to time-varying load, Stage 2 performs online, intra-tier scheduling with a lightweight Hyperion Scheduling for Real-Time (HypSched-RT) that maps each request to the best available node using real-time estimates of queue length and effective capacity. Experiments with Phi-3-medium demonstrate that Hyperion reduces latency by up to 52.1% (vs. GPipe) and 31.2% (vs. HEFT). Furthermore, Hyperion exhibits superior scalability for long-sequence generation, maintaining 44.5% lower latency and higher GPU utilization.

cs.DC↗

arXiv2025

From Static to Adaptive Defense: Federated Multi-Agent Deep Reinforcement Learning-Driven Moving Target Defense Against DoS Attacks in UAV Swarm Networks

The proliferation of UAVs has enabled a wide range of mission-critical applications and is becoming a cornerstone of low-altitude networks, supporting smart cities, emergency response, and more. However, the open wireless environment, dynamic topology, and resource constraints of UAVs expose low-altitude networks to severe DoS threats. Traditional defense approaches, which rely on fixed configurations or centralized decision-making, cannot effectively respond to the rapidly changing conditions in UAV swarm environments. To address these challenges, we propose a novel federated multi-agent deep reinforcement learning (FMADRL)-driven moving target defense (MTD) framework for proactive DoS mitigation in low-altitude networks. Specifically, we design lightweight and coordinated MTD mechanisms, including leader switching, route mutation, and frequency hopping, to disrupt attacker efforts and enhance network resilience. The defense problem is formulated as a multi-agent partially observable Markov decision process, capturing the uncertain nature of UAV swarms under attack. Each UAV is equipped with a policy agent that autonomously selects MTD actions based on partial observations and local experiences. By employing a policy gradient-based algorithm, UAVs collaboratively optimize their policies via reward-weighted aggregation. Extensive simulations demonstrate that our approach significantly outperforms state-of-the-art baselines, achieving up to a 34.6% improvement in attack mitigation rate, a reduction in average recovery time of up to 94.6%, and decreases in energy consumption and defense cost by as much as 29.3% and 98.3%, respectively, under various DoS attack strategies. These results highlight the potential of intelligent, distributed defense mechanisms to protect low-altitude networks, paving the way for reliable and scalable low-altitude economy.

cs.CR↗

arXiv2025

Adaptive Digital Twin of Sheet Metal Forming via Proper Orthogonal Decomposition-Based Koopman Operator with Model Predictive Control

Digital Twin (DT) technologies are transforming manufacturing by enabling real-time prediction, monitoring, and control of complex processes. Yet, applying DT to deformation-based metal forming remains challenging because of the strongly coupled spatial-temporal behavior and the nonlinear relationship between toolpath and material response. For instance, sheet-metal forming by the English wheel, a highly flexible but artisan-dependent process, still lacks digital counterparts that can autonomously plan and adapt forming strategies. This study presents an adaptive DT framework that integrates Proper Orthogonal Decomposition (POD) for physics-aware dimensionality reduction with a Koopman operator for representing nonlinear system in a linear lifted space for the real-time decision-making via model predictive control (MPC). To accommodate evolving process conditions or material states, an online Recursive Least Squares (RLS) algorithm is introduced to update the operator coefficients in real time, enabling continuous adaptation of the DT model as new deformation data become available. The proposed framework is experimentally demonstrated on a robotic English Wheel sheet metal forming system, where deformation fields are measured and modeled under varying toolpaths. Results show that the adaptive DT is capable of controlling the forming process to achieve the given target shape by effectively capturing non-stationary process behaviors. Beyond this case study, the proposed framework establishes a generalizable approach for interpretable, adaptive, and computationally-efficient DT of nonlinear manufacturing systems, bridging reduced-order physics representations with data-driven adaptability to support autonomous process control and optimization.

eess.SY↗

arXiv2025

AnyMAC: Cascading Flexible Multi-Agent Collaboration via Next-Agent Prediction

Recent progress in large language model (LLM)-based multi-agent collaboration highlights the power of structured communication in enabling collective intelligence. However, existing methods largely rely on static or graph-based inter-agent topologies, lacking the potential adaptability and flexibility in communication. In this work, we propose a new framework that rethinks multi-agent coordination through a sequential structure rather than a graph structure, offering a significantly larger topology space for multi-agent communication. Our method focuses on two key directions: (1) Next-Agent Prediction, which selects the most suitable agent role at each step, and (2) Next-Context Selection (NCS), which enables each agent to selectively access relevant information from any previous step. Together, these components construct task-adaptive communication pipelines that support both role flexibility and global information flow. Extensive evaluations across multiple benchmarks demonstrate that our approach achieves superior performance while substantially reducing communication overhead.

