arXiv subjects

Nan Cheng

Publications and source records attributed to Nan Cheng.

At least 19 recordsLinked to original sources

arXiv2026

YANAMI: A Large-Scale Multimodal Dataset and Benchmark for Multiturn Stateful Interaction

Unified Multimodal Models (UMMs) integrate visual understanding, generation, and editing within a single unified framework. However, existing unified multimodal datasets and benchmarks remain dominated by single-turn tasks. Even in recent multi-turn datasets, many turns can be solved independently without tracking information across turns. Consequently, they provide limited supervision and evaluation for multimodal stateful interaction, which requires models to understand, maintain, update, and faithfully realize evolving dialogue states across turns. To address this gap, we introduce YANAMI, the first large-scale multimodal dialogue dataset and benchmark for stateful interaction, comprising YANAMI-400K and YANAMI-Bench. YANAMI-400K contains 400K multi-turn multimodal dialogues, with more than 2M images and 2.6M dialogue turns. The dialogues span four representative scenarios: Multi-Image Fusion, Image Editing, World Modeling, and Visual Reasoning, and require models to continuously track, preserve, and revise evolving multimodal dialogue states across turns. YANAMI-Bench comprises 400 multi-turn dialogues for systematically evaluating multimodal stateful interaction. It jointly evaluates Dialogue State Understanding and Visual Realization, characterizing the gap between models' ability to understand evolving dialogue states and their ability to faithfully realize them in visual outputs. Experiments show that fine-tuning BAGEL on YANAMI-400K improves image editing, generation, and multimodal stateful interaction by 10.3%, 2.0%, and 13.23%, respectively, while preserving its general visual understanding capabilities. Evaluations on YANAMI-Bench further reveal that existing UMMs still struggle to maintain, update, and visually realize evolving multimodal dialogue states.

cs.CV↗

arXiv2026

Behavioral Affinity Transduction for Zero-Shot Vision-Language Classification

An image that is hard to classify on its own may have a helpful neighbor in the same unlabeled batch. Zero-shot vision-language models (VLMs) score images independently and leave this evidence unused. We study small unlabeled query batches with no labeled examples. Visual similarity can reflect pose or background, so it may connect images from different classes. Each image's scores over the class vocabulary offer another way to choose neighbors. We introduce Behavioral Affinity Transduction (BAT), which builds a sparse graph from these class-response profiles. The graph supplies neighbor evidence during prediction. For EM-Dirichlet, it also screens candidate classes and initializes assignments. BAT plugs into direct and iterative readouts of a frozen VLM. Across diverse datasets, BAT improves the mean accuracy of every tested readout. In the main RN50 comparison, soft and hard EM-Dirichlet gain $4.22$ and $2.72$ percentage points.

cs.CV↗

arXiv2026

RayAR: Autoregressive Dominant Path Generation for Low-Overhead MIMO Beam Alignment

Beam alignment in multiple-input multiple-output (MIMO) systems requires selecting suitable transmit and receive beam pairs with limited measurement overhead. Although 3GPP Release 18 investigates beam prediction from partial measurements, collecting these measurements still incurs probing overhead. Geometry can focus this probing through the departure and arrival directions of dominant paths, whose identification requires accounting for coupled diffraction interactions. To address this challenge, we propose RayAR, an autoregressive method that generates dominant propagation paths from urban geometry. RayAR conditions candidate ranking on the path prefix, local diffraction geometry, and receiver reachability, updating this context after each selection until the receiver becomes visible. The completed path's departure and arrival directions rank beam pairs for probing, allowing the pair with the highest received power to be selected from a small candidate set. Under 3GPP Release 18 beam-management metrics, RayAR reduces probing by 96.88\% relative to exhaustive sweeping and achieves the highest optimal-pair hit rate among compared methods at the same budget. Real-world measurements further demonstrate the accuracy of this geometric guidance, with simulation-trained RayAR achieving the lowest departure and arrival angular errors among compared methods without fine-tuning and a mean arrival-direction error of 9.07$^\circ$.

eess.SP↗

arXiv2026

RFLocMatch: Reference-Conditioned Residual Learning from Angle-Delay Spectra for Accurate Localization

