Searcharxiv⌕ Search

arXiv subjects

Rui Zhang

Publications and source records attributed to Rui Zhang.

At least 55 records · Page 3Linked to original sources
arXiv2026

Exploiting LLM Agents for Trustworthy AutoResearch in Wireless Communications

Large language model (LLM) agent-enabled AutoResearch is attracting growing interest across scientific disciplines, in which LLMs are leveraged for knowledge synthesis, multistep planning, code generation, tool invocation, and iterative refinement, thus automating the research lifecycle, from hypothesis generation and experimentation to analysis and manuscript preparation. Wireless communications is particularly suitable to this paradigm. This is due to the fact that advances in this field often rely on fundamental-limit analysis, system optimization, and protocol design, all supported by mature mathematical, simulation, and optimization toolchains, as well as standards, measurement, and digital-twin platforms. However, integrating autonomous agents into rigorous wireless research workflows requires traceable processes and verifiable evidence. This article presents a general trustworthy wireless AutoResearch framework. This framework employs typed research contracts, version-controlled artifacts, independent validators, and bounded agent authority to connect hypothesis generation with system modeling, mathematical formu lation, algorithm design, code generation, simulation, reproducible claims, and manuscript preparation. We conduct a case study on integrated sensing and communication (ISAC) for unmanned aerial vehicles (UAVs). It is shown that the proposed framework can generate innovative research ideas and, with appropriate expert intervention, produce a manuscript whose evaluation score is comparable to or higher than those of related IEEE conference and letter papers. These findings demonstrate the effectiveness of LLM agents in orchestrating authoritative scientific tools and versioned research artifacts, while underscoring the importance of human-AI collaboration.

eess.SP↗
arXiv2026

Scratchy: Visual-Scratchpad Multimodal Reasoning for Cryptographic Proof Generation in EasyCrypt

Large language models (LLMs) have recently made substantial progress in formal proof generation, yet presenting distinctive challenges in cryptographic area. Computational security arguments posit that a valid proof must coordinate probability, adversarial games, invariants, assumptions and bounds, which can be provided by a machine-checked framework named EasyCrypt. Although all objects may appear in available context, LLMs still struggle because proof-theoretic dependencies are typically implicit in a linear representation and distributed across multiple programs. So, this paper presents Scratchy, a visual-scratchpad approach that exposes these dependencies for multimodal generation. Given the natural-language security description, with formal context and target propositions, the proof objects can be normalized into a typed proof-relation graph. Then a structure-preserving visual compiler transforms the graph into the formula-rich visual proof state that guides a multimodal model in generating the EasyCrypt proof. Also, the Scratchy-eval, a 114-task dataset derived from reliable official EasyCrypt files, has been introduced. It contains 64 security-form proof generations and 50 multiple-choice knowledge tests. After a series of evaluations, covering semantic grounding, relational invariants, and game reductions, classical LLMs like GPT-5.6-Sol and Claude-Opus-5 have gained a clear advantage from Scratchy's structured visual proof states. This contrast suggests that explicit proof structure can make the improvement and multimodal proof-state representation as a promising direction for computer-aided cryptography.

cs.CR↗
arXiv2026

FATS: A Prompt Injection Attack Utilizing Feign Security Agents with Deceptive Few-shots Learning

Large Language Models (LLMs) face significant security risks despite their advanced capabilities. While techniques like Reinforcement Learning with Human Feedback (RLHF) improve ethical alignment, excessive exposure to security-related training data may cause LLMs to overtrust such information, creating new vulnerabilities. Investigating this issue, we propose a novel attack method termed FATS (Feign Agent Attack with Toxic-shots). By obfuscating preference extraction, compromising toxicity samples, and inducing malicious behavior, we can effectively mislead LLMs into generating harmful outputs. To evaluate FATS effectiveness, we introduce the FAQuery dataset and conduct experiments on various LLMs. Well-known benchmarks like Advbench were selected to assess the approach. Results demonstrate that mainstream models, including GPT-4.1 (61.6\%) and Deepseek-R1 (99.3\%) are highly susceptible. It underscored the need to rigorously analyze security-related data sources during model training, developing more secure and reliable LLMs.