cs.AI↗

arXiv2025

Separate the Wheat from the Chaff: Winnowing Down Divergent Views in Retrieval Augmented Generation

Retrieval-augmented generation (RAG) enhances large language models (LLMs) by integrating external knowledge sources to address their limitations in accessing up-to-date or specialized information. A natural strategy to increase the likelihood of retrieving relevant information is to expand the number of retrieved documents. However, involving more documents could introduce significant noise, as many documents may be irrelevant or misleading, thereby reducing the overall accuracy of the generated responses. To overcome the challenge associated with handling a larger number of documents, we propose WinnowRAG, a novel RAG framework designed to systematically filter out noisy documents while preserving valuable content -- a process we refer to as winnowing. WinnowRAG operates in two stages: In Stage I, we perform query-aware clustering to group similar documents and form distinct topic clusters. Each cluster is assigned to an LLM agent for generating a unique answer. In Stage II, we perform winnowing, wherein a critic LLM evaluates the outputs of multiple agents and iteratively separates useful documents from noisy ones. To retain useful documents when discarding agents, we propose two strategic merging techniques to ensure that only relevant knowledge is used for generating the final response. Crucially, WinnowRAG is model-agnostic and does not require any model fine-tuning, making it easily adaptable to various tasks. Extensive experiments on various realistic datasets demonstrate the effectiveness of WinnowRAG over state-of-the-art baselines.

cs.CL↗

arXiv2025

From Cross-Task Examples to In-Task Prompts: A Graph-Based Pseudo-Labeling Framework for In-context Learning

The capability of in-context learning (ICL) enables large language models (LLMs) to perform novel tasks without parameter updates by conditioning on a few input-output examples. However, collecting high-quality examples for new or challenging tasks can be costly and labor-intensive. In this work, we propose a cost-efficient two-stage pipeline that reduces reliance on LLMs for data labeling. Our approach first leverages readily available cross-task examples to prompt an LLM and pseudo-label a small set of target task instances. We then introduce a graph-based label propagation method that spreads label information to the remaining target examples without additional LLM queries. The resulting fully pseudo-labeled dataset is used to construct in-task demonstrations for ICL. This pipeline combines the flexibility of cross-task supervision with the scalability of LLM-free propagation. Experiments across five tasks demonstrate that our method achieves strong performance while lowering labeling costs.

cs.AI↗

arXiv2025

Pinching-antenna-enabled Federated Learning: Tail Latency, Participation, and Convergence Analysis

Federated learning (FL) in wireless networks is limited by straggler delays from unpredictable channel conditions. In this paper, we investigate the pinching-antenna system (PASS), which dynamically 'pinches' the radiator along a dielectric waveguide to shorten the worst links. In synchronous FL (SFL), we prove that PASS shortens the worst-link distance, and it increases the on-time completion probability in asynchronous FL (AFL). Accordingly, SFL exhibits stochastic dominance on round time, while AFL yields explicit latency and participation gains. We then pair physical-layer (PHY)-aware sampling with error-feedback compression and prove that pinching raises the minimum inclusion probability, thus shrinking both the sampling variability and compression-induced floors in a Lyapunov analysis. Simulations demonstrate consistent wall clock speedups and markedly shorter latency tails. By addressing stragglers at their PHY root, PASS complements higher-layer scheduling and accelerates wireless FL in both SFL and AFL.

