arXiv subjects

Rui Zhang

Publications and source records attributed to Rui Zhang.

At least 217 records · Page 12Linked to original sources

arXiv2026

Prune2Drive: A Plug-and-Play Framework for Accelerating Vision-Language Models in Autonomous Driving

Vision-Language Models (VLMs) have emerged as a promising paradigm in autonomous driving (AD), providing a unified framework for perception and decision-making. However, their real-world deployment is hindered by significant computational overhead when processing high-resolution, multi-view images. This complexity stems from the massive number of visual tokens, which increases inference latency and memory consumption due to the quadratic complexity of self-attention. To address these challenges, we propose Prune2Drive, a plug-and-play visual token pruning framework for multi-view VLMs in AD. Prune2Drive introduces two core innovations: (i) a diversity-aware token selection mechanism that prioritizes semantic and spatial coverage across views, and (ii) a view-adaptive pruning controller that automatically learns optimal pruning ratios based on camera importance to downstream tasks. Unlike prior methods, Prune2Drive requires no model retraining or access to attention maps, ensuring compatibility with modern efficient attention implementations. Extensive experiments on the DriveLM and DriveLMM-o1 benchmarks demonstrate that Prune2Drive achieves significant speedups and memory savings with minimal performance impact. When retaining only 10% of visual tokens, our method achieves a 6.40x speedup in the prefilling phase and consumes only 13.4% of the original FLOPs, with a mere 3% average performance drop on the DriveLM benchmark. Code is available at: https://github.com/MinhaoXiong/Prune2Drive.git

cs.CV↗

arXiv2026

Nonreciprocal entanglement in exciton optomechanics with an optical parametric amplifier

We study nonreciprocal bipartite and tripartite entanglement in a spinning exciton-optomechanical system (EOMS) with an optical parametric amplifier (OPA). We demonstrate that nonreciprocal entanglement among photons, excitons, and phonons can be achieved under experimentally feasible parameters. We find that the nonreciprocal entanglement induced by Sagnac effects can be regulated through the OPA. Particularly, We show that the OPA significantly enhances photon-exciton entanglement and tripartite entanglement but weakens photon-phonon and exciton-phonon entanglement. Moreover, we find that the photon-exciton nonreciprocal entanglement not only can be generated at room temperature and even higher temperature but also exhibits highly robustness to cavity dissipation. Our works open a way to manipulate the room-temperature nonreciprocal entanglement, which may be useful for developing nonreciprocal quantum technologies.

quant-ph↗

arXiv2026

LLM4AD: A Platform for Algorithm Design with Large Language Model

We introduce LLM4AD, a unified Python platform for algorithm design (AD) with large language models (LLMs). LLM4AD is a generic framework with modularized blocks for search methods, algorithm design tasks, and LLM interface. The platform integrates numerous key methods and supports a wide range of algorithm design tasks across various domains including optimization, machine learning, and scientific discovery. We have also designed a unified evaluation sandbox to ensure a secure and robust assessment of algorithms. Additionally, we have compiled a comprehensive suite of support resources, including tutorials, examples, a user manual, online resources, and a dedicated graphical user interface (GUI) to enhance the usage of LLM4AD. We believe this platform will serve as a valuable tool for fostering future development in the merging research direction of LLM-assisted algorithm design.

cs.AI↗

arXiv2026

Towards Autonomous Memory Agents

Recent memory agents improve LLMs by extracting experiences and conversation history into an external storage. This enables low-overhead context assembly and online memory update without expensive LLM training. However, existing solutions remain passive and reactive; memory growth is bounded by information that happens to be available, while memory agents seldom seek external inputs in uncertainties. We propose autonomous memory agents that actively acquire, validate, and curate knowledge at a minimum cost. U-Mem materializes this idea via (i) a cost-aware knowledge-extraction cascade that escalates from cheap self/teacher signals to tool-verified research and, only when needed, expert feedback, and (ii) semantic-aware Thompson sampling to balance exploration and exploitation over memories and mitigate cold-start bias. On both verifiable and non-verifiable benchmarks, U-Mem consistently beats prior memory baselines and can surpass RL-based optimization, improving HotpotQA (Qwen2.5-7B) by 14.6 points and AIME25 (Gemini-2.5-flash) by 7.33 points.

cs.AI↗

arXiv2026

Turning Semantics into Topology: LLM-Driven Attribute Augmentation for Collaborative Filtering

