arXiv subjects

Rui Zhang

Publications and source records attributed to Rui Zhang.

At least 343 records · Page 19Linked to original sources

arXiv2025

RealBench: Benchmarking Verilog Generation Models with Real-World IP Designs

The automatic generation of Verilog code using Large Language Models (LLMs) has garnered significant interest in hardware design automation. However, existing benchmarks for evaluating LLMs in Verilog generation fall short in replicating real-world design workflows due to their designs' simplicity, inadequate design specifications, and less rigorous verification environments. To address these limitations, we present RealBench, the first benchmark aiming at real-world IP-level Verilog generation tasks. RealBench features complex, structured, real-world open-source IP designs, multi-modal and formatted design specifications, and rigorous verification environments, including 100% line coverage testbenches and a formal checker. It supports both module-level and system-level tasks, enabling comprehensive assessments of LLM capabilities. Evaluations on various LLMs and agents reveal that even one of the best-performing LLMs, o1-preview, achieves only a 13.3% pass@1 on module-level tasks and 0% on system-level tasks, highlighting the need for stronger Verilog generation models in the future. The benchmark is open-sourced at https://github.com/IPRC-DIP/RealBench.

cs.LG↗

arXiv2025

Collaborative Inference and Learning between Edge SLMs and Cloud LLMs: A Survey of Algorithms, Execution, and Open Challenges

As large language models (LLMs) evolve, deploying them solely in the cloud or compressing them for edge devices has become inadequate due to concerns about latency, privacy, cost, and personalization. This survey explores a collaborative paradigm in which cloud-based LLMs and edge-deployed small language models (SLMs) cooperate across both inference and training. We present a unified taxonomy of edge-cloud collaboration strategies. For inference, we categorize approaches into task assignment, task division, and mixture-based collaboration at both task and token granularity, encompassing adaptive scheduling, resource-aware offloading, speculative decoding, and modular routing. For training, we review distributed adaptation techniques, including parameter alignment, pruning, bidirectional distillation, and small-model-guided optimization. We further summarize datasets, benchmarks, and deployment cases, and highlight privacy-preserving methods and vertical applications. This survey provides the first systematic foundation for LLM-SLM collaboration, bridging system and algorithm co-design to enable efficient, scalable, and trustworthy edge-cloud intelligence.

cs.DC↗

arXiv2025

Emergent discrete space-time crystal of Majorana-like quasiparticles in chiral liquid crystals

Time crystals spontaneously break the time translation symmetry, as recently has been frequently reported in quantum systems. Here we describe the observation of classical analogues of both 1+1-dimensional and 2+1-dimensional discrete space-time crystals in a liquid crystal system driven by a Floquet electrical signal. These classical time crystals comprise particle-like structural features and exists over a wide range of temperatures and electrical driving conditions. The phenomenon-enabling period-doubling effect comes from their topological Majorana-like quasiparticle features, where periodic inter-transformations of co-existing topological solitons and disclinations emerge in response to external stimuli and play pivotal roles. Our discrete space-time crystals exhibit robustness against temporal perturbations and spatial defects, behaving like a time-crystalline analogues of a smectic phase. Our findings show that the simultaneous symmetry breaking in time and space can be a widespread occurrence in numerous open systems, not only in quantum but also in a classical soft matter context.

cond-mat.soft↗

arXiv2025

Polarforming Design for Movable Antenna Systems

Polarforming has emerged as a promising technique to enable the antenna to shape its polarization into a desired state for aligning with that of the received electromagnetic (EM) wave or reconfiguring that of the transmitted EM wave. In this letter, we investigate polarforming design for the movable antenna (MA)-enabled communication system. Specifically, we consider a single-input single-output (SISO) system with reconfigurable antenna positions and polarizations to leverage both spatial and polarization degrees of freedom (DoFs). First, we present a polarized channel model and characterize the channel response as a function of antenna positions and polarforming phase shifts. To maximize the achievable rate of the proposed system, we then develop a successive convex approximation (SCA)-based optimization algorithm by iteratively optimizing the antenna positions and phase shifts at both the transmitter and receiver. Furthermore, simulation results demonstrate the performance gains of the proposed system over conventional systems in mitigating channel depolarization and adapting to channel fading.

eess.SY↗

arXiv2025

Antenna Position and Beamforming Optimization for Movable Antenna Enabled ISAC: Optimal Solutions and Efficient Algorithms