cs.IT↗

arXiv2025

GraphTOP: Graph Topology-Oriented Prompting for Graph Neural Networks

Graph Neural Networks (GNNs) have revolutionized the field of graph learning by learning expressive graph representations from massive graph data. As a common pattern to train powerful GNNs, the "pre-training, adaptation" scheme first pre-trains GNNs over unlabeled graph data and subsequently adapts them to specific downstream tasks. In the adaptation phase, graph prompting is an effective strategy that modifies input graph data with learnable prompts while keeping pre-trained GNN models frozen. Typically, existing graph prompting studies mainly focus on *feature-oriented* methods that apply graph prompts to node features or hidden representations. However, these studies often achieve suboptimal performance, as they consistently overlook the potential of *topology-oriented* prompting, which adapts pre-trained GNNs by modifying the graph topology. In this study, we conduct a pioneering investigation of graph prompting in terms of graph topology. We propose the first **Graph** **T**opology-**O**riented **P**rompting (GraphTOP) framework to effectively adapt pre-trained GNN models for downstream tasks. More specifically, we reformulate topology-oriented prompting as an edge rewiring problem within multi-hop local subgraphs and relax it into the continuous probability space through reparameterization while ensuring tight relaxation and preserving graph sparsity. Extensive experiments on five graph datasets under four pre-training strategies demonstrate that our proposed GraphTOP outshines six baselines on multiple node classification datasets. Our code is available at https://github.com/xbfu/GraphTOP.

cs.LG↗

arXiv2025

Navigating Sparsities in High-Dimensional Linear Contextual Bandits

High-dimensional linear contextual bandit problems remain a significant challenge due to the curse of dimensionality. Existing methods typically consider either the model parameters to be sparse or the eigenvalues of context covariance matrices to be (approximately) sparse, lacking general applicability due to the rigidity of conventional reward estimators. To overcome this limitation, a powerful pointwise estimator is introduced in this work that adaptively navigates both kinds of sparsity. Based on this pointwise estimator, a novel algorithm, termed HOPE, is proposed. Theoretical analyses demonstrate that HOPE not only achieves improved regret bounds in previously discussed homogeneous settings (i.e., considering only one type of sparsity) but also, for the first time, efficiently handles two new challenging heterogeneous settings (i.e., considering a mixture of two types of sparsity), highlighting its flexibility and generality. Experiments corroborate the superiority of HOPE over existing methods across various scenarios.

math.ST↗

arXiv2025

Voyager: An End-to-End Framework for Design-Space Exploration and Generation of DNN Accelerators

While deep neural networks (DNNs) have achieved state-of-the-art performance in fields from computer vision to natural language processing, efficiently running these computationally demanding models requires hardware accelerators. However, designing these accelerators is a time-consuming, labor-intensive process that does not scale well. While prior efforts have sought to automate DNN accelerator generation, they offer limited parameterization, cannot produce high-performance, tapeout-ready designs, provide limited support for datatypes and quantization schemes, and lack an integrated, end-to-end software compiler. This work proposes Voyager, a high-level synthesis (HLS)-based framework for design space exploration (DSE) and generation of DNN accelerators. Voyager overcomes the limitations of prior work by offering extensive configurability across technology nodes, clock frequencies, and scales, with customizable parameters such as number of processing elements, on-chip buffer sizes, and external memory bandwidth. Voyager supports a wider variety of datatypes and quantization schemes versus prior work, including both built-in floating-point, posit and integer formats, as well as user-defined formats with both per-tensor scaling and microscaling quantization. Voyager's PyTorch-based compiler efficiently maps networks end-to-end on the generated hardware, with support for quantization, fusion, and tiling. We evaluate Voyager on state-of-the-art vision and language models. Voyager enables fast DSE with full-dataset accuracy evaluation for datatypes and quantization schemes. Generated designs achieve a high utilization across models and scales, up to 99.8%, and outperform prior generators with up to 61% lower latency and 56% lower area. Compared to hand-optimized accelerators, Voyager achieves comparable performance, while offering much greater automation in design and workload mapping.

cs.AR↗

arXiv2025

ALLabel: Three-stage Active Learning for LLM-based Entity Recognition using Demonstration Retrieval

Many contemporary data-driven research efforts in the natural sciences, such as chemistry and materials science, require large-scale, high-performance entity recognition from scientific datasets. Large language models (LLMs) have increasingly been adopted to solve the entity recognition task, with the same trend being observed on all-spectrum NLP tasks. The prevailing entity recognition LLMs rely on fine-tuned technology, yet the fine-tuning process often incurs significant cost. To achieve a best performance-cost trade-off, we propose ALLabel, a three-stage framework designed to select the most informative and representative samples in preparing the demonstrations for LLM modeling. The annotated examples are used to construct a ground-truth retrieval corpus for LLM in-context learning. By sequentially employing three distinct active learning strategies, ALLabel consistently outperforms all baselines under the same annotation budget across three specialized domain datasets. Experimental results also demonstrate that selectively annotating only 5\%-10\% of the dataset with ALLabel can achieve performance comparable to the method annotating the entire dataset. Further analyses and ablation studies verify the effectiveness and generalizability of our proposal.

