Searcharxiv⌕ Search

arXiv subjects

Chang Wu

Publications and source records attributed to Chang Wu.

At least 19 recordsLinked to original sources
arXiv2026

Optimal Non-Adaptive Vantage Point Selection

We study the \emph{vantage point selection} problem, introduced by Ashvinkumar, Chowdhury, Gao, Goswami, Mitchell, and Polishchuk [WADS'25] to model the problem of estimating bottleneck capacities on the Internet. The input is a weighted undirected graph with unique shortest paths where every edge has a distinct unknown \emph{capacity}. When the algorithm \emph{queries} a vertex $v$, it reveals the minimum-capacity edge on the shortest path from $v$ to every other vertex reachable from $v$. The goal is to maximize the total number of revealed edges. The quality of an algorithm is measured by its competitive ratio against an optimal algorithm that knows all edge capacities a priori. We first consider the foundational single-query setting, where both the algorithm and the optimal algorithm are restricted to a single query. There is a trivial upper bound of $O(n)$ on the competitive ratio and the best known lower bound was $\tilde{\Omega}(\sqrt{n})$. We provide an algorithm and matching lower bound (up to polylogarithmic factors) showing that the best possible competitive ratio is $\tilde{\Theta}(n^{2/3})$. Furthermore, we extend our results to the general setting where the optimal algorithm is allowed $k$ queries and our algorithm is allowed $\alpha k$ queries for $\alpha\geq 1$. We present a randomized non-adaptive algorithm and matching lower bound (up to polylogarithmic factors) showing that the best possible expected competitive ratio for non-adaptive algorithms is the following surprisingly complex bound: $$ \tilde{\Theta}\left( \min\left\{ \frac{n}{\alpha k}, \max\left( \sqrt{\frac{n}{\alpha}}, \frac{n^{2/3}}{\alpha k^{1/3}} \right) \right\} \right). $$

cs.DS↗
arXiv2026

EasyOPD: An Easy-to-use On-Policy Distillation Framework for Large Language Models

Conventional language-model distillation often relies on fixed teacher-generated data, which may not cover the states encountered by an evolving student policy. On-policy distillation (OPD) instead collects teacher or evaluator supervision on student-generated rollouts. However, existing OPD methods differ substantially in supervision form, tokenizer compatibility, teacher access, and supervision granularity, leading to fragmented implementations that are difficult to reproduce and extend. We present \textsc{EasyOPD}, an on-policy distillation framework built on verl, a distributed reinforcement-learning framework for large language models. \textsc{EasyOPD} separates user-side configuration, method-specific supervision logic, and verl-based execution. Its method modules connect to the shared backend through extension boundaries for loss construction, rollout metadata, reward processing, tokenizer alignment, and teacher-side computation. We instantiate representative methods for three OPD settings -- cross-tokenizer OPD, on-policy self-distillation, and step-wise OPD. Experiments on reasoning, code-generation, scientific-knowledge, and tool-use benchmarks show that these implementations can be executed through the same verl-based backend while retaining their method-specific objectives and task-dependent performance profiles. We release \textsc{EasyOPD} with runnable YAML configurations, documentation, and an installable demonstration package and video.

cs.CL↗
arXiv2026

PolicyAlign: Direct Policy-Based Safety Alignment for Large Language Models

Safety alignment of large language models (LLMs) typically depends on high-quality supervision data, such as safe demonstrations or preference pairs. However, in real-world deployment, emerging safety requirements are often specified as natural-language policies, while corresponding supervision data may be costly, delayed, or unavailable. This creates a mismatch between rapidly evolving safety policies and conventional data-driven alignment methods. To address this, we propose PolicyAlign, a simple yet effective framework for directly aligning LLMs with safety policies. Given a safety policy, PolicyAlign first synthesizes policy-violating instructions and then performs on-policy self-distillation to internalize policy-guided behavior. To improve training stability and data efficiency, we further introduce Policy-Sensitive Filtering, which selects instructions where the policy induces the largest behavioral shift. Experiments across multiple models show that PolicyAlign consistently improves safety while maintaining low over-refusal and preserving general capabilities. PolicyAlign also generalizes to medical, legal, and financial safety scenarios, highlighting its potential as a scalable and maintainable approach to policy-based LLM safety alignment. The code is released at https://github.com/Qwen-Applications/PolicyAlign.