Large Language Models (LLMs) have shown great potential for enhancing recommender systems through their extensive world knowledge and reasoning capabilities. However, effectively translating these semantic signals into traditional collaborative embeddings remains an open challenge. Existing approaches typically fall into two extremes: direct inference methods are computationally prohibitive for large-scale retrieval, while embedding-based methods primarily focus on unilateral feature augmentation rather than holistic collaborative signal enhancement. To bridge this gap, we propose Topology-Augmented Graph Collaborative Filtering (TAGCF), a novel framework that transforms semantic knowledge into topological connectivity. Unlike existing approaches that depend on textual features or direct interaction synthesis, TAGCF employs LLMs to infer interaction intents and underlying causal relationships from user-item pairs, representing these insights as intermediate attribute nodes within an enriched User-Attribute-Item (U-A-I) graph. Furthermore, to effectively model the heterogeneous relations in this augmented structure, we propose Adaptive Relation-weighted Graph Convolution (ARGC), which employs relation-specific prediction networks to dynamically estimate the importance of each relation type. Extensive experiments across multiple benchmark datasets and CF backbones demonstrate consistent improvements, with comprehensive evaluations including cold-start scenarios validating the effectiveness and robustness of our framework. All code will be made publicly available. For anonymous review, our code is available at the following anonymous link: https://anonymous.4open.science/r/AGCF-2441353190/.

cs.IR↗

arXiv2026

QiMeng-CodeV-R1: Reasoning-Enhanced Verilog Generation

Large language models (LLMs) trained via reinforcement learning with verifiable reward (RLVR) have achieved breakthroughs on tasks with explicit, automatable verification, such as software programming and mathematical problems. Extending RLVR to electronic design automation (EDA), especially automatically generating hardware description languages (HDLs) like Verilog from natural-language (NL) specifications, however, poses three key challenges: the lack of automated and accurate verification environments, the scarcity of high-quality NL-code pairs, and the prohibitive computation cost of RLVR. To this end, we introduce CodeV-R1, an RLVR framework for training Verilog generation LLMs. First, we develop a rule-based testbench generator that performs robust equivalence checking against golden references. Second, we propose a round-trip data synthesis method that pairs open-source Verilog snippets with LLM-generated NL descriptions, verifies code-NL-code consistency via the generated testbench, and filters out inequivalent examples to yield a high-quality dataset. Third, we employ a two-stage "distill-then-RL" training pipeline: distillation for the cold start of reasoning abilities, followed by adaptive DAPO, our novel RLVR algorithm that can reduce training cost by adaptively adjusting sampling rate. The resulting model, CodeV-R1-7B, achieves 68.6% and 72.9% pass@1 on VerilogEval v2 and RTLLM v1.1, respectively, surpassing prior state-of-the-art by 12~20%, while even exceeding the performance of 671B DeepSeek-R1 on RTLLM. We have released our model, training code, and dataset to facilitate research in EDA and LLM communities.

cs.LG↗

arXiv2026

To Reason or Not to: Selective Chain-of-Thought in Medical Question Answering

Objective: To improve the efficiency of medical question answering (MedQA) with large language models (LLMs) by avoiding unnecessary reasoning while maintaining accuracy. Methods: We propose Selective Chain-of-Thought (Selective CoT), an inference-time strategy that first predicts whether a question requires reasoning and generates a rationale only when needed. Two open-source LLMs (Llama-3.1-8B and Qwen-2.5-7B) were evaluated on four biomedical QA benchmarks-HeadQA, MedQA-USMLE, MedMCQA, and PubMedQA. Metrics included accuracy, total generated tokens, and inference time. Results: Selective CoT reduced inference time by 13-45% and token usage by 8-47% with minimal accuracy loss ($\leq$4\%). In some model-task pairs, it achieved both higher accuracy and greater efficiency than standard CoT. Compared with fixed-length CoT, Selective CoT reached similar or superior accuracy at substantially lower computational cost. Discussion: Selective CoT dynamically balances reasoning depth and efficiency by invoking explicit reasoning only when beneficial, reducing redundancy on recall-type questions while preserving interpretability. Conclusion: Selective CoT provides a simple, model-agnostic, and cost-effective approach for medical QA, aligning reasoning effort with question complexity to enhance real-world deployability of LLM-based clinical systems.

cs.CL↗

arXiv2026

Event-Triggered Gossip for Distributed Learning

While distributed learning offers a new learning paradigm for distributed network with no central coordination, it is constrained by communication bottleneck between nodes. We develop a new event-triggered gossip framework for distributed learning to reduce inter-node communication overhead. The framework introduces an adaptive communication control mechanism that enables each node to autonomously decide in a fully decentralized fashion when to exchange model information with its neighbors based on local model deviations. We analyze the ergodic convergence of the proposed framework under noconvex objectives and interpret the convergence guarantees under different triggering conditions. Simulation results show that the proposed framework achieves substantially lower communication overhead than the state-of-the-art distributed learning methods, reducing cumulative point-to-point transmissions by \textbf{71.61\%} with only a marginal performance loss, compared with the conventional full-communication baseline.