In this paper, we propose an integrated sensing and communication (ISAC) system enabled by movable antennas (MAs), which can dynamically adjust antenna positions to enhance both sensing and communication performance for future wireless networks. To characterize the benefits of MA-enabled ISAC systems, we first derive the Cramér-Rao bound (CRB) for angle estimation error, which is then minimized for optimizing the antenna position vector (APV) and beamforming design, subject to a pre-defined signal-to-noise ratio (SNR) constraint to ensure the communication performance. In particular, for the case with receive MAs only, we provide a closed-form optimal antenna position solution, and show that employing MAs over conventional fixed-position antennas (FPAs) can achieve a sensing performance gain upper-bounded by 4.77 dB. On the other hand, for the case with transmit MAs only, we develop a boundary traversal breadth-first search (BT-BFS) algorithm to obtain the global optimal solution in the line-of-sight (LoS) channel scenario, along with a lower-complexity boundary traversal depth-first search (BT-DFS) algorithm to find a local optimal solution efficiently. While in the scenario with non-LoS (NLoS) channels, a majorization-minimization (MM) based Rosen's gradient projection (RGP) algorithm with an efficient initialization method is proposed to obtain stationary solutions for the considered problem, which can be extended to the general case with both transmit and receive MAs. Extensive numerical results are presented to verify the effectiveness of the proposed algorithms, and demonstrate the superiority of the considered MA-enabled ISAC system over conventional ISAC systems with FPAs in terms of sensing and communication performance trade-off.

cs.IT↗

arXiv2025

External Large Foundation Model: How to Efficiently Serve Trillions of Parameters for Online Ads Recommendation

Ads recommendation is a prominent service of online advertising systems and has been actively studied. Recent studies indicate that scaling-up and advanced design of the recommendation model can bring significant performance improvement. However, with a larger model scale, such prior studies have a significantly increasing gap from industry as they often neglect two fundamental challenges in industrial-scale applications. First, training and inference budgets are restricted for the model to be served, exceeding which may incur latency and impair user experience. Second, large-volume data arrive in a streaming mode with data distributions dynamically shifting, as new users/ads join and existing users/ads leave the system. We propose the External Large Foundation Model (ExFM) framework to address the overlooked challenges. Specifically, we develop external distillation and a data augmentation system (DAS) to control the computational cost of training/inference while maintaining high performance. We design the teacher in a way like a foundation model (FM) that can serve multiple students as vertical models (VMs) to amortize its building cost. We propose Auxiliary Head and Student Adapter to mitigate the data distribution gap between FM and VMs caused by the streaming data issue. Comprehensive experiments on internal industrial-scale applications and public datasets demonstrate significant performance gain by ExFM.

cs.IR↗

arXiv2025

Quorum sensing of light-activated colloids in nematic liquid crystals

Motile living organisms routinely probe their surroundings to adapt in ever-evolving environments. Although synthetic microswimmers offer surrogates for self-propelled living entities, they often lack the complex feedback mechanisms that enable organisms to adapt. In this work, we present an experimental platform in which light-activated colloids dispersed in a nematic liquid crystal can (i) switch from directed to active Brownian motion depending on the nematic anchoring and (ii) mechanically adjust their motility in response to crowding, effectively enforcing quorum-sensing interactions. Both features are caused by a distinctive self-propulsion mechanism as unveiled through experiments, simulations, and theory. We characterize the dynamics of a single colloid and demonstrate that its motion is captured by an active Brownian particle model if the nematic anchoring is homeotropic, and by directed self-propulsion along the nematic director if the anchoring is planar. Next, we investigate the many-body dynamics, showing that it undergoes a clustering phase separation through effective quorum-sensing interactions. Our work suggests how to create adaptive materials with life-like capabilities using readily accessible properties of liquid crystals and colloids without explicitly engineering any of the needed mechano-chemical feedbacks.

cond-mat.soft↗

arXiv2025

VisOnlyQA: Large Vision Language Models Still Struggle with Visual Perception of Geometric Information

