Search arXiv⌕ Search

arXiv subjects

Rui Zhang

Publications and source records attributed to Rui Zhang.

At least 91 records · Page 5Linked to original sources
arXiv2026

InkShield: Writing Style Protection Against Unauthorized Handwriting Mimicry

Recent handwritten text generators can reproduce a writer's style from publicly available references, posing risks of document forgery and identity misuse. An attacker may use a publicly available handwritten note or signature sample to generate forged recommendation letters or authorization forms, leading to document fraud, identity misuse, and misleading decisions. However, existing protections against unauthorized image editing or synthesis transfer poorly to handwriting style mimicry. Designed for natural images with complex backgrounds, they often optimize perturbations over the whole image. For sparse handwriting images, such global perturbations become conspicuous in blank background regions and largely degrade the visual quality. In this work, we propose InkShield, a proactive writing-style defense that protects reference images before release. InkShield selects a decoy writer to define a style-displacement direction, optimizes perturbations with a frozen handwriting-generation surrogate, and confines them to ink-stroke edges to avoid conspicuous background artifacts. On IAM, the average Top-1/Top-5 rates at which generated samples are retrieved as the target writer by two independent writer evaluators decrease from 11.94%/36.52% to 2.03%/8.79%. Meanwhile, the protected references remain visually close to the originals (LPIPS 0.0078), and the generated text remains readable. InkShield also exhibits transferability to other handwriting generators. Overall, InkShield provides practical protection against unauthorized handwriting style mimicry.

cs.CR↗
arXiv2026

Flexible-Sector 6DMA Base Station: Modeling and Design

Six-dimensional movable antenna (6DMA) has emerged as a promising new technology for future wireless networks, which can adaptively adjust the three-dimensional (3D) positions and 3D rotations of antennas/antenna arrays for performance enhancement. This paper proposes a novel cost-effective 6DMA-based base station (BS) architecture, termed the \textit{flexible-sector} BS, which allows the deployed antennas to flexibly rotate and move along a circular track, thus enabling common sector rotation and flexible antenna allocation across sectors to adapt to the spatial user distribution efficiently. In particular, we focus on the uplink transmission in a single-cell system, where the flexible-sector BS receives independent messages from multiple users. We introduce an angular-domain user distribution model, which captures the users' spatial clustering or hot-spot distribution effectively. Assuming the zero-forcing (ZF) based receiver applied at the BS to decode multiuser signals, we derive the average sum rate achievable for the users as a function of the common rotation of sectors and the antenna allocation over them. Moreover, we develop a two-step algorithm to jointly optimize the common sector rotation and antenna allocation to maximize the average sum rate of all users. It is shown that the optimal antenna number in each sector linearly increases with the number of users in it. It is also revealed that under the most favorable user distribution, the achievable sum rate gain increases in the order of $\log_{2}(B)$ in the regime of asymptotically large number of antennas, where $B$ denotes the number of sectors. Numerically results also show that as $B$ increases, the proposed flexible-sector BS achieves higher sum rate, and it outperforms other benchmark schemes, such as the traditional fixed-sector BS as well as the BS with sector rotation or antenna allocation optimization only.

cs.NI↗
arXiv2026

To Use AI as Dice of Possibilities with Timing Computation

The dominant noun-based modeling paradigm, grounded in probability theory and committed to pre-specified noun entities as primitive modeling units, is insufficient as a \emph{grammar of thought}: It leaves \emph{timing} outside the computational scope, precluding any adequate representation of the future as an open space of possibilities. This paper addresses three conceptual gaps absent from the existing literature: (1) possibility space -- a framework admitting multiple possible timelines for the same event; (2) timing computation -- the treatment of timing as a computable rather than observed dimension; and (3) causal factum -- the maximal causal efficacy recovered by reasoning backward from possible futures, rather than assumed in advance. Together, these definitions dissolve the confounding problem inherent to noun-based causal inference and provide the foundation for a spontaneously growing causal-reasoning world model. As proof of concept, we instantiate the framework and apply it to longitudinal EHR data from 3,276 breast cancer patients, demonstrating for the first time, to our knowledge, automatic trajectory discovery and counterfactual timing deduction (i.e., a What-If Machine) in a purely data-driven manner.