cs.CL↗

arXiv2025

Learning from Diverse Reasoning Paths with Routing and Collaboration

Advances in large language models (LLMs) significantly enhance reasoning capabilities but their deployment is restricted in resource-constrained scenarios. Knowledge distillation addresses this by transferring knowledge from powerful teacher models to compact and transparent students. However, effectively capturing the teacher's comprehensive reasoning is challenging due to conventional token-level supervision's limited scope. Using multiple reasoning paths per query alleviates this problem, but treating each path identically is suboptimal as paths vary widely in quality and suitability across tasks and models. We propose Quality-filtered Routing with Cooperative Distillation (QR-Distill), combining path quality filtering, conditional routing, and cooperative peer teaching. First, quality filtering retains only correct reasoning paths scored by an LLM-based evaluation. Second, conditional routing dynamically assigns paths tailored to each student's current learning state. Finally, cooperative peer teaching enables students to mutually distill diverse insights, addressing knowledge gaps and biases toward specific reasoning styles. Experiments demonstrate QR-Distill's superiority over traditional single- and multi-path distillation methods. Ablation studies further highlight the importance of each component including quality filtering, conditional routing, and peer teaching in effective knowledge transfer. Our code is available at https://github.com/LzyFischer/Distill.

cs.CL↗

arXiv2025

PRIME: Plasticity-Robust Incremental Model for Encrypted Traffic Classification in Dynamic Network Environments

With the continuous development of network environments and technologies, ensuring cyber security and governance is increasingly challenging. Network traffic classification(ETC) can analyzes attributes such as application categories and malicious intent, supporting network management services like QoS optimization, intrusion detection, and targeted billing. As the prevalence of traffic encryption increases, deep learning models are relied upon for content-agnostic analysis of packet sequences. However, the emergence of new services and attack variants often leads to incremental tasks for ETC models. To ensure model effectiveness, incremental learning techniques are essential; however, recent studies indicate that neural networks experience declining plasticity as tasks increase. We identified plasticity issues in existing incremental learning methods across diverse traffic samples and proposed the PRIME framework. By observing the effective rank of model parameters and the proportion of inactive neurons, the PRIME architecture can appropriately increase the parameter scale when the model's plasticity deteriorates. Experiments show that in multiple encrypted traffic datasets and different category increment scenarios, the PRIME architecture performs significantly better than other incremental learning algorithms with minimal increase in parameter scale.

cs.NI↗

arXiv2025

Court of LLMs: Evidence-Augmented Generation via Multi-LLM Collaboration for Text-Attributed Graph Anomaly Detection

The natural combination of intricate topological structures and rich textual information in text-attributed graphs (TAGs) opens up a novel perspective for graph anomaly detection (GAD). However, existing GAD methods primarily focus on designing complex optimization objectives within the graph domain, overlooking the complementary value of the textual modality, whose features are often encoded by shallow embedding techniques, such as bag-of-words or skip-gram, so that semantic context related to anomalies may be missed. To unleash the enormous potential of textual modality, large language models (LLMs) have emerged as promising alternatives due to their strong semantic understanding and reasoning capabilities. Nevertheless, their application to TAG anomaly detection remains nascent, and they struggle to encode high-order structural information inherent in graphs due to input length constraints. For high-quality anomaly detection in TAGs, we propose CoLL, a novel framework that combines LLMs and graph neural networks (GNNs) to leverage their complementary strengths. CoLL employs multi-LLM collaboration for evidence-augmented generation to capture anomaly-relevant contexts while delivering human-readable rationales for detected anomalies. Moreover, CoLL integrates a GNN equipped with a gating mechanism to adaptively fuse textual features with evidence while preserving high-order topological information. Extensive experiments demonstrate the superiority of CoLL, achieving an average improvement of 13.37% in AP. This study opens a new avenue for incorporating LLMs in advancing GAD.

cs.LG↗