Large Vision Language Models (LVLMs) have achieved remarkable performance in various vision-language tasks. However, it is still unclear how accurately LVLMs can perceive visual information in images. In particular, the capability of LVLMs to perceive geometric information, such as shape, angle, and size, remains insufficiently analyzed, although the perception of these properties is crucial for tasks that require a detailed visual understanding. In this work, we introduce VisOnlyQA, a dataset for evaluating the geometric perception of LVLMs, and reveal that LVLMs often cannot accurately perceive basic geometric information in images, while human performance is nearly perfect. VisOnlyQA consists of 12 tasks that directly ask about geometric information in geometric shapes, charts, chemical structures, and 3D shapes. Our experiments highlight the following findings: (i) State-of-the-art LVLMs struggle with basic geometric perception. 23 LVLMs we evaluate, including GPT-4o and Gemini 2.5 Pro, work poorly on VisOnlyQA. (ii) Additional training data does not resolve this issue. Fine-tuning on the training set of VisOnlyQA is not always effective, even for in-distribution tasks. (iii) LLM may be the bottleneck. LVLMs using stronger LLMs exhibit better geometric perception on VisOnlyQA, while it does not require complex reasoning, suggesting that the way LVLMs process information from visual encoders is a bottleneck. The datasets, code, and model responses are provided at https://github.com/psunlpgroup/VisOnlyQA.

cs.CL↗

arXiv2025

Elongated vortex quantum droplets in binary Bose-Einstein condensates

Stability of elongated (``slender") quantum droplets (QDs) with embedded unitary and multiple vorticity is a problem that was not solved previously. In this work, we propose a solution which relies upon the use of the spatial modulation of the inter-species scattering length in the binary Bose-Einstein condensates, in the form of a two-dimensional axisymmetric Gaussian, shaped by means of the optical Feshbach resonance. The corresponding effective nonlinear trapping potential supports completely stable elongated QDs with vorticity $S=0$ and partly stable families of elongated QDs with $S=1,2,3,4$ (other nonlinear systems do not maintain stability of vortex droplets with $\geq 2$). We systematically analyze effects of the amplitude and width of the Gaussian modulation, as well as the total number of atoms, on the shape and stability of the QDs, some effects being explained analytically. Collisions between identical QDs with $% S=1$ moving in opposite directions along the central axis leads to their merger into still more elongated breathing QDs with the same vorticity, while collisions between QDs with $S=\pm 1$ are quasi-elastic. Moving modulation profiles are able to adiabatically rotate the trapped elongated QDs. Application of a torque to the vector QD sets in the gyroscopic regime of robust precession, which realizes a macroscopic spin-orbit-coupling effect.

cond-mat.quant-gas↗

arXiv2025

Movable Antenna-Aided Near-Field Integrated Sensing and Communication

Integrated sensing and communication (ISAC) is emerging as a pivotal technology for next-generation wireless networks. However, existing ISAC systems are based on fixed-position antennas (FPAs), which inevitably incur a loss in performance when balancing the trade-off between sensing and communication. Movable antenna (MA) technology offers promising potential to enhance ISAC performance by enabling flexible antenna movement. Nevertheless, exploiting more spatial channel variations requires larger antenna moving regions, which may invalidate the conventional far-field assumption for channels between transceivers. Therefore, this paper utilizes the MA to enhance sensing and communication capabilities in near-field ISAC systems, where a full-duplex base station (BS) is equipped with multiple transmit and receive MAs movable in large-size regions to simultaneously sense multiple targets and serve multiple uplink (UL) and downlink (DL) users for communication. We aim to maximize the weighted sum of sensing and communication rates (WSR) by jointly designing the transmit beamformers, sensing signal covariance matrices, receive beamformers, and MA positions at the BS, as well as the UL power allocation. The resulting optimization problem is challenging to solve. Thus, we propose an efficient two-layer random position (RP) algorithm to tackle it. In addition, to reduce movement delay and cost, we design an antenna position matching (APM) algorithm based on the greedy strategy to minimize the total MA movement distance. Extensive simulation results demonstrate the substantial performance improvement achieved by deploying MAs in near-field ISAC systems. Moreover, the results show the effectiveness of the proposed APM algorithm in reducing the antenna movement distance, which is helpful for energy saving and time overhead reduction for MA-aided near-field ISAC systems with large moving regions.

cs.IT↗

arXiv2025

Evaluating Robustness of Large Audio Language Models to Audio Injection: An Empirical Study

Large Audio-Language Models (LALMs) are increasingly deployed in real-world applications, yet their robustness against malicious audio injection attacks remains underexplored. This study systematically evaluates five leading LALMs across four attack scenarios: Audio Interference Attack, Instruction Following Attack, Context Injection Attack, and Judgment Hijacking Attack. Using metrics like Defense Success Rate, Context Robustness Score, and Judgment Robustness Index, their vulnerabilities and resilience were quantitatively assessed. Experimental results reveal significant performance disparities among models; no single model consistently outperforms others across all attack types. The position of malicious content critically influences attack effectiveness, particularly when placed at the beginning of sequences. A negative correlation between instruction-following capability and robustness suggests models adhering strictly to instructions may be more susceptible, contrasting with greater resistance by safety-aligned models. Additionally, system prompts show mixed effectiveness, indicating the need for tailored strategies. This work introduces a benchmark framework and highlights the importance of integrating robustness into training pipelines. Findings emphasize developing multi-modal defenses and architectural designs that decouple capability from susceptibility for secure LALMs deployment.