cs.CL↗
arXiv2026

Kaiwu-PyTorch-Plugin: Bridging Deep Learning and Photonic Quantum Computing for Energy-Based Models and Active Sample Selection

This paper introduces the Kaiwu-PyTorch-Plugin (KPP) to bridge Deep Learning and Photonic Quantum Computing across multiple dimensions. KPP integrates the Coherent Ising Machine into the PyTorch ecosystem, addressing classical inefficiencies in Energy-Based Models. The framework facilitates quantum integration in three key aspects: accelerating Boltzmann sampling, optimizing training data via Active Sampling, and constructing hybrid architectures like QBM-VAE and Q-Diffusion. Empirical results on single-cell and OpenWebText datasets demonstrate KPPs ability to achieve SOTA performance, validating a comprehensive quantum-classical paradigm.

quant-ph↗
arXiv2026

Unsupervised dimensionality reduction of polarimetric data for pixel-wise pathological tissue differentiation

Extracellular matrix (ECM) constitutes a key basement structure to human organisms by acting as a complex network of large proteins and carbohydrates that provide structural support to surrounding cells. Remodeling in the extracellular matrix's structural fibers leads to insight into the development of diseases such as cancer, fibrosis and carcinoma. While standard tissues visualization in the ECM involves multiple lengthy histopathological staining protocols, Mueller matrix-based polarimetry provides label-free tissue slices' microstructural information and optical properties. This work aims to identify three types of fiber tissues commonly found in the ECM of gastrointestinal tissue specimens by analyzing their polarization properties. To address decomposition methods' reliance on restrictive hypotheses and inability with an individual polarization-based parameter to determine the nature of a given biological tissue; this study employs Uniform Manifold Approximation and Projection (UMAP) method to offer greater discriminative power and flexibility. Subsequently, polarization-based features will be extracted and compared between fiber regions statistically to discern potential diagnostic differences. By providing colorized images, this work aims to demonstrate the feasibility of distinguishing different fibers with polarization approach, offering insights for future clinical development while complementing existing staining methods for pathological tissue specimens.

physics.optics↗
arXiv2026

AgentNoiseBench: Benchmarking Robustness of Tool-Using LLM Agents Under Noisy Condition

Recent advances in large language models have enabled LLM-based agents to achieve strong performance on a variety of benchmarks. However, their performance in real-world deployments often that observed on benchmark settings, especially in complex and imperfect environments. This discrepancy largely arises because prevailing training and evaluation paradigms are typically built on idealized assumptions, overlooking the inherent stochasticity and noise present in real-world interactions. To bridge this gap, we introduce AgentNoiseBench, a framework for systematically evaluating the robustness of agentic models under noisy environments. We first conduct an in-depth analysis of biases and uncertainties in real-world scenarios and categorize environmental noise into two primary types: user-noise and tool-noise. Building on this analysis, we develop an automated pipeline that injects controllable noise into existing agent-centric benchmarks while preserving task solvability. Leveraging this pipeline, we perform extensive evaluations across a wide range of models with diverse architectures and parameter scales. Our results reveal consistent performance variations under different noise conditions, highlighting the sensitivity of current agentic models to realistic environmental perturbations.

cs.AI↗
arXiv2026

NOMA-Assisted Multi-BS MEC Networks for Delay-Sensitive and Computation-Intensive IoT Applications

The burgeoning and ubiquitous deployment of the Internet of Things (IoT) landscape struggles with ultra-low latency demands for computation-intensive tasks in massive connectivity scenarios. In this paper, we propose an innovative uplink non-orthogonal multiple access (NOMA)-assisted multi-base station (BS) mobile edge computing (BS-MEC) network tailored for massive IoT connectivity. To fulfill the quality-of-service (QoS) requirements of delay-sensitive and computation-intensive IoT applications, we formulate a joint task offloading, user grouping, and power allocation optimization problem with the overarching objective of minimizing the system's total delay, aiming to address issues of unbalanced subchannel access, inter-group interference, computational load disparities, and device heterogeneity. To effectively tackle this problem, we first reformulate task offloading and user grouping into a non-cooperative game model and propose an exact potential game-based joint decision-making (EPG-JDM) algorithm, which dynamically selects optimal task offloading and subchannel access decisions for each IoT device based on its channel conditions, thereby achieving the Nash Equilibrium. Then, we propose a majorization-minimization (MM)-based power allocation algorithm, which transforms the original subproblem into a tractable convex optimization paradigm. Extensive simulation experiments demonstrate that our proposed EPG-JDM algorithm significantly outperforms state-of-the-art decision-making algorithms and classic heuristic algorithms, yielding performance improvements of up to 19.3% and 14.7% in terms of total delay and power consumption, respectively.