Radio fingerprint localization supports mobile robots and location-aware services when satellite positioning is unreliable. Angle-delay power fingerprints capture power distributions over angles and delays, but localization remains vulnerable to spatial ambiguity and measurement perturbations. Reflections and blockage can produce similar fingerprints at distant locations, while noise in query fingerprints can alter query-reference rankings despite a clean reference library. These effects can place a distant reference first in the ranking, creating tail errors. Similarity scores can generate plausible candidates, but reliable selection requires candidate-specific residual evidence and comparison across alternatives. This separation motivates RFLocMatch, which uses complementary joint and link-specific matching to preserve candidate locations supported by different links. Reference-conditioned residual learning then scores each candidate using the query and reference fingerprints, their absolute difference, and their element-wise product, while candidate-context modeling compares alternatives. Tail-focused training emphasizes costly errors, and inference replaces the initial match only when a candidate's score advantage exceeds a validation-calibrated threshold. On ray-tracing-generated data, RFLocMatch reduces dual-transmitter 99th-percentile error by 75.2% under link and receiver perturbations relative to the best-performing baseline. On real-world single-transmitter channel impulse response (CIR) measurements with motion-assisted angular-spectrum estimation, it attains 8.25-m 90th-percentile error and 3.83-m mean absolute error.

eess.SP↗

arXiv2026

RadioTraj3D: Height-Aware Adaptive Sampling for 3D Radio-Map Reconstruction from Ultra-Sparse Trajectories

Aerial networks require radio propagation information at unvisited positions and heights to plan routes, select links, and allocate wireless resources. A three-dimensional radio map (3D RM) represents propagation conditions over the service area, enabling these decisions before flight. However, constructing such a map from autonomous aerial vehicle (AAV) measurements is challenging, since radio measurements are available only along the trajectory, whereas the target covers the 3D service volume. Existing methods use fixed AAV trajectories that ignore how building distributions and heights affect electromagnetic propagation, missing the heights most informative for RM reconstruction. To address these issues, we propose RadioTraj3D, which uses building-height information to coordinate measurement selection and layer-wise reconstruction. Building-height variations reveal propagation-sensitive layers that guide height-adaptive sampling. We therefore propose G-METS to select geometry-sensitive heights and allocate an exact budget across edge, corridor, and open regions before channel acquisition. A dual-view reconstructor then integrates local three-dimensional boundaries with full-height context through one bounded coefficient per layer. Simulated outdoor and indoor maps demonstrate state-of-the-art reconstruction across environments and vertical grids. On real-world AAV measurements from the LACN dataset, RadioTraj3D improves peak signal-to-noise ratio by 0.84 dB and reduces normalized mean squared error by 17.5% over Completion AE.

eess.SP↗

arXiv2026

SateBeam: Beam-Aware Radio Map Estimation With Physics-Consistent Parametric Modeling for Unknown Multiple Satellites

Dense low-Earth-orbit (LEO) networks increasingly reuse spectrum across moving satellites and overlapping beams, making a spatial radio map essential for interference diagnosis and coordination. Constructing such a map from sparse ground power measurements is difficult because the active satellite subset and its cardinality are unknown, candidate footprints can be highly coherent, and beam pointing, width, effective power, Doppler, and background must be inferred jointly. Known ephemerides do more than enumerate visible candidates. Propagated positions determine candidate-specific ranges, viewing geometry, and spatial footprints, while radial velocities induce distinct time-frequency signatures. Their joint spatial--Doppler structure rejects candidates whose geometry or time--frequency signature conflicts with the observations before continuous beam inference. SateBeam therefore screens all candidates through Doppler-resolved nonnegative fitting. GPU-accelerated grid correlations initialize continuous off-grid refinement; a Gamma-likelihood Bayesian information criterion (BIC) selects model cardinality, and backward deletion and exchange repair greedy support errors. Across paired real-ephemeris scenarios, SateBeam recovers the exact support in every case and reduces independent-query RMSE from $0.655$ to $0.050$ dB relative to orthogonal matching pursuit, with consistent advantages under model mismatch and larger candidate sets. The code is available at https://github.com/UNIC-Lab/SateBeam.