eess.SP↗

arXiv2026

A Survey on Reconfigurable and Movable Antennas for Wireless Communications and Sensing

Reconfigurable antennas (RAs) and movable antennas (MAs) have been recognized as promising technologies to enhance the performance of wireless communication and sensing systems by introducing additional degrees of freedom (DoFs) in tuning antenna radiation and/or placement. This paradigm shift from conventional non-reconfigurable/movable antennas offers tremendous new opportunities for realizing multi-functional, more adaptive, and efficient next-generation wireless networks. In this paper, we provide a comprehensive survey on the fundamentals, architectures, and applications of these two emerging antenna technologies. First, we provide a chronological overview of the parallel historical development of both RA and MA technologies. Next, we review and classify the state-of-the-art hardware architectures for implementing RAs and MAs, followed by a detailed comparison of their distinct mechanisms, performance metrics, and functionalities. Subsequently, we focus on various applications of RAs and MAs in wireless communication systems, analyzing their respective performance advantages and key design considerations such as mode selection, movement optimization, and channel acquisition. We also explore the significant roles of RAs and MAs in advancing wireless sensing and integrated sensing and communication (ISAC). Furthermore, we present numerical performance comparisons to illustrate the distinct characteristics and complementary advantages of RA and MA systems. Finally, we outline key challenges and identify promising future research directions to inspire further innovations in this burgeoning field.

eess.SP↗

arXiv2026

UAV Swarm Enabled Aerial Movable Antenna System for Low-Altitude Economy: From Far-Field to Near-Field Communication

Unmanned aerial vehicle (UAV) with the intrinsic three-dimensional (3D) mobility provides an ideal platform for implementing aerial movable antenna (AMA) system enabled by UAV swarm cooperation. Besides, AMA system is readily to achieve an extremely large-scale array aperture, rendering the conventional far-field uniform plane wave (UPW) model no longer valid for aerial-to-ground links. This paper studies the UAV swarm enabled near-field AMA communication, by taking into account the non-uniform spherical wave (NUSW) model, where UAV swarm trajectory simultaneously influences the channel amplitude and phase. We formulate a general optimization problem to maximize the minimum average communication rate over user equipments (UEs), by jointly optimizing the 3D UAV swarm trajectory and receive beamforming for all UEs. To draw useful insights, the special case of single UE is first studied, and successive convex approximation (SCA) technique is proposed to efficiently optimize the UAV swarm trajectory. For the special case of placement optimization, the optimal placement positions of UAVs for cases of single UAV and two UAVs are derived in closed-form. Then, for the special case of two UEs, we show that an inter-UE interference (IUI)-free communication can be achieved by symmetrically placing an even number of UAVs along a hyperbola, with its foci corresponding to the locations of the two UEs. Furthermore, for arbitrary number of UEs, an alternating optimization algorithm is proposed to efficiently tackle the non-convex optimization problem. Numerical results validate the significant performance gains over the benchmark schemes.

cs.IT↗

arXiv2026

Channel Gain Map Reconstruction Based on Virtual Scatterer Model

This paper proposes an efficient method for modeling and reconstructing the channel gain map (CGM) based on virtual scatterers. Specifically, we develop a virtual scatterer model to characterize the channel power gain distribution in three-dimensional (3D) space, by capturing the multi-path propagation environment structure and exploiting the angular-domain spatial correlation of scatterer response. In this model, the CGM is represented as a function over a set of tunable parameters for virtual scatterers, including their number, positions, and scatterer response coefficients (SRCs), which can be estimated from a limited number of channel power gain measurements at a given set of locations within the region of interest. This new representation offers a flexible and scalable modeling framework for efficient and accurate CGM reconstruction. Furthermore, we propose a progressive estimation algorithm to acquire the scatterers' parameters. In this algorithm, we gradually increase the number of virtual scatterers to balance the computational complexity and estimation accuracy. In addition, by exploiting the spatial correlation of scatterer response, we propose a Gaussian process regression (GPR)-based inference method to predict the SRCs that cannot be directly estimated. Finally, ray-tracing-based simulation results under realistic physical environments validate the effectiveness of the proposed method, demonstrating that it achieves higher reconstruction accuracy compared to conventional CGM estimation approaches.

cs.IT↗

arXiv2026

Deep learning based Channel Estimation and Beamforming in Movable Antenna Systems