cs.AI↗
arXiv2026

A Policy-Driven Runtime Layer for Agentic LLM Serving

Multi-agent LLM systems have become the dominant production workload, but the serving stack was not built for them. The agent framework above knows agent identities, role, schemas, and dispatch structure but never sees an engine-level event; the serving engine below sees every event but knows nothing about agents. A surprising number of cross-cutting policies depend on both: prefix caching, batch shaping, speculative execution, fairness, tool-result memoization, safety enforcement, and more. Each lives in the seam between the two layers and is currently solved by a one-off patch into one neighbor or the other. We argue this seam is best addressed by an architectural change rather than point fixes: insert a third tier, an agent runtime layer, between the framework and the engine, exposing four primitives (observe, score, predict, act) into which any agent-aware policy plugs, with agent identity as the shared coordinate. We map nine concrete policies onto the layer and validate the abstraction in depth on the one with the largest immediate serving-cost lever: KV caching across sessions, instantiated as CacheScout, which learns the per-workload agent transition matrix online and uses it for survival-based eviction and between-step prefetch. Preliminary results on five real multi-agent workloads show +13 to +37 pp cache hit-rate lift, 12% to 29% lower mean TTFT, and 6% to 14% higher throughput over an unmodified serving stack.

cs.AI↗
arXiv2026

InitGen: Candidate Generation for Interaction Initiation in Intelligent Assistants

Interaction initiation refers to presenting multiple candidate queries when a user opens an intelligent assistant before expressing any intent for the current session. In production, candidate generation incorporates dynamic context and produces all candidates within a strict latency budget. Learning from user feedback is also difficult since the generator usually produces more candidates than are finally displayed. After downstream filtering and ranking, only a subset is exposed to users, so the observed feedback is partial and cannot be reliably assigned to individual queries. We present InitGen, a framework for candidate generation that is deployed in the interaction initiation pipeline of OPPO's Xiaobu Assistant. InitGen generates a set of candidate queries jointly and aligns the generated set with user feedback through weighted preference optimization. The sample weights are derived from user activity and downstream ranking scores. The activity weight reduces the dominance of highly active users during training, while the ranking score is used as a practical estimate of the reliability of the observed feedback. InitGen also uses a rolling window update strategy to incorporate recent interaction data into periodic model updates. In an online A/B test against a strong production baseline, InitGen improves the click-through rate from 0.95% to 1.61%, corresponding to a relative improvement of 69.1%, and increases query exposure by 17.9% under the same traffic allocation. InitGen generates the complete candidate set within 180 ms and has been fully deployed in OPPO's Xiaobu Assistant, which serves over 150 million monthly active users.

cs.IR↗
arXiv2026

Flexible Beamforming Design with Two-layer Rotatable Antenna: Synergizing Array and Antenna Rotations

Reconfigurable antenna technology, such as movable antennas (MAs) and rotatable antennas (RAs), has emerged as a promising solution to enhance wireless communication performance by exploiting new degrees of freedom (DoFs) in antenna reconfiguration. However, existing RA designs mostly consider array-wise or antenna-wise rotation only, limiting their potential in wide-range radiation pattern control. To overcome this, we propose a new two-layer RA architecture for downlink coverage improvement, which combines array-wise rotation for global orientation adjustment with per-antenna rotation for fine-grained radiation refinement. We then formulate an optimization problem to maximize the minimum beamforming gain over a target region by jointly optimizing the two-layer rotations and transmit beamforming. To solve this non-convex problem, an efficient block coordinate descent (BCD) algorithm is proposed, which alternately optimizes one of the three variables in an iterative manner, with the other two being fixed. Numerical results demonstrate that the proposed two-layer RA significantly improves the minimum beamforming gain over fixed antenna arrays and single-layer RAs.

eess.SP↗
arXiv2026

Where to Perform Channel Measurements for CKM Construction: A Random Field Theory Analysis