cs.CR↗
arXiv2026

Why Do Reasoning Models Lose Coverage? The Role of Data and Forks in the Road

Recent progress in large language models has led to the emergence of reasoning models, which have shown strong performance on complex tasks through specialized fine-tuning procedures. While these methods reliably improve pass@1 accuracy, prior works have observed that they show a coverage shrinkage behavior, where pass@k degrades relative to the base model. In this paper, we investigate the cause of reasoning shrinkage under SFT-based post-training. We hypothesize that this behavior is driven by properties of the fine-tuning data, specifically related to decision points or "forks in the road" scenarios where model encounters indecipherable patterns with multiple valid reasoning paths. To test this hypothesis, we design controlled case studies that simulate such decision-point settings, spanning indecipherable nodes in graph branching, and reasoning modes. By tracking post-training dynamics in these settings, we find that the shrinkage phenomenon is tightly correlated with the prevalence of decision-point scenarios in the training data. We also demonstrate that this shrinkage behavior can be partially mitigated through targeted data synthesis design of decision-points and a more systematic diversity-encouraging decoding mechanism. Our findings identify data-centric factors as a key driver of shrinkage in reasoning models and highlight diversity-aware designs as an effective lever for controlling it. (Data and code for reproducing our experiments are available at https://github.com/psunlpgroup/reasoning_forks )

cs.LG↗
arXiv2026

Correctness Forensics for Batch Speculative Decoding: Diagnosing the Ragged Tensor Problem

Inference optimizations are routinely evaluated by throughput alone, without verifying output correctness. We conduct a forensic analysis of batch speculative decoding and find that several widely-used implementations silently produce corrupted outputs (repetitive tokens, symbols) while reporting competitive speed; failures invisible to metrics like ROUGE. We trace the root cause to the ragged tensor problem: variable token acceptance desynchronizes position IDs, attention masks, and KV-cache across a batch. We formalize the synchronization invariants (rectangular alignment and position-ID contiguity) that valid batched inference must preserve and show that maintaining them incurs superlinear alignment overhead under contiguous layouts. EQSPEC enforces the invariants without custom kernels; EXSPEC schedules same-length sequences to bypass realignment. On SpecBench across three model families, EXSPEC reaches 3 x throughput at batch size 8 with 95% exact match to standard decoding; residual divergence traces to floating-point non-determinism, not synchronization error. Code:https://github.com/eBay/spec_dec

cs.CL↗
arXiv2026

A New Paradigm of 6G Networks: Proactive Channel Cognition and Reconfiguration

The sixth-generation (6G) wireless networks are expected to enable the deep integration of communication, sensing, computing, control, and intelligence in highly dynamic environments. This evolution drives a fundamental transition from conventional passive channel adaptation to proactive channel cognition and reconfiguration, wherein wireless channels are no longer regarded as uncontrollable propagation media but as network resources that can be learned, predicted, and actively reconfigured. This paper presents a comprehensive overview of this emerging paradigm. We first review channel cognition through the channel knowledge map (CKM) as a systematic framework for learning and exploiting channel characteristics across space, time, and frequency domain. The definitions, construction methods, and applications in wireless networks of CKMs are comprehensively reviewed. Building upon channel cognition, we then review channel reconfiguration technologies from two complementary perspectives: transceiver-side reconfiguration enabled by movable antennas (MAs) and environment-side reconfiguration enabled by intelligent reflecting surfaces (IRSs). For both MA- and IRS-enabled wireless systems, we review their architectures, performance advantages, and key design challenges. Finally, we discuss several promising research directions to inspire further innovations in this burgeoning field.