cs.IT↗

arXiv2026

RMSampler: Sparse Radio Map Reconstruction with Active Sampling and Diffusion Posterior Correction

Reconstructing a radio map (RM) from sparse received-power measurements supports non-cooperative interference monitoring and spectrum management. However,sparse measurements leave uncertainty about both the global RM and the interfering emitter location, making informative sampling and accurate reconstruction challenging. To address these challenges, a novel joint sampling and reconstruction method named RMSampler is proposed in this paper to improve measurement selection and RM reconstruction under limited measurement budgets. For measurement selection, RMSampler evaluates global RM error reduction using the covariance of diffusion-generated RMs and localization error reduction using candidate emitter locations. Because these errors have different units, their expected relative reductions are combined into a scale-invariant sampling criterion, with each acquired measurement updating both uncertainty estimates. After sampling, the updated emitter-location probabilities guide a separate conditional diffusion ensemble for final reconstruction. To improve measurement agreement, an effective sample size (ESS) target guides robust posterior correction, followed by a minimum-distortion projection enforcing measurement and building constraints. For the reconstruction ensemble, analysis establishes that increasing likelihood power reduces expected robust measurement loss, while pretrained neural parameters and architecture remain unchanged. Experiments using simulated and real-world measured data demonstrate improved reconstruction under matched measurement budgets. In the Chongqing real-world measured data experiment, root mean square error (RMSE) decreases from 3.54 to 2.73~dB relative to random sampling under a common reconstruction method.

eess.SP↗

arXiv2026

Map2APS: A Physically Grounded Benchmark for Direct Angle Power Spectrum Prediction from Urban Geometry

Angle power spectrum (APS) characterizes the directional distribution of received signal power and is directly relevant to beam management and MIMO processing. While environment-aware learning has been widely studied for radio maps and path loss, direct map-to-APS prediction still lacks a standardized large-scale benchmark. This paper presents Map2APS, a physically grounded benchmark constructed from intelligent ray-tracing (IRT) path-level propagation records. Map2APS covers 51 equal-height urban maps and approximately 2.55 million Tx--Rx samples, with a strict cross-map split for evaluating generalization to unseen urban layouts. We benchmark representative model families and introduce MS-AReg as a strong reference baseline. On the full held-out test set of 249{,}993 samples, MS-AReg achieves a cosine similarity of 0.948, a peak location error of 1.20$^\circ$, and an inference latency of 0.101 ms/sample. We further report dominant-direction metrics, including Top-1 dominant peak hit rate and dominant peak recall, to evaluate whether predicted spectra preserve decision-relevant arrival directions. The benchmark, code, and evaluation scripts are released at https://github.com/UNIC-Lab/aps-data.

eess.SP↗

arXiv2026

RelLedger: Relational Information Governance for LLM Agent Organizations

In LLM agent organizations, shared records determine which facts are available for later decisions. A sender consults interaction histories before deciding whether to report an event. A delivery gap across histories does not show whose relationship drove the choice or whether the resulting record matters downstream. We introduce RelLedger to audit these links. It holds the event, evidence, risk, and message fixed while crossing the sender's histories with the event target and an unrelated actor. Role reassignment and history rewrites locate the controlling cue. Message and cost interventions show when the effect appears. An attribution ledger maps each claim to its required response cells and separates missing interventions from sampling uncertainty. Recipient replay follows delivered information into downstream decisions. Executable workflows for a simulated one-person company extend the audit to retrieved histories, tool calls, and shared ledger updates. Across GPT, Gemini, Claude, DeepSeek, and Qwen, the audit reveals model-specific control paths and smaller relation gaps under explicit loss rules. Claude sends the same factual notice 62.22 percentage points more often with conflict histories than with friendly histories. In executable workflows, strained histories reduce recipient review rates by 45.83 points relative to warm histories for Claude.

cs.MA↗

arXiv2026

Adaptive Beam Hopping and Power Control for Dual-Layer Over-the-Air Online Federated Learning in LEO Satellite Networks