Channel knowledge map (CKM) is regarded as a promising technology for future sixth-generation (6G) networks, facilitating environmental-aware wireless communication, sensing, and localization. Research works on CKM construction can be classified as model-based methods and data-based approaches. Specifically, data-based CKM construction exploits the fundamental principle of spatial correlation to complete CKM based on limited measurement data, leading to the question of "where to perform channel measurements". In this paper, we study the spatial measurement strategy for efficient data-based CKM construction, and consider a specific type of CKM named channel gain map (CGM). The general objective is to select a subset of locations for channel measurements, so as to minimize the average mean-squared-error (AMSE) of the global CGM construction. In order to reduce the infinite measurement locations to a finite set, we discretize the underlying physical space into a finite number of cubic grid points, and formulate a combinatorial optimization problem to select measurement locations from them. In order to solve the proposed problem, we employ two representative algorithms, namely the greedy algorithm and the simulated annealing (SA), and discuss their respective advantages. To overcome the accuracy-complexity trade-off of traditional uniform discretization, we develop an adaptive discretization strategy from the viewpoint of Gaussian random field theory to minimize the information loss from the original continuous field to its approximated discrete representation in the mean-squared sense. Compared to uniform discretization, the proposed adaptive discretization strategy achieves a significant performance gain in terms of AMSE-reduction, establishing the theoretical framework of spatial measurement and providing practical guidance for implementation.

cs.IT↗
arXiv2026

Physics Transformer: Tailoring Transformer for General PDE Prediction

Transformer architectures have attracted increasing attention for solving partial differential equations (PDEs), owing to their flexibility in handling irregular discretizations and their ability to capture long-range physical dependencies. However, unlike discrete language tokens or fixed-resolution image patches, observed physical fields are finite samples of underlying infinite-dimensional functions. Consequently, effectively applying Transformers to PDEs requires a tokenizer that respects the functional nature of physical fields and constructs physically expressive tokens from arbitrary discretizations.To this end, we propose \methodname{Physics Transformer}, a function-projection-based Transformer architecture for physical field prediction. Physics Transformer treats a physical field as a continuous function and partitions its discretization into locality-preserving spatial patches. Within each patch, it dynamically learns a set of adaptive local basis functions and projects the sampled field onto these bases to obtain compact physics tokens. The resulting tokens capture diverse latent physical states while preserving fine-scale spatial structures, enabling efficient global interaction through factorized attention across space and physical states. The projected representation further supports efficient decoding at arbitrary query locations. Extensive experiments on diverse benchmarks, ranging from two-dimensional PDE dynamics to industrial-scale three-dimensional CFD simulations, demonstrate that Physics Transformer accurately captures fine-grained physical structures and achieves state-of-the-art predictive performance. These results establish function projection as a practical and effective foundation for designing Transformer architectures for PDE solving.

cs.LG↗
arXiv2026

A General Deep Learning Framework for Wireless Resource Allocation under Discrete Constraints

While deep learning (DL)-based methods have achieved remarkable success in continuous wireless resource allocation, efficient solutions for problems involving discrete variables remain challenging. This is primarily due to the zero-gradient issue in backpropagation, the difficulty of enforcing intricate constraints with discrete variables, and the inability in generating solutions with non-same-parameter-same-decision (non-SPSD) property. To address these challenges, this paper proposes a general DL framework by introducing the support set to represent the discrete variables. We model the elements of the support set as random variables and learn their joint probability distribution. By factorizing the joint probability as the product of conditional probabilities, each conditional probability is sequentially learned. This probabilistic modeling directly tackles all the aforementioned challenges of DL for handling discrete variables. By operating on probability distributions instead of hard binary decisions, the framework naturally avoids the zero-gradient issue. During the learning of the conditional probabilities, discrete constraints can be seamlessly enforced by masking out infeasible solutions. Moreover, with a dynamic context embedding that captures the evolving discrete solutions, the non-SPSD property is inherently provided by the proposed framework. We apply the proposed framework to two representative mixed-discrete wireless resource allocation problems: (a) joint user association and beamforming in cell-free systems, and (b) joint antenna positioning and beamforming in movable antenna-aided systems. Simulation results demonstrate that the proposed DL framework consistently outperforms existing baselines in terms of both system performance and computational efficiency.