cs.CL↗

arXiv2025

Automating Expert-Level Medical Reasoning Evaluation of Large Language Models

As large language models (LLMs) become increasingly integrated into clinical decision-making, ensuring transparent and trustworthy reasoning is essential. However, existing evaluation strategies of LLMs' medical reasoning capability either suffer from unsatisfactory assessment or poor scalability, and a rigorous benchmark remains lacking. To address this, we introduce MedThink-Bench, a benchmark designed for rigorous, explainable, and scalable assessment of LLMs' medical reasoning. MedThink-Bench comprises 500 challenging questions across ten medical domains, each annotated with expert-crafted step-by-step rationales. Building on this, we propose LLM-w-Ref, a novel evaluation framework that leverages fine-grained rationales and LLM-as-a-Judge mechanisms to assess intermediate reasoning with expert-level fidelity while maintaining scalability. Experiments show that LLM-w-Ref exhibits a strong positive correlation with expert judgments. Benchmarking twelve state-of-the-art LLMs, we find that smaller models (e.g., MedGemma-27B) can surpass larger proprietary counterparts (e.g., OpenAI-o3). Overall, MedThink-Bench offers a foundational tool for evaluating LLMs' medical reasoning, advancing their safe and responsible deployment in clinical practice.

cs.CL↗

arXiv2025

Testing CP-violation in a Heavy Higgs Sector at CLIC

We propose to probe CP-violation in the heavy (pseudo)scalar sector of an extended Higgs model, in which we make simultaneous use of the $HVV$ ($V=W^\pm, Z$) and $Ht\bar{t}$ interactions of a heavy Higgs state $H$. The CP-even component of $H$ can be probed through the tree level $HVV$ interaction while the CP-odd component of $H$ can be probed if the final $t\bar{t}$ pair can be tested to form a $^1S_0$ state. We can then confirm CP-violation if both CP-even and CP-odd components of $H$ are discovered. This is possible at the Compact Linear Collider (CLIC) by exploiting $H$ production from Vector-Boson Fusion (VBF) and decay to $t\bar{t}$ pairs. We analyze the distribution of the azimuthal angle between the leptons coming from top and antitop quarks, that would allow one to disentangle the CP nature of such a heavy Higgs state. We also show its implications for the 2-Higgs-Doublet Model (2HDM) with CP-violation.

hep-ph↗

arXiv2025

Synergistic Localization and Sensing in MIMO-OFDM Systems via Mixed-Integer Bilevel Learning

Wireless localization and sensing technologies are essential in modern wireless networks, supporting applications in smart cities, the Internet of Things (IoT), and autonomous systems. High-performance localization and sensing systems are critical for both network efficiency and emerging intelligent applications. Integrating channel state information (CSI) with deep learning has recently emerged as a promising solution. Recent works have leveraged the spatial diversity of multiple input multiple output (MIMO) systems and the frequency granularity of orthogonal frequency division multiplexing (OFDM) waveforms to improve spatial resolution. Nevertheless, the joint modeling of localization and sensing under the high-dimensional CSI characteristics of MIMO-OFDM systems remains insufficiently investigated. This work aims to jointly model and optimize localization and sensing tasks to harness their potential synergy. We first formulate localization and sensing as a mixed-integer bilevel deep learning problem and then propose a novel stochastic proximal gradient-based mixed-integer bilevel optimization (SPG-MIBO) algorithm. SPG-MIBO is well-suited for high-dimensional and large-scale datasets, leveraging mini-batch training at each step for computational and memory efficiency. The algorithm is also supported by theoretical convergence guarantees. Extensive experiments on multiple datasets validate its effectiveness and highlight the performance gains from joint localization and sensing optimization.