eess.SP↗
arXiv2026

Polarforming for Wireless Communications: Modeling and Performance Analysis

This paper presents, for the first time, the concept of polarforming for wireless communications. Polarforming refers to a novel technique that enables the polarization of an antenna to shape into a desired polarization state for aligning with the polarization of an electromagnetic (EM) wave. It can fully leverage polarization diversity to enhance the performance of wireless communication systems through polarization matching. To implement polarforming, we propose a new paradigm of phase shifter (PS)-based polarization-reconfigurable antennas (PRAs) that can form linear, circular, and general elliptical polarizations by phase shift control. To further demonstrate the benefits of polarforming, we investigate a PRA-aided wireless communication system equipped with tunable polarization of antennas. We characterize the multiple-input multiple-output (MIMO) channel capacity of the considered system as a function of the phase shifts of PS-based PRAs. We also provide a detailed polarforming interpretation under the single-input single-output (SISO) scenario and theoretically show how polarforming differs from the conventional (analog) beamforming based on PSs. Moreover, we develop an alternating optimization approach to maximize the channel capacity for the systems with single-antenna transmitter/receiver. Based on the water-filling principle, we also derive an upper bound on the MIMO channel capacity with PS-based PRAs and then maximize this capacity bound by optimizing the phase shifts through alternating optimization. Finally, comprehensive simulation results are presented, which not only validate the effectiveness of polarforming in combating channel depolarization but also exhibit substantial performance improvements over conventional systems.

eess.SP↗
arXiv2026

ScentEcho: Exploring Adsorbent Materials for Accurate Odor Collection and Playback

Delivering odors that feel realistic and recognizable remains a core challenge for olfactory interaction systems, particularly in applications that demand precise scent delivery. A key limitation lies in the difficulty of capturing, preserving, and playing back real-world scent sources in a reliable and scalable manner. This study explores the potential of adsorbent materials for supporting realistic scent playback. We present ScentEcho, a portable system that enables modular scent collection and release. Through user evaluations, we identify which adsorbent materials tend to perform better for specific odors, and observe that perceived intensity strongly influences similarity ratings. In addition, odor recognition follows a graded pattern, with users moving from broad category identification to more specific source recognition as similarity increases. These findings offer practical insights for designing olfactory interfaces that are both expressive and perceptually aligned with user expectations.

cs.HC↗
arXiv2026

QiMeng-ChipV-RTL: Exploiting Information Locality for IP-level Verilog Generation

The generation of Register-Transfer Level (RTL) code is a crucial yet labor-intensive step in digital hardware design, traditionally requiring engineers to manually translate complex specifications into thousands of lines of synthesizable Hardware Description Language (HDL) code. While Large Language Models (LLMs) have shown promise in automating this process, existing approaches--including fine-tuned domain-specific models and advanced agent-based systems--struggle to scale to industrial IP-level design tasks. We identify three key challenges: (1) handling long, highly detailed documents, where critical interface constraints become buried in unrelated submodule descriptions; (2) generating long RTL code, where both syntactic and semantic correctness degrade sharply with increasing output length; and (3) navigating the complex debugging cycles required for functional verification through simulation and waveform analysis. To overcome these challenges, we propose ChipV-RTL, a multi-agent framework that leverages information locality in modular hardware design. ChipV-RTL decomposes the long-document to long-code generation problem into a set of short-document, short-code tasks, enabling scalable generation and debugging. Specifically, ChipV-RTL integrates hierarchical document partitioning, task planning, localized code generation, interface-consistent merging, and AST-guided locality-aware debugging. Experiments on RealBench, an IP-level Verilog generation benchmark, demonstrate that ChipV-RTL substantially outperforms state-of-the-art (SOTA) LLMs and agents, achieving a pass rate of 45.0% compared to 21.6%. Code, project page are available at https://iprc-dip.github.io/ChipV-RTL/.