cs.LG↗
arXiv2026

AIM: Amortized Inference for Multistate Transition Models

Interval censored continuous time multistate transition models (MSTMs) are widely used to characterize disease progression and other dynamic processes. Existing inference procedures are predominantly likelihood-based and require a separate model fit for each dataset, involving repeated evaluation of transition probability matrices. This repeated computation can become burdensome when the same model is applied across centers, time periods, or newly collected cohorts. We propose AIM, an amortized Bayesian inference framework for interval censored continuous time MSTMs. AIM learns the relationship between informative summary statistics and model parameters from simulated datasets generated during an offline training stage. Once trained for a prespecified model class, AIM provides posterior inference for new datasets without repeated likelihood optimization. Under fixed observation schedules and discretized covariate strata, we show that interval-specific transition counts are sufficient for the observed panel likelihood and establish identifiability of the corresponding population summaries. We further prove consistency of the induced summary posterior and its neural approximation, yielding a consistent posterior mean estimator. Simulation studies under progressive and competing-pathway MSTMs demonstrate accurate point estimation and reliable uncertainty quantification. AIM completed online inference in milliseconds, with median speedups ranging from approximately 154-fold to 2308-fold relative to repeated likelihood-based estimation. These results establish AIM as a scalable and theoretically grounded framework for reusable Bayesian inference in interval censored MSTMs.

stat.ME↗
arXiv2026

Intelligent Reflecting Surfaces for Integrated Sensing and Communications: From System Coexistence to Networked Mutualism

The rapid development of sixth-generation (6G) wireless networks requires seamless integration of communication and sensing to support ubiquitous intelligence and real-time, high-reliability applications. Integrated sensing and communication (ISAC) has emerged as a key solution for achieving this convergence, offering joint utilization of spectral, hardware, and computing resources. However, realizing high-performance ISAC remains challenging due to environmental line-of-sight (LoS) blockage, limited spatial resolution, and the inherent coverage asymmetry and resource coupling between sensing and communication. Intelligent reflecting surfaces (IRSs), featuring low-cost, energy-efficient, and programmable electromagnetic reconfiguration, provide a promising solution to overcome these limitations. This article presents a comprehensive overview of IRS-aided wireless sensing and ISAC technologies, including IRS architectures, target detection and estimation techniques, beamforming designs, and performance metrics. It further explores IRS-enabled new opportunities for more efficient performance balancing, coexistence, and networking in ISAC systems, focuses on current design bottlenecks, and outlines future research directions. This article aims to offer a unified design framework that guides the development of practical and scalable IRS-aided ISAC systems for the next-generation wireless network.

eess.SP↗
arXiv2026

Construction and Dynamic Update of Channel Gain Maps via 3D Gaussian Splatting

Channel knowledge maps (CKMs) have emerged as a promising technique for providing scene-specific and location-dependent propagation knowledge to enable environment-aware wireless network design. This paper investigates the construction and dynamic updating of a particular type of CKM, namely grid-based channel gain maps (CGMs), for large-scale networks using three-dimensional Gaussian splatting (3DGS). First, we formulate a grid-based channel gain model, where each map entry is defined as the locally averaged channel gain over a receiver grid, thereby suppressing phase-sensitive small-scale fluctuations. The resulting channel gain is decomposed into distance-dependent attenuation, path transmittance, and effective scattering contributions. Based on this decomposition, we develop a physics-informed Gaussian-splatting-based channel gain (GS-CG) model, which represents the propagation environment as a set of Gaussian primitives. The proposed model maps Gaussian geometry, opacity, and directional features to propagation-related factors and renders grid-level channel gains through a differentiable process. To accommodate real-time environmental changes, we further propose an incremental learning mechanism that updates a static reference GS-CG representation into a dynamic CGM. Specifically, the reference Gaussian primitives are frozen, while a compact set of tunable Gaussians is introduced to capture newly induced local channel-gain variations from sparse measurements.Numerical results demonstrate that the proposed GS-CG methods accurately reconstruct grid-based CGMs, efficiently adapt to dynamic environmental changes, and achieve a favorable accuracy-complexity tradeoff for fast CGM refinement.