This paper investigates over-the-air (OTA) computation enabled online federated learning (FL) in low-Earth orbit (LEO) satellite networks. Specifically, we consider a dual-layer OTA aggregation architecture, where ground devices upload analog model updates to serving satellites via uplink OTA aggregation, and satellites forward the aggregated signals to a data processing center through the second round OTA aggregation. Then, we formulate a long-term data-utilization maximization problem in which devices continuously collect new data and untrained samples gradually lose freshness. The problem is subject to the satellite beam budget, transmit-power limit, and global mean squared error (MSE) constraint that governs end-to-end aggregation distortion. This yields a coupled mixed-integer nonlinear programming (MINLP) problem, involving tightly coupled discrete beam-hopping decisions and continuous power control. Due to the combinatorial action space and nonconvex constraints, the problem is NP-hard and computationally intractable. Furthermore, the time-varying satellite topology and dynamic data generation render it a sequential decision-making problem, necessitating adaptive online scheduling. To address these issues, we cast the problem as a Markov decision process and develop a proximal policy optimization (PPO)-based deep reinforcement learning framework that jointly optimizes adaptive beam hopping and power control, using an MSE-aware reward to balance data utilization and aggregation accuracy. Numerical simulation results verify that the proposed algorithm consistently outperforms other benchmark schemes, achieving superior long-term data utilization and faster FL convergence while satisfying the MSE requirement.

cs.IT↗

arXiv2026

Nonlinear Curvature-Free Periodic Folding in Origami via Symmetry Classification of Linear Modes

Broadly studied origami crease patterns such as the Miura-ori are capable of rigid folding that maintains their spatial periodicity. However, periodic crease patterns generically require additional creases and fold into quasi-cylindrical shapes. Here, using group theory, we show that the folding properties of such sheets are largely determined by their spatial symmetries, known as layer groups. Within each symmetry class, the allowed linear shape-periodic modes of sheets are constrained and classified by the irreducible representation they belong to. Such classification further gives a sufficient condition, containing a symmetry constraint and a topological constraint, for the existence of a nonlinear strain mode. In this way, familiar special cases are placed within a unified framework that connects symmetry, network topology, and deployability. Finally, we turn our classification results into a predictive design principle that enables the rapid design of novel sheets with prescribed properties.

cond-mat.soft↗

arXiv2026

World-to-Wrist: Task-Conditioned Future Wrist Modeling for Fine-Grained Robot Manipulation

Vision-language-action (VLA) models often treat main-view and wrist-view observations as parallel visual inputs, overlooking their distinct roles in robot manipulation. Fine-grained manipulation, however, benefits from anticipating how wrist-local interactions may evolve under the global task context. To address this limitation, we present World-to-Wrist VLA (W2-VLA), a VLA model for fine-grained robot manipulation with task-conditioned future wrist modeling. Given current multi-view observations and a task instruction, W2-VLA contextualizes a set of latent modeling tokens as a compact interface between the vision-language model and the wrist predictor. Conditioned on this interface and the observed wrist history, the predictor forecasts future wrist latents, which are transformed into future-aware context for action prediction. In addition, we introduce W2-CoT, a synthesis pipeline that produces structured annotations describing manipulation progress, physical transition cues, and wrist-local evidence. These annotations provide auxiliary supervision that shapes the task-conditioned latent interface. Experiments on LIBERO, LIBERO-Plus, RoboTwin 2.0, and real-world manipulation tasks demonstrate improved fine-grained and contact-sensitive manipulation across single-arm and bimanual settings, while maintaining real-time action generation above $80$~Hz.

cs.RO↗

arXiv2026

A Tutorial on Learning-Based Radio Map Construction: Data, Paradigms, and Physics-Awareness