cs.LG↗
arXiv2026

Automated Shape-Model-Based Astrometry of Phobos from Mars Express SRC Images

High-resolution spacecraft images provide important astrometric constraints for orbit refinement, but measurements of resolved bodies are often limited by labor-intensive control-point selection and the difficulty of achieving consistent reductions over large image archives. We present an automated shape-model-based astrometric pipeline for Phobos and apply it to Mars Express Super Resolution Channel (SRC) images. For each exposure, a synthetic image is rendered from a high-resolution 3D shape model under the nominal spacecraft-target-Sun geometry. Feature correspondences between the observed and synthetic images are established using SuperPoint and SuperGlue, followed by RANSAC filtering. The matched synthetic-image keypoints are then associated with surface points through ray-shape intersection. The geometric adjustment fixes the adopted body orientation, spacecraft state, and corrected camera pointing and estimates only two effective plane-of-sky position offsets using the exact perspective-projection model. These offsets are used to derive the center-of-figure position of Phobos. We first test the method on an image set previously analysed with a control-point approach and obtain comparable astrometric performance. We then extend the analysis to a larger SRC dataset spanning 2007-2025 and obtain 1113 successful measurements. Relative to the JPL MAR099 ephemeris, the resulting observed-minus-computed residuals have mean values of 0.186 km in $α\times cos(δ)$ and 0.053 km in $δ$, with corresponding standard deviations of 0.609 km and 0.583 km. These results demonstrate that the proposed pipeline provides a practical approach to large-scale, homogeneous astrometric reduction of archival spacecraft images of Phobos, with potential application to other resolved bodies.

astro-ph.IM↗
arXiv2026

Efficient, Adaptive Near-Field Beam Training based on Linear Bandit

This paper proposes a posterior sampling-based beam training framework for near-field communication under multi-path channels. By leveraging Thompson Sampling (TS), the framework adaptively balances exploration and exploitation to maximize the final beamforming gain under a finite pilot overhead. To ensure data-efficient learning, we incorporate a structured Gaussian prior in the DFT domain and use an RBF covariance as a tractable local-correlation prior, motivated by near-field energy leakage, to promote information sharing among neighboring DFT components. We develop three TS strategies: codebook-constrained search for rapid stabilization via structural regularization, continuous-space search for high accuracy refinement, and a two-stage hybrid refinement scheme that balances training efficiency and estimation accuracy. Simulation results show that the proposed framework reduces pilot overhead by over 90\% while achieving more than a 2 dB SNR gain over baselines in multipath environments. Furthermore, simulations show that the continuous-space search approaches the full-CSI benchmark as the available pilot numbers become sufficiently large.

eess.SP↗
arXiv2026

Adaptive Payload-Aided Near-Field Beam Tracking via Thompson Sampling

Extremely large antenna arrays at high frequencies substantially extend the radiative near-field region in 6G networks, making mobile beam alignment depend jointly on user angle and range. The added range dimension enlarges the beam-search space, making repeated pilot-based sweeping costly under mobility, while sensing-assisted tracking depends on propagation conditions, echo quality, and target reflectivity. We propose an adaptive payload-aided near-field beam-tracking framework based on maximum likelihood estimation (MLE) and Thompson sampling (TS). Selected received payload samples are fed back and reused as tracking observations, avoiding dedicated beam-sweeping symbols during tracking. Within each sliding window, local angle and range trajectories are modeled by low-order polynomials to capture velocity, acceleration, and higher-order motion variations, and are estimated by MLE using the spherical-wave channel model. A local Gaussian approximation centered at the MLE, with covariance from the inverse observed Fisher information, represents trajectory uncertainty. For payload transmissions selected for feedback, TS samples a trajectory hypothesis and maps it to a payload beam toward the sampled state, while the remaining transmissions use the MLE-predicted beam. To handle nonstationary mobility, an asymptotic chi-square characterization of in-window estimation risk motivates joint adaptation of observation-window length and polynomial degree, while online residual statistics adjust the update interval and feedback ratio. The framework is also extended to uniform planar arrays with elevation tracking. Simulations under smooth and sharp-turn trajectories show high payload-accounted mean normalized beamforming gain, low normalized-gain variance, and high effective-symbol reliability, while the adaptive mechanism provides substantial robustness under nonstationary sharp-turn mobility.