Movable antenna (MA) has emerged as a promising technology for future wireless systems. Compared with traditional fixed-position antennas, MA improves system performance by antenna movement to optimize channel conditions. For multiuser wideband MA systems, this paper proposes deep learning-based framework integrating channel estimation (CE), antenna position optimization, and beamforming, with a clear workflow and enhanced efficiency. Specifically, to obtain accurate channel state information (CSI), we design a two-stage CE mechanism: first reconstructing the channel matrix from limited measurements via compressive sensing, then introducing a Swin-Transformer-based denoising network to refine CE accuracy for subsequent optimization. Building on this, we address the joint optimization challenge by proposing a Transformer-based network that intelligently maps CSI sequences of candidate positions to optimal MA positions while combining a model-driven weighted minimum mean square error (WMMSE) beamforming approach to achieve better performance. Simulation results demonstrate that the proposed methods achieve superior performance compared with existing counterparts under various conditions. The codes about this work are available at https://github.com/ZiweiWan/Code-4-DL-MA-CE-BF.

cs.IT↗

arXiv2026

Opportunistic Screening of Wolff-Parkinson-White Syndrome using Single-Lead AI-ECG Mobile System: A Real-World Study of over 3.5 million ECG Recordings in China

Wolff-Parkinson-White (WPW) syndrome, a congenital cardiac conduction abnormality with low prevalence, carries a significant risk of sudden cardiac death. Early identification remains challenging due to screening costs and professional resource scarcity. This retrospective real-world study systematically evaluates an integrated Artificial Intelligence-enabled mobile screening system comprising portable single-lead devices, AI primary screening, and cardiologist review. Analyzing 3,566,626 ECG records from 87,836 individuals between 2019 and 2025, the AI model achieved an AUC of 0.6676 and a specificity of 95.92% in complex real-world signal environments. Despite predictive probability bias inherent in ultra-low prevalence contexts, the model demonstrated stable risk stratification, with high-confidence scores concentrated among true positive individuals. The risk of detecting WPW in AI-positive records was 86.2-fold higher than in AI-negative records. By implementing a human-AI collaborative workflow, the volume of ECGs requiring manual review was reduced by approximately 99.5% compared to universal screening. In an ideal collaborative scenario, an average of only 18 ECGs required review to confirm one WPW case, representing a more than 60-fold increase in screening efficiency. Compared to traditional 12-lead ECGs and electrophysiological studies, this system significantly reduced time and medical costs. Our findings suggest that a risk-stratification-based human-AI collaborative system provides a promising paradigm for the early public health detection of low-prevalence, high-risk arrhythmias.

eess.SP↗

arXiv2026

Human-AI Co-Embodied Intelligence for Scientific Experimentation and Manufacturing

Scientific experimentation and manufacturing rely on prolonged protocol development and complex, multi-step implementation, which require continuous human expertise for precise execution and decision-making, limiting interpretability and scalability. Here, we introduce human-artificial intelligence (AI) co-embodied intelligence, a new form of physical AI that unites human researchers, agentic AI, and wearable hardware. In this paradigm, humans provide precise execution, while agentic AI contributes contextual reasoning, adaptive planning, and analysis. The wearable interface continuously captures experimentation and manufacturing, facilitating seamless communication between humans and AI. We instantiate this paradigm in a microfabrication cleanroom, leading to the agentic-physical experimentation (APEX) system which understands fabrication procedure with accuracy 51% higher than state-of-the-art multimodal large language models/vision language models (LLMs/VLMs), detects and corrects fabrication errors in real-time, and transfers procedural expertise to novice users. Critically, APEX system enables the co-development of fabrication protocols in cleanrooms, overcoming the incompatibility of elastomeric materials in standard microfabrication processes and enabling previously unattainable fabrication outcomes, as demonstrated by the wafer-scale realization of brain-level soft neural probe capable of single-unit-resolution neural recording. These results establish the human-AI co-embodied intelligence that extends agentic reasoning beyond computation into the physical domain, transforming scientific experimentation and manufacturing into autonomous, traceable, interpretable and scalable processes.

cs.AI↗

arXiv2026

BadTemplate: A Training-Free Backdoor Attack via Chat Template Against Large Language Models