Radio maps (RMs) provide the digital representation of the wireless propagation environment, mapping complex geographical and topological boundary conditions to critical spatial-spectral metrics that range from received signal strength to full channel state information matrices. The integration of artificial intelligence into next generation wireless networks further necessitates the accurate construction of RMs as a foundational prerequisite for electromagnetic digital twins. This paper presents a comprehensive survey of learning-based RM construction, systematically addressing three intertwined dimensions: data, paradigms, and physics-awareness. From the data perspective, we review physical measurement campaigns, ray tracing simulation engines, and publicly available benchmark datasets, identifying their respective strengths and fundamental limitations. From the paradigm perspective, we establish a core taxonomy that categorizes RM construction into source-aware forward prediction and \added{source-agnostic} inverse reconstruction, and examine five principal neural architecture families spanning convolutional neural networks, vision transformers, graph neural networks, generative adversarial networks, and diffusion models. We further survey optics-inspired methods adapted from neural radiance fields and 3D Gaussian splatting for continuous wireless radiation field modeling. From the physics-awareness perspective, we introduce a three-level integration framework encompassing data-level feature engineering, loss-level partial differential equation regularization, and \added{architecture-level} structural isomorphism. Open challenges including foundation model development, physical hallucination detection, and amortized inference for real-time deployment are discussed to outline future research directions.

eess.SY↗

arXiv2026

A Tutorial on Movable Antenna-Enabled ISAC Systems: Fundamentals, Parameter Estimation, and Security Issues

Movable antenna (MA) technology has recently emerged as a promising paradigm for enhancing the flexibility and performance of wireless systems by allowing antennas to dynamically adjust their spatial positions within a confined region. Meanwhile, integrated sensing and communication (ISAC) has attracted significant attention as a key technology for next-generation wireless networks, aiming to integrate communication and sensing within a shared hardware and spectral framework. By leveraging the additional spatial degrees of freedom offered by MA, MA-enabled ISAC systems provide new opportunities to enhance both communication performance and sensing accuracy. However, the integration of MA into ISAC also poses new challenges in parameter estimation and security. In this tutorial, we provide a comprehensive overview of MA-enabled ISAC systems, with a particular focus on their fundamentals, parameter estimation, and security issues. First, we introduce the basic principles of MA and ISAC, and review representative MA-enabled ISAC systems and their potential applications. Then, we establish unified mathematical models for communication and sensing, and systematically review representative channel and sensing parameter estimation methods tailored to MA-enabled ISAC systems. Numerical comparisons are provided to illustrate the characteristics and performance of different estimation methods. Furthermore, we investigate the security issues of MA-enabled ISAC systems, introduce the fundamentals of physical-layer security (PLS), and summarize how the spatial reconfigurability of MAs can be exploited to enhance the security of ISAC systems. Representative case studies are presented to demonstrate the performance gains of MA-enabled secure ISAC systems. Finally, we identify several open issues and future research directions toward practical MA-enabled ISAC systems.

eess.SP↗

arXiv2026

BeamRMX: Radiation-Pattern-Driven Learning for Generalizable Beam Radio Map Prediction and Beam Management

The evolution toward sixth-generation (6G) wireless networks is driving larger antenna arrays and highly directional multi-beam transmission, making accurate knowledge of beam-dependent spatial coverage important for beam management and environment-aware network operation. Radio maps (RMs) provide such a representation, yet conventional RM prediction assumes omnidirectional or transmitter-level radiation. In beamformed multiple-input multiple-output (MIMO) systems, one propagation scene instead gives rise to many configuration-dependent beam radio maps (BeamRMs), creating challenges in beam representation and generalization. Existing methods either condition prediction on beam descriptors or use beam maps as auxiliary inputs to generic architectures. We propose BeamRMX, which, to the best of our knowledge, is the first dedicated framework to treat the spatial radiation pattern as the primary BeamRM query and learn how scene geometry transforms it into the received power field. XBase learns multiscale interactions between the radiation query and scene geometry, while an optional Evidence Adapter uses a few cross-configuration BeamRMs from the same scene. Matched-domain and zero-shot experiments show consistent gains over deterministic and diffusion baselines, including mean absolute error reductions of 26.1\% on unseen scenes and 47.8\% on an unseen configuration. Cross-configuration evidence further improves reconstruction and intra-sector beam refinement.

eess.SP↗

arXiv2026

PrismWF: A Multi-Granularity Patch-Based Transformer for Robust Website Fingerprinting Attack