eess.SP↗
arXiv2026

The number of limit cycles of piecewise linear Liénard systems

For the planar Liénard differential system $\dot{x}=F(x)-y$, $\dot{y}=x$, where $F(x)$ is a piecewise linear function, Tonnelier (SIAM J. Appl. Math., 2002) conjectured that the maximum number of limit cycles of the system is $n$ when $F(x)$ has $n$ fold points and no jump points, and $2n$ when $F(x)$ has $n$ jump points and no fold points. This conjecture was confirmed by Llibre et al. (J. Nonlinear Sci., 2015) (resp. Chen et al. (J. London Math. Soc., 2026a)) when $F(x)$ has one fold point and no jump points (resp. two fold points). More recently, Chen et al. (J. London Math. Soc., 2026b) proved that the conjecture is correct when $F(x)$ has no fold points and one jump point. All other cases remain open. Here we verify that the lower bound for the maximum number of limit cycles of the system can be $n$ when $F(x)$ has only $n$ fold points, and $2n$ when $F(x)$ has only $n$ jump points, thereby confirming the lower bound part of Tonnelier's conjecture. Moreover, when $F(x)$ has $m$ jump points and $n-m$ fold points, $0\le m\le n$, we also show that the system can have $n+m=(n-m)+2m$ limit cycles. In addition, a complete classification of the {dynamics} near infinity for this class of systems is provided.

math.DS↗
arXiv2026

Reduced-Order Physics-Informed Neural Network with Adaptive Basis Refinement for Structural Identification

Physics-informed neural networks (PINNs) provide a flexible framework for solving forward and inverse problems. However, their direct application to structural dynamics remains limited by high system dimensionality and model-form errors arising from incomplete physics. Reduced-order models (ROMs) can alleviate the dimensionality bottleneck, yet existing PINN-ROM couplings typically rely on fixed reduced subspaces, target forward simulations, or assume complete physics, restricting their use for inverse identification under parametric variability or incomplete system knowledge. To address these limitations, this work proposes a Reduced-Order Physics-Informed Neural Network (RO-PINN) framework with adaptive basis refinement for structural identification under known and incomplete physics. Via projection, reduced governing equations are embedded directly into the PINN loss, facilitating learning in a low-dimensional latent space. An adaptive scheme updates the projection basis during training so that the latent space is progressively realigned with evolving structural parameters or learned residual restoring forces. This realignment reduces basis-mismatch errors and limits their influence on the inferred residual force. The method is validated on a four-story steel frame with nonlinear hysteretic braces under sparse and noisy measurements. Results show parameter identification comparable to or more accurate than Bayesian model updating with lower computational cost in the considered cases, recovery of unmodeled nonlinear restoring forces under incomplete physics, and joint identification of residual restoring forces and structural parameters within the same framework. Overall, RO-PINN provides a unified framework for structural identification by integrating reduced-order modeling, adaptive basis refinement, and physics-informed learning within a single formulation.

cs.CE↗
arXiv2026

Hybrid Topological Defects in Ferroelectric Nematic Fluids

We investigate the evolution of topological defects in polar fluids driven by discrete inversion symmetry-breaking acrossthe nematic-to-ferroelectric nematic phase transition. Using photopatterned surface alignment to prescribe well-defined initial defect configurations in the nematic phase, we track their metamorphosis upon entering the ferroelectric phase. Through systematic comparisons between experiments and numerical simulations, we demonstrate that the resulting polar structures are generically hybrid, intertwining topological configurations of different dimensionalities. Specifically, we identify three basic hybrid defects evolving from precursor disclinations of net charge 0 and +1 (via pairs), and +1 (via single defects): domain walls terminated by surface disclinations, monopole-decorated domain walls, and meron-mediated boojum and monopole complexes. We further demonstrate that these stable hybrid polar defects are ubiquitous in the ferroelectric nematic phase, providing the basic motifs needed to understand, predict, and engineer complex topological textures in polar fluids.

cond-mat.soft↗
arXiv2026

Tensor Decomposition-Based Wireless Sensing for MIMO-OFDM ISAC via Flexible Spatial-Temporal-Spectral Optimization