cs.IT↗
arXiv2026

AXIS: A Growable Community-Driven Data Engine for Scalable Robot Manipulation

Learning effective robot manipulation policies requires diverse, high-quality demonstrations, yet existing data pipelines are often difficult to scale because they rely on specialized hardware, centralized operators, or fixed task suites. We present AXIS, a growable community-driven data engine and benchmark for scalable robot learning, which enables browser-based teleoperation for large-scale demonstration collection, automatically generates and validates new manipulation tasks, and transforms community-collected demonstrations into training-ready data through automated success checking, quality filtering, trajectory smoothing, and visual and physics-based augmentation. The AXIS dataset currently contains 207 diverse tasks and 50K+ trajectories. Meanwhile, AXIS organizes data into task snapshots and evaluates policies with a systematic held-out protocol. We compare vision-language-action (VLA) policies under a unified AXIS evaluation suite and analyze scaling behavior across different data volumes. Continual pretraining on AXIS substantially improves the overall success rate of $π_{0.5}$ by 5.8%, outperforms the model pretrained on RoboCasa365 by 37.3%, and exhibits consistent scaling with increasing data volume, with the largest gains observed under layout, sensor-noise, and camera perturbations.

cs.RO↗
arXiv2026

A Covariance-Surrogate Framework for Movable-Antenna Enabled Anti-Jamming with Unknown Jammers

In this paper, we investigate a movable antenna (MA) enabled anti-jamming optimization problem, where a legitimate uplink system is exposed to multiple jammers with unknown jamming channels. To enhance the anti-jamming capability of the considered system, an MA array is deployed at the receiver, and the antenna positions and the minimum-variance distortionless-response (MVDR) receive beamformer are jointly optimized to maximize the output signal-to-interference-plus-noise ratio (SINR). The main challenge arises from the fact that the interference covariance matrix is unknown and nonlinearly dependent on the antenna positions. To overcome these issues, we propose a surrogate objective by replacing the unknown covariance with the sample covariance evaluated at the current antenna position anchor. Under a two-timescale framework, the surrogate objective is updated once per block (contains multiple snapshots) at the current anchor position, while the MVDR beamformer is adapted on a per-snapshot basis. We establish a local bound on the discrepancy between the surrogate and the true objective by leveraging matrix concentration inequalities, and further prove that a natural historical-averaging surrogate suffers from a non-vanishing geometric bias. Building on these insights, we develop a low-complexity projected trust-region (TR) surrogate optimization (PTRSO) algorithm that maintains the locality of each iteration via TR constraints and enforces feasibility through projection, which is guaranteed to converge to a stationary point near the anchor. Numerical results verify the effectiveness and robustness of the proposed PTRSO algorithm, which consistently achieves higher output SINR than existing baselines.

eess.SP↗
arXiv2026

Machine Learning Potential-Driven Molecular Dynamics Simulations of Dehydrogenation in Pristine and Doped MgH$_2$

Machine learning potential-driven molecular dynamics simulations (ML-MD) were employed to provide atomistic insights into the dehydrogenation kinetics of pristine and doped MgH2. Through systematic investigation of distinct surface orientations, the MgH2 (100) surface was identified as the most active low-index surface for hydrogen release. For pristine MgH2, our simulations revealed a novel H2 formation mechanism characterized by H2 generation in the subsurface region followed by diffusion to the surface for desorption, highlighting the critical role of subsurface processes beyond conventional surface-driven pathways. Comprehensive screening of 22 doping elements identified Ni as the most effective dopant. Among several descriptors, machine learning analysis identified the time-coupled Miedema electron density as the critical descriptor, underscoring the role of electronic properties. Consequently, a volcano-shaped relationship was uncovered between the intrinsic Miedema electron density ( nws ) and total hydrogen release (optimal window: 4.0 < nws < 5.4x10-2 e/bohr3). Dopants within this range serve a dual function: acting as thermodynamic sinks for H attraction while maintaining a balanced interaction strength to facilitate H-H coupling and H2 release. This atomistic-level validation provides strong theoretical support for the experimentally observed "hydrogen pump" effect of catalytic phases. The present study demonstrates the strong capability of ML- MD in navigating through complex catalytic mechanisms and establishing quantitative property-activity relationships, providing a robust framework for rational design of high-performance catalysts for MgH2 and other hydrogen storage materials.