Chat template is a common technique used in the training and inference stages of Large Language Models (LLMs). It can transform input and output data into role-based and templated expressions to enhance the performance of LLMs. However, this also creates a breeding ground for novel attack surfaces. In this paper, we first reveal that the customizability of chat templates allows an attacker who controls the template to inject arbitrary strings into the system prompt without the user's notice. Building on this, we propose a training-free backdoor attack, termed BadTemplate. Specifically, BadTemplate inserts carefully crafted malicious instructions into the high-priority system prompt, thereby causing the target LLM to exhibit persistent backdoor behaviors. BadTemplate outperforms traditional backdoor attacks by embedding malicious instructions directly into the system prompt, eliminating the need for model retraining while achieving high attack effectiveness with minimal cost. Furthermore, its simplicity and scalability make it easily and widely deployed in real-world systems, raising serious risks of rapid propagation, economic damage, and large-scale misinformation. Furthermore, detection by major third-party platforms HuggingFace and LLM-as-a-judge proves largely ineffective against BadTemplate. Extensive experiments conducted on 5 benchmark datasets across 6 open-source and 3 closed-source LLMs, compared with 3 baselines, demonstrate that BadTemplate achieves up to a 100% attack success rate and significantly outperforms traditional prompt-based backdoors in both word-level and sentence-level attacks. Our work highlights the potential security risks raised by chat templates in the LLM supply chain, thereby supporting the development of effective defense mechanisms.

cs.CR↗

arXiv2026

SynthVerse: A Large-Scale Diverse Synthetic Dataset for Point Tracking

Point tracking aims to follow visual points through complex motion, occlusion, and viewpoint changes, and has advanced rapidly with modern foundation models. Yet progress toward general point tracking remains constrained by limited high-quality data, as existing datasets often provide insufficient diversity and imperfect trajectory annotations. To this end, we introduce SynthVerse, a large-scale, diverse synthetic dataset specifically designed for point tracking. SynthVerse includes several new domains and object types missing from existing synthetic datasets, such as animated-film-style content, embodied manipulation, scene navigation, and articulated objects. SynthVerse substantially expands dataset diversity by covering a broader range of object categories and providing high-quality dynamic motions and interactions, enabling more robust training and evaluation for general point tracking. In addition, we establish a highly diverse point tracking benchmark to systematically evaluate state-of-the-art methods under broader domain shifts. Extensive experiments and analyses demonstrate that training with SynthVerse yields consistent improvements in generalization and reveal limitations of existing trackers under diverse settings.

cs.CV↗

arXiv2026

Fedcompass: Federated Clustered and Periodic Aggregation Framework for Hybrid Classical-Quantum Models

Federated learning enables collaborative model training across decentralized clients under privacy constraints. Quantum computing offers potential for alleviating computational and communication burdens in federated learning, yet hybrid classical-quantum federated learning remains susceptible to performance degradation under non-IID data. To address this,we propose FEDCOMPASS, a layered aggregation framework for hybrid classical-quantum federated learning. FEDCOMPASS employs spectral clustering to group clients by class distribution similarity and performs cluster-wise aggregation for classical feature extractors. For quantum parameters, it uses circular mean aggregation combined with adaptive optimization to ensure stable global updates. Experiments on three benchmark datasets show that FEDCOMPASS improves test accuracy by up to 10.22% and enhances convergence stability under non-IID settings, outperforming six strong federated learning baselines.

cs.LG↗

arXiv2026

Benchmarking neural surrogates on realistic spatiotemporal multiphysics flows

Predicting multiphysics dynamics is computationally expensive and challenging due to the severe coupling of multi-scale, heterogeneous physical processes. While neural surrogates promise a paradigm shift, the field currently suffers from an "illusion of mastery", as repeatedly emphasized in top-tier commentaries: existing evaluations overly rely on simplified, low-dimensional proxies, which fail to expose the models' inherent fragility in realistic regimes. To bridge this critical gap, we present REALM (REalistic AI Learning for Multiphysics), a rigorous benchmarking framework designed to test neural surrogates on challenging, application-driven reactive flows. REALM features 11 high-fidelity datasets spanning from canonical multiphysics problems to complex propulsion and fire safety scenarios, alongside a standardized end-to-end training and evaluation protocol that incorporates multiphysics-aware preprocessing and a robust rollout strategy. Using this framework, we systematically benchmark over a dozen representative surrogate model families, including spectral operators, convolutional models, Transformers, pointwise operators, and graph/mesh networks, and identify three robust trends: (i) a scaling barrier governed jointly by dimensionality, stiffness, and mesh irregularity, leading to rapidly growing rollout errors; (ii) performance primarily controlled by architectural inductive biases rather than parameter count; and (iii) a persistent gap between nominal accuracy metrics and physically trustworthy behavior, where models with high correlations still miss key transient structures and integral quantities. Taken together, REALM exposes the limits of current neural surrogates on realistic multiphysics flows and offers a rigorous testbed to drive the development of next-generation physics-aware architectures.

cs.LG↗