cs.NI↗
arXiv2026

Nipping the Drift in the Bud: Retrospective Rectification for Robust Vision-Language Navigation

Vision-Language Navigation (VLN) requires embodied agents to interpret natural language instructions and navigate through complex continuous 3D environments. However, the dominant imitation learning paradigm suffers from exposure bias, where minor deviations during inference lead to compounding errors. While DAgger-style approaches attempt to mitigate this by correcting error states, we identify a critical limitation: Instruction-State Misalignment. Forcing an agent to learn recovery actions from off-track states often creates supervision signals that semantically conflict with the original instruction. In response to these challenges, we introduce BudVLN, an online framework that learns from on-policy rollouts by constructing supervision to match the current state distribution. BudVLN performs retrospective rectification via counterfactual re-anchoring and decision-conditioned supervision synthesis, using a geodesic oracle to synthesize corrective trajectories that originate from valid historical states, ensuring semantic consistency. Experiments on the standard R2R-CE and RxR-CE benchmarks demonstrate that BudVLN consistently mitigates distribution shift and achieves state-of-the-art performance in both Success Rate and SPL.

cs.RO↗
arXiv2025

3D-GSRD: 3D Molecular Graph Auto-Encoder with Selective Re-mask Decoding

Masked graph modeling (MGM) is a promising approach for molecular representation learning (MRL).However, extending the success of re-mask decoding from 2D to 3D MGM is non-trivial, primarily due to two conflicting challenges: avoiding 2D structure leakage to the decoder, while still providing sufficient 2D context for reconstructing re-masked atoms. To address these challenges, we propose 3D-GSRD: a 3D Molecular Graph Auto-Encoder with Selective Re-mask Decoding. The core innovation of 3D-GSRD lies in its Selective Re-mask Decoding(SRD), which re-masks only 3D-relevant information from encoder representations while preserving the 2D graph structures. This SRD is synergistically integrated with a 3D Relational-Transformer(3D-ReTrans) encoder alongside a structure-independent decoder. We analyze that SRD, combined with the structure-independent decoder, enhances the encoder's role in MRL. Extensive experiments show that 3D-GSRD achieves strong downstream performance, setting a new state-of-the-art on 7 out of 8 targets in the widely used MD17 molecular property prediction benchmark. The code is released at https://github.com/WuChang0124/3D-GSRD.

cs.LG↗
arXiv2025

AoI-Aware Task Offloading and Transmission Optimization for Industrial IoT Networks: A Branching Deep Reinforcement Learning Approach

In the Industrial Internet of Things (IIoT), the frequent transmission of large amounts of data over wireless networks should meet the stringent timeliness requirements. Particularly, the freshness of packet status updates has a significant impact on the system performance. In this paper, we propose an age-of-information (AoI)-aware multi-base station (BS) real-time monitoring framework to support extensive IIoT deployments. To meet the freshness requirements of IIoT, we formulate a joint task offloading and resource allocation optimization problem with the goal of minimizing long-term average AoI. Tackling the core challenges of combinatorial explosion in multi-BS decision spaces and the stochastic dynamics of IIoT systems is crucial, as these factors render traditional optimization methods intractable. Firstly, an innovative branching-based Dueling Double Deep Q-Network (Branching-D3QN) algorithm is proposed to effectively implement task offloading, which optimizes the convergence performance by reducing the action space complexity from exponential to linear levels. Then, an efficient optimization solution to resource allocation is proposed by proving the semi-definite property of the Hessian matrix of bandwidth and computation resources. Finally, we propose an iterative optimization algorithm for efficient joint task offloading and resource allocation to achieve optimal average AoI performance. Extensive simulations demonstrate that our proposed Branching-D3QN algorithm outperforms both state-of-the-art DRL methods and classical heuristics, achieving up to a 75% enhanced convergence speed and at least a 22% reduction in the long-term average AoI.