cond-mat.mtrl-sci↗
arXiv2026

Automated Reinforcement Learning: An Overview

Reinforcement Learning and, recently, Deep Reinforcement Learning are popular methods for solving sequential decision-making problems modeled as Markov Decision Processes. RL modeling of a problem and selecting algorithms and hyper-parameters require careful consideration, as different configurations may entail completely different performances. These considerations are mainly the task of RL experts; however, RL is progressively becoming popular in other fields, such as combinatorial optimization, where researchers and system designers are not necessarily RL experts. Besides, many modeling decisions are typically made manually, such as defining state and action space, size of batches, batch update frequency, and time steps. For these reasons, automating different components of RL is of great importance, and it has attracted much attention in recent years. Automated RL provides a framework in which different components of RL, including MDP modeling, algorithm selection, and hyper-parameter optimization, are modeled and defined automatically. In this article, we present the literature on automated RL (AutoRL), including the recent large language model (LLM) based techniques. We also discuss the recent work on techniques that are not presently tailored for automated RL but hold promise for future integration into AutoRL. Furthermore, we discuss the challenges, open questions, and research directions in AutoRL.

cs.LG↗
arXiv2026

ToolSciVer: Multimodal Scientific Claim Verification with Visual Tool Augmented Reinforcement Learning

Multimodal Scientific Claim Verification (MSCV) requires models to verify scientific claims using visually grounded evidence from papers, including figures, tables, charts, and textual context. However, existing methods often fail because they struggle to locate decisive visual evidence, accurately read structured scientific visuals, and integrate multimodal observations into reliable reasoning. We introduce ToolSciVer, the first tool-augmented framework for MSCV to our knowledge. ToolSciVer equips a VLM with three type-aware visual tools, table row/column focus, chart-to-structure parsing, and high-resolution region zoom, which convert dense scientific visuals into explicit, claim-facing evidence, and trains the policy with Group Relative Policy Optimization (GRPO) under a composite reward of answer correctness, format validity, length control, tool-use efficiency, and tool-validity penalties. Experiments on SciVer and MuSciClaims datasets on five VLMs from three model families (Qwen, InternVL, Gemma) demonstrate that our method achieves superior performance compared to four competitive baselines including prompting-based and RL-based tool-use methods, highlighting the effectiveness of learned, type-aware tool use for scientific claim verification.

cs.CL↗
arXiv2026

Are LLM-Generated GPU Kernels Production-Ready? A Trace-Driven Benchmark and Optimization Agent

Existing GPU kernel generation benchmarks draw problems from synthetic or curated sources that diverge from deployed workloads. We present Atrex-Bench, a benchmark whose 30 operators and 440 shapes are sampled directly from full-cluster production inference traces of compute-limited, memory-rich GPUs. Each problem carries an importance weight derived from its share of observed GPU time, weighted by application card-hours and computed separately for the serving phases in which it runs, together with a per-problem roofline ceiling, so the aggregate score emphasizes the kernels that consume the most serving time. Evaluating six frontier coding agents on Atrex-Bench shows that even the best vanilla model reaches only ${\sim}10\%$ of the hardware roofline on production operators; and correctness alone overstates capability, since much of the apparent pass rate comes from PyTorch fallbacks rather than kernels the model wrote. To close this gap, we co-release Atrex-Kernel-Agent (AKA), a profile-driven kernel-optimization agent that combines iterative measure-revise search, optimization dropout for escaping stalled search contexts, and a layered GPU-optimization knowledge base (298 reference-kernel files and 244 optimization-knowledge documents, plus external upstream reference projects for API/ISA lookup). In a controlled case study, the agent converts zero-FlyDSL fallbacks into real kernels that match or exceed hand-tuned production baselines.

cs.AI↗