cs.NI↗

arXiv2025

Act-With-Think: Chunk Auto-Regressive Modeling for Generative Recommendation

Generative recommendation (GR) typically encodes behavioral or semantic aspects of item information into discrete tokens, leveraging the standard autoregressive (AR) generation paradigm to make predictions. However, existing methods tend to overlook their intrinsic relationship, that is, the semantic usually provides some reasonable explainability "$\textbf{why}$" for the behavior "$\textbf{what}$", which may constrain the full potential of GR. To this end, we present Chunk AutoRegressive Modeling (CAR), a new generation paradigm following the decision pattern that users usually think semantic aspects of items (e.g. brand) and then take actions on target items (e.g. purchase). Our CAR, for the $\textit{first time}$, incorporates semantics (SIDs) and behavior (UID) into a single autoregressive transformer from an ``act-with-think'' dual perspective via chunk-level autoregression. Specifically, CAR packs SIDs and UID into a conceptual chunk for item unified representation, allowing each decoding step to make a holistic prediction. Experiments show that our CAR significantly outperforms existing methods based on traditional AR, improving Recall@5 by 7.93% to 22.30%. Furthermore, we verify the scaling effect between model performance and SIDs bit number, demonstrating that CAR preliminary emulates a kind of slow-thinking style mechanism akin to the reasoning processes observed in large language models (LLMs).

cs.IR↗

arXiv2025

Wideband Coverage Enhancement for IRS-Aided Wireless Networks Based on Power Measurement

By applying tunable phase shifts to incident waves via passive signal reflection, intelligent reflecting surface (IRS) can offer significant performance improvement for wireless communication systems. To reap such performance gain, channel knowledge for IRS-cascaded links is generally required, which is practically challenging to acquire due to their high-dimensional and time-varying characteristics. Conventional pilot-based channel estimation incurs excessive overhead due to the large number of reflecting elements, thus undermining the IRS efficiency, especially for wideband systems with frequency-selective fading channels. To tackle this issue, we propose in this letter a power-measurement-based channel autocorrelation matrix estimation and coverage enhancement approach for IRS-aided orthogonal frequency division multiplexing (OFDM) systems. Specifically, by estimating equivalent channel autocorrelation matrices of IRS-cascaded OFDM channels based on receive signal power and optimizing the IRS reflection vector based on them, the average coverage performance in the IRS-aided region is enhanced without the need for frequent reconfiguration of IRS reflection coefficients based on user instantaneous channels. Simulation results validate the effectiveness of the proposed approach for improving the average channel gain over the coverage region.

eess.SP↗

arXiv2025

World-Consistent Data Generation for Vision-and-Language Navigation

Vision-and-Language Navigation (VLN) is a challenging task that requires an agent to navigate through photorealistic environments following natural-language instructions. One main obstacle existing in VLN is data scarcity, leading to poor generalization performance over unseen environments. Though data argumentation is a promising way for scaling up the dataset, how to generate VLN data both diverse and world-consistent remains problematic. To cope with this issue, we propose the world-consistent data generation (WCGEN), an efficacious data-augmentation framework satisfying both diversity and world-consistency, aimed at enhancing the generalization of agents to novel environments. Roughly, our framework consists of two stages, the trajectory stage which leverages a point-cloud based technique to ensure spatial coherency among viewpoints, and the viewpoint stage which adopts a novel angle synthesis method to guarantee spatial and wraparound consistency within the entire observation. By accurately predicting viewpoint changes with 3D knowledge, our approach maintains the world-consistency during the generation procedure. Experiments on a wide range of datasets verify the effectiveness of our method, demonstrating that our data augmentation strategy enables agents to achieve new state-of-the-art results on all navigation tasks, and is capable of enhancing the VLN agents' generalization ability to unseen environments.

cs.CV↗

arXiv2025

Precise Near-Field Beam Training with DFT Codebook based on Amplitude-only Measurement

Extremely large antenna arrays (ELAAs) operating in high-frequency bands have spurred the development of near-field communication, driving advancements in beam training and signal processing design. In this work, we present a low-complexity near-field beam training scheme that fully utilizes the conventional discrete Fourier transform (DFT) codebook designed for far-field users. We begin by analyzing the received beam pattern in the near field and derive closed-form expressions for the beam width and central gain. These analytical results enable the definition of an angle-dependent, modified Rayleigh distance, which effectively distinguishes near-field and far-field user regimes. Building on the analysis, we develop a direct and computationally efficient method to estimate user distance, with a complexity of O(1), and further improve its accuracy through a simple refinement. Simulation results demonstrate significant gains in both single- and multi-user settings, with up to 2.38 dB SNR improvement over exhaustive search. To further enhance estimation accuracy, we additionally propose a maximum likelihood estimation (MLE) based refinement method, leveraging the Rician distribution of signal amplitudes and achieving accuracy close to the Cramer--Rao bound (CRB). Simulation shows the single-user and multi-user achievable rates can both approach those obtained with ideal channel state information.

eess.SP↗