eess.SY↗
arXiv2025

Physiological Signal-Driven QoE Optimization for Wireless Virtual Reality Transmission

Abrupt resolution changes in virtual reality (VR) streaming can significantly impair the quality-of-experience (QoE) of users, particularly during transitions from high to low resolutions. Existing QoE models and transmission schemes inadequately address the perceptual impact of these shifts. To bridge this gap, this article proposes, for the first time, an innovative physiological signal-driven QoE modeling and optimization framework that fully leverages users' electroencephalogram (EEG), electrocardiogram (ECG), and skin activity signals. This framework precisely captures the temporal dynamics of physiological responses and resolution changes in VR streaming, enabling accurate quantification of resolution upgrades' benefits and downgrades' impacts. Integrated the proposed QoE framework into the radio access network (RAN) via a deep reinforcement learning (DRL) framework, adaptive transmission strategies have been implemented to allocate radio resources dynamically, which mitigates short-term channel fluctuations and adjusts frame resolution in response to channel variations caused by user mobility. By prioritizing long-term resolution while minimizing abrupt transitions, the proposed solution achieves an 88.7\% improvement in resolution and an 81.0\% reduction in handover over the baseline. Experimental results demonstrate the effectiveness of this physiological signal-driven strategy, underscoring the promise of edge AI in immersive media services.

cs.NI↗
arXiv2025

Search and Refine During Think: Facilitating Knowledge Refinement for Improved Retrieval-Augmented Reasoning

Large language models have demonstrated impressive reasoning capabilities but are inherently limited by their knowledge reservoir. Retrieval-augmented reasoning mitigates this limitation by allowing LLMs to query external resources, but existing methods often retrieve irrelevant or noisy information, hindering accurate reasoning. In this paper, we propose AutoRefine, a reinforcement learning post-training framework that adopts a new "search-and-refine-during-think" paradigm. AutoRefine introduces explicit knowledge refinement steps between successive search calls, enabling the model to iteratively filter, distill, and organize evidence before generating an answer. Furthermore, we incorporate tailored retrieval-specific rewards alongside answer correctness rewards using group relative policy optimization. Experiments on single-hop and multi-hop QA benchmarks demonstrate that AutoRefine significantly outperforms existing approaches, particularly in complex, multi-hop reasoning scenarios. Detailed analysis shows that AutoRefine issues frequent, higher-quality searches and synthesizes evidence effectively.

cs.CL↗
arXiv2025

CFP: Efficient Optimization of Intra-Operator Parallelism Plans for Large Model Training

Optimizing the parallel training of large models requires exploring intra-operator parallelism plans for a computation graph that typically contains tens of thousands of primitive operators. While the optimization of parallel data processing graphs has been extensively researched in database systems, the vast search space makes it challenging to apply traditional database query optimization methods and algorithms. This paper introduces CFP, an optimization system for intra-operator parallelism that significantly reduces the complexity of searching for parallelism plans by leveraging two structural patterns found in large models. First, we identify parallel-preserving subgraphs, which ensure that the optimal global plan assigns the same parallel strategy to all operators within the subgraph. This approach allows us to avoid enumerating all possible combinations of parallel strategies for these operators. Second, we recognize repetitive subgraph patterns within the large computational graph, enabling us to profile a moderate number of representative subgraphs and accurately estimate the cost of parallelism plans with low overhead. With the significantly reduced search space, we can employ dynamic programming to search for the optimized parallelism plan. In our experiments, we demonstrate that CFP achieves significant speedups compared to the state-of-the-art framework for large models like GPT and LLAMA.

cs.DC↗
arXiv2025

Topology-aware Microservice Architecture in Edge Networks: Deployment Optimization and Implementation