Tor is a low-latency anonymous communication network that protects user privacy by encrypting website traffic. However, recent website fingerprinting (WF) attacks have shown that encrypted traffic can still leak users' visited websites by exploiting statistical features such as packet size, direction, and inter-arrival time. Most existing WF attacks formulate the problem as a single-tab classification task, which significantly limits their effectiveness in realistic browsing scenarios where users access multiple websites concurrently, resulting in mixed traffic traces. To this end, we propose PrismWF, a multi-granularity patch-based Transformer for multi-tab WF attack. Specifically, we design a robust traffic feature representation for raw web traffic traces and extract multi-granularity features using convolutional kernels with different receptive fields. To effectively integrate information across temporal scales, the proposed model refines features through three hierarchical interaction mechanisms: inter-granularity detail supplementation from fine to coarse granularities, intra-granularity patch interaction with dedicated router tokens, and router-guided dual-level intra- and cross-granularity fusion. This design aligns with the cognitive logic of global coarse-grained reconnaissance and local fine-grained querying, enabling effective modeling of mixed traffic patterns in WF attack scenarios. Extensive experiments on various datasets and WF defenses demonstrate that our method achieves state-of-the-art performance compared to existing baselines.

cs.CR↗

arXiv2026

Learn for Variation: Efficient AAV Trajectory Learning through a Differentiable Wireless World Model

Autonomous aerial vehicles (AAVs) enable data collection for sixth-generation Internet-of-Things networks, but their trajectories couple nonlinear wireless rates with long-horizon service progress. This paper views the evolution of AAV kinematics, channel state, and user backlog as a structured differentiable world model and develops Learn for Variation (L4V) to exploit that model efficiently. L4V replaces a discontinuous completion-time objective with a cumulative-backlog surrogate, unrolls the mission dynamics, and propagates pathwise sensitivities to a neural policy through the discrete adjoint recursion. The resulting derivative is exact conditional on a fixed exogenous-noise realization; stochastic expected-objective optimization still requires sampling. We show that the structured adjoint grows at most polynomially with the horizon and establish a stationary-point rate for fixed-step full-gradient descent under standard smoothness assumptions. The framework also learns shared OFDMA allocation under reparameterized shadowing and Rician fading, while distributional pretraining amortizes model-based optimization into forward-only deployment on unseen layouts. Paired stress tests cover channel-generator mismatch, noisy partial observations, a fixed-resource two-AAV extension, and a circular no-fly region. Code and configurations are available at https://github.com/UNIC-Lab/L4V-AAV. Against genetic-algorithm, DQN, A2C, DDPG, and differentiable model-predictive-control implementations, L4V reduces mission time by up to $65\%$, executes a default mission in $53$ ms, and completes all $60$ frozen-policy tests after pretraining on $1{,}600$ layouts.

eess.SY↗

arXiv2026

RMWorld: Task-Aware Radio World Models with Value-of-Information Guided Multi-Trial Learning for Multi-UAV Communication Control

Reliable multi-UAV communication control depends on predicting which aerial links will serve traffic before measurements are available. Radio world models (radio WMs) make such planning tractable, but their errors are nonuniform: a globally accurate model may still fail along high-demand corridors or association boundaries where rate errors reverse control decisions. This mismatch creates a learning challenge. Link queries must reduce decision-relevant channel uncertainty, while counterfactual trials must be filtered so that biased rollouts do not corrupt the policy. Existing acquisition and model-based control treat these budgets separately, valuing uncertainty, coverage, or optimistic return rather than risk reduction. We present RMWorld, a task-aware radio-WM framework that couples value-of-information channel calibration with credibility-diversity multi-trial selection. A biased propagation formula is corrected by a Bayesian residual, and each link is valued by its exact one-label reduction in locally linearized task-integrated posterior rate variance. Counterfactual branches are selected by a task-gated log-determinant objective, followed by conflict projection and fixed-batch validation. We derive the variance-reduction identity, prove posterior task-risk equivalence and the submodular greedy guarantee, and establish a scoped first-order non-interference result. Across 100 paired 3GPP trials RMWorld reaches 0.949~bit/s/Hz task-weighted RMSE, and across 30 severe-load DeepMIMO trials it reduces median backlog by 0.967 versus Ensemble UCB at 37.5\% more offline rollouts.

cs.IT↗