Integrated sensing and communication (ISAC) is regarded as a key enabling technique in future 6th-generation (6G) mobile communication systems. However, existing multi-input multi-output (MIMO) orthogonal frequency division multiplexing (OFDM) ISAC designs generally rely on the fixed-position antennas and fixed allocation of time-frequency resources, thereby limiting the degrees of freedom of wireless sensing along the spatial-temporal-spectral dimensions. In this paper, we propose a novel wireless sensing framework for MIMO-OFDM ISAC systems with flexible spatial-temporal-spectral optimization and propose a tensor decomposition-based approach to estimate target parameters, including azimuth/elevation angles, ranges, and velocities. Specifically, we first establish a monostatic wireless sensing model for MIMO-OFDM ISAC systems, where the positions of antenna elements, the allocation of OFDM symbols and subcarriers can be flexibly configured. Then, we formulate the problem of estimating target parameters as a tensor decomposition problem admitting to the canonical polyadic format, which enables the parallel target parameters estimation process from corresponding factor matrices along the spatial, temporal, and spectral dimensions, respectively. Based on the decomposed factor matrices, we derive the Cramer-Rao Bound (CRB) for the unknown target parameters and reveal that the estimation accuracy of azimuth/elevation angles, velocities and ranges is fundamentally determined by the array geometry, the distribution of OFDM symbols and subcarriers. Building on this insight, we obtain an optimized solution for the positions of antenna elements, and optimal solutions for the subcarrier allocation and OFDM symbol allocation to minimize the CRB, as well as the mean square error of target parameters estimation.

eess.SP↗
arXiv2026

GigaBrain-0.7: Scaling Embodied Foundation Models to Emergent Capabilities with a Three-System Architecture

Vision-language-action (VLA) models have become a dominant paradigm for generalist embodied agents, demonstrating strong complex and long-horizon task completion in structured settings. Yet it remains an open question whether current VLA systems can benefit from more effective architectural design, scale to substantially larger and more heterogeneous data regimes, and achieve broader generalization across tasks and embodiments. To this end, we present GigaBrain-0.7, an embodied foundation model with substantially improved generalization across diverse robot embodiments. Specifically, GigaBrain-0.7 unifies understanding, prediction, and action through a three-system architecture, scales pretraining to over 37,000 hours of heterogeneous embodied data, and introduces one-stage alignment training that jointly optimizes vision-language understanding and multi-embodiment action generation. Compared with the preceding GigaBrain-0 series and prior state-of-the-art models including $π_{0.5}$, GigaBrain-0.7 achieves substantial improvements in foundation zero-shot capabilities, language-conditioned instruction following, and post-training task success rates. In particular, on our in-house Maker H01 platform and mainstream robot embodiments, GigaBrain-0.7 demonstrates strong task adaptability and completion ability across both home and industrial scenarios. All training code and pretrained model weights will be released.

cs.RO↗
arXiv2026

LAPF: LLM-Agent-Based Path Finder Using the UAVScenes Dataset

Uncrewed aerial vehicles (UAVs) are increasingly deployed for autonomous navigation in complex outdoor environments, where dynamic conditions and mission requirements require intelligent adaptive decision-making. Existing optimization-based, Machine Learning (ML), and Reinforcement Learning (RL) approaches often rely on predefined models or task-specific training, limiting their generalization and adaptability in uncertain scenarios. Recent Large Language Model (LLM)-assisted approaches offer promising reasoning capabilities but remain constrained by limited agentic functionality, including insufficient memory, planning, and tool interaction mechanisms.This paper proposes an LLM-Agent-Based Path Finder (LAPF) framework for autonomous UAV navigation in town-scale outdoor environments. LAPF extends LLM-assisted navigation by integrating perception, memory, planning, and action modules into a closed-loop cognitive architecture. The proposed agent leverages prior navigation experiences, performs Chain-of-Thought (CoT) reasoning, couples each detected hazard to a bounded corrective action, and dynamically refines waypoint decisions based on environmental feedback.The three independent trials per method demonstrate that LAPF achieves mean path lengths of 512.83 m and 506.37 m, compared to the straight-line optimum of 497.33 m, corresponding to path length reductions of 17.2% and 15.6% relative to CoT prompting and absolute path efficiencies of 97.1% and 98.1% in open-field and obstacle-injected scenarios, respectively. Furthermore, LAPF is the only evaluated approach that couples every detected hazard to a bounded, metric-neutral corrective action while maintaining near-goal stability, with zero clamp events in both scenarios, whereas CoT prompting increases from 9.7 to 14.0 events.

cs.RO↗