As a ubiquitous deployment paradigm, integrating microservice architecture (MSA) into edge networks promises to enhance the flexibility and scalability of services. However, it also presents significant challenges stemming from dispersed node locations and intricate network topologies. In this paper, we have proposed a topology-aware MSA characterized by a three-tier network traffic model encompassing the service, microservices, and edge node layers. This model meticulously characterizes the complex dependencies between edge network topologies and microservices, mapping microservice deployment onto link traffic to accurately estimate communication delay. Building upon this model, we have formulated a weighted sum communication delay optimization problem considering different types of services. Then, a novel topology-aware and individual-adaptive microservices deployment (TAIA-MD) scheme is proposed to solve the problem efficiently, which accurately senses the network topology and incorporates an individual-adaptive mechanism in a genetic algorithm to accelerate the convergence and avoid local optima. Extensive simulations show that, compared to the existing deployment schemes, TAIA-MD improves the communication delay performance by approximately 30% to 60% and effectively enhances the overall network performance. Furthermore, we implement the TAIA-MD scheme on a practical microservice physical platform. The experimental results demonstrate that TAIA-MD achieves superior robustness in withstanding link failures and network fluctuations.

cs.NI↗
arXiv2025

DMSA: A Decentralized Microservice Architecture for Edge Networks

The dispersed node locations and complex topologies of edge networks, combined with intricate dynamic microservice dependencies, render traditional centralized microservice architectures (MSAs) unsuitable. In this paper, we propose a decentralized microservice architecture (DMSA), which delegates scheduling functions from the control plane to edge nodes. DMSA redesigns and implements three core modules of microservice discovery, monitoring, and scheduling for edge networks to achieve precise awareness of instance deployments, low monitoring overhead and measurement errors, and accurate dynamic scheduling, respectively. Particularly, DMSA has customized a microservice scheduling scheme that leverages multi-port listening and zero-copy forwarding to guarantee high data forwarding efficiency. Moreover, a dynamic weighted multi-level load balancing algorithm is proposed to adjust scheduling dynamically with consideration of reliability, priority, and response delay. Finally, we have implemented a physical verification platform for DMSA. Extensive empirical results demonstrate that compared to state-of-the-art and traditional scheduling schemes, DMSA effectively counteracts link failures and network fluctuations, improving the service response delay and execution success rate by approximately $60\% \sim 75\%$ and $10\%\sim15\%$, respectively.

cs.NI↗
arXiv2024

Statistical QoS Provision in Business-Centric Networks

More refined resource management and Quality of Service (QoS) provisioning is a critical goal of wireless communication technologies. In this paper, we propose a novel Business-Centric Network (BCN) aimed at enabling scalable QoS provisioning, based on a cross-layer framework that captures the relationship between application, transport parameters, and channels. We investigate both continuous flow and event-driven flow models, presenting key QoS metrics such as throughput, delay, and reliability. By jointly considering power and bandwidth allocation, transmission parameters, and AP network topology across layers, we optimize weighted resource efficiency with statistical QoS provisioning. To address the coupling among parameters, we propose a novel deep reinforcement learning (DRL) framework, which is Collaborative Optimization among Heterogeneous Actors with Experience Sharing (COHA-ES). Power and sub-channel (SC) Actors representing multiple APs are jointly optimized under the unified guidance of a common critic. Additionally, we introduce a novel multithreaded experience-sharing mechanism to accelerate training and enhance rewards. Extensive comparative experiments validate the effectiveness of our DRL framework in terms of convergence and efficiency. Moreover, comparative analyses demonstrate the comprehensive advantages of the BCN structure in enhancing both spectral and energy efficiency.

cs.NI↗
arXiv2024

MSSP : A Versatile Multi-Scenario Adaptable Intelligent Robot Simulation Platform Based on LIDAR-Inertial Fusion

This letter presents a multi-scenario adaptable intelligent robot simulation platform based on LIDAR-inertial fusion, with three main features: (1 The platform includes an versatile robot model that can be freely controlled through manual control or autonomous tracking. This model is equipped with various types of LIDAR and Inertial Measurement Unit (IMU), providing ground truth information with absolute accuracy. (2 The platform provides a collection of simulation environments with diverse characteristic information and supports developers in customizing and modifying environments according to their needs. (3 The platform supports evaluation of localization performance for SLAM frameworks. Ground truth with absolute accuracy eliminates the inherent errors of global positioning sensors present in real experiments, facilitating detailed analysis and evaluation of the algorithms. By utilizing the simulation platform, developers can overcome the limitations of real environments and datasets, enabling fine-grained analysis and evaluation of mainstream SLAM algorithms in various environments. Experiments conducted in different environments and with different LIDARs demonstrate the wide applicability and practicality of our simulation platform. The implementation of the simulation platform is open-sourced on Github.

cs.RO↗