arXiv subjects

Rui Wang

Publications and source records attributed to Rui Wang.

At least 37 records · Page 2Linked to original sources

arXiv2026

Federated Layer-Wise Exchange for Cross-Client Money Laundering Pattern Detection

Subgraph pattern detection is a fundamental graph mining task central to anti-money laundering (AML) in finance. However, state-of-the-art graph neural network (GNN)-based methods assume centralized graph access, impractical when transaction data cannot be shared across institutions. In practice, graphs are distributed across clients, where local GNN training diverges from centralized learning, creating representation and adjoint equivalence gaps that induce a parameter-gradient gap. We formalize this as a structural observability problem, where AML patterns crossing subgraph boundaries become locally unidentifiable. To bridge these gaps, we propose a layer-wise exchange framework: clients synchronize node representations each forward pass layer and adjoints each backward pass, without exposing raw features or labels. Under a shared-parameter assumption, we prove node representations and parameter gradients are equivalent to those of centralized GNN training. Experiments on directed multigraphs with money-laundering patterns show layer-wise exchange performs best with per-step synchronization and remains effective under practical per-epoch synchronization. Our results show layer-wise exchange and parameter synchronization to be complementary, supporting distributed pattern detection in privacy-constrained financial settings.

cs.LG↗

arXiv2026

DepthTile: Depth-Guided Existing-Image Self-Tiling with Input-Side Tileability Assessment

Existing-image self-tiling aims to transform a given image into a seamlessly repeatable tile while preserving its original semantics and local details. This task requires weak editing to retain the source but leave periodic seams, whereas strong editing improves tileability at the large risk of content drift.Existing diffusion-based tiling pipelines alleviate boundary discontinuities, yet lack awareness of which regions are geometrically important to preserve. In this work, we propose DepthTile, a depth-guided self-tiling method whose generation module requires no retraining of the diffusion backbone. It converts monocular depth into a spatial preservation prior and integrates it into the timestep-dependent masking mechanism of Tiled Diffusion. DepthTile converts depth into a spatial editability map and fuses it with the differential diffusion mask. This strengthens source preservation in near-field regions indicated by the monocular depth prior while retaining editing flexibility near compatible background boundaries. To access when self-tiling is feasible, we introduce the Self-Tiling Ability Score (STAS), a lightweight input-side predictor based on RGB, gradient, depth, and depth-gradient cues. On a 335-image benchmark, relative to the default Tiled Diffusion pipeline, DepthTile reduces MAE, LPIPS, and Tiling Score by 12.8%, 26.7%, and 8.4%, respectively. STAS reliably enables difficulty-aware analysis and further supports compatibility-aware pairwise image tiling.

cs.CV↗

arXiv2026

Tornado Wave-Encoded Point Spread Functions for Multi-Period Three-Dimensional Localization Imaging

Three-dimensional (3D) localization microscopy using rotational point spread functions (PSFs) is fundamentally challenged by limited axial range, poor PSF compactness, and depth-decoding ambiguity -- particularly in dense specimens with heavy PSF overlap. To address these limitations, we introduce a 3D localization approach based on tornado wave (ToW)-PSFs, combined with a convolutional neural network (CNN) designed to decode continuous rotational patterns and resolve multi-period axial ambiguity. Our engineered PSF encodes the 3D position of each nanoparticle into a compact double-lobe pattern whose orientation rotates with axial position. This design yields a clean, well-defined structural evolution across an unprecedented 15 um axial range, with an average rotation rate of 21.8 degrees/um, ensuring robust long-range depth encoding. To recover coordinates from overlapping emitters, we systematically benchmark a conventional matching-pursuit (MP) algorithm against our CNN. While MP performs adequately in sparse scenes, the CNN demonstrates exceptional robustness in dense fields, achieving a 70.24% localization accuracy at 20 particles per image-substantially outperforming MP's 22.52% -- while also significantly suppressing axial period-jump errors. Experimental validation on nanoparticles confirms reliable single- and multi-particle localization throughout the entire working range. Our results establish ToW-PSFs as a powerful and practical optical encoding strategy for high-density, extended-range 3D localization imaging.

physics.optics↗

arXiv2026

OGPO: Offline Goal-conditioned Policy Optimization for Recoverable Vision-Language-Action Models

Vision-language-action (VLA) models have shown strong promise in robotic manipulation, yet their post-training still predominantly relies on trajectory-level supervised imitation over robot demonstrations. While effective for learning feasible actions, this paradigm supervises policies to reproduce expert actions at each step, biasing them toward demonstration-specific action paths and providing limited guidance for recovering toward task-progress states once execution deviates from demonstrated trajectories. To address this limitation, we propose OGPO, an Offline Goal-conditioned Policy Optimization framework for recoverable VLA post-training. Instead of treating offline demonstrations merely as step-wise action labels, OGPO adaptively relabels trajectories with semantic key states and constructs goal-conditioned process rewards to optimize the policy for reaching these task-progress states. In this way, OGPO shifts VLA post-training from trajectory-level action imitation to key-state reachability learning, enabling policies to acquire a more robust ability to complete goal states from feasible off-demonstration states without requiring additional online interaction. Experiments on LIBERO and MetaWorld show that OGPO consistently improves VLA policy performance over standard supervised fine-tuning. Moreover, evaluations on LIBERO-Plus and our proposed LIBERO-ReAct, a mid-execution perturbation benchmark, further demonstrate that OGPO achieves stronger robustness and goal-directed recoverability under distribution shifts and recoverable off-demonstration states.

cs.AI↗

arXiv2026

MENTOR: Learning from Failure with On-Policy Pedagogical Intervention

Reinforcement Learning from Verifiable Rewards (RLVR) is a key driver for Large Reasoning Models, but it is vulnerable to "zero-reward collapse", a training failure where a sudden increase in task difficulty causes the learning signal to vanish. We argue that the conventional approach of discarding these failed trajectories is wasteful, as they contain valuable diagnostic information about the model's cognitive gaps, a bright side that can be leveraged for recovery. Existing solutions, however, often regress to static, "off-policy-style" interventions like pre-defined hint libraries or perform post-hoc refinement, failing to provide the adaptive, forward-looking guidance needed to escape the collapse. To address this, we propose a paradigm shift towards on-policy pedagogical intervention and introduce MENTOR, a multi-agent framework that acts as a live mentor. MENTOR diagnoses the root cause of failure in real-time and dynamically generates targeted, instructional prompts to guide the learning agent's next attempt. As a plug-and-play module, MENTOR integrates seamlessly into existing policy optimization pipelines like GRPO without modifying the training infrastructure. Extensive experiments on math and code generation show that MENTOR effectively mitigates zero-reward collapse, outperforming state-of-the-art baselines. Notably, it achieves massive average relative gains of up to 78.3% on Llama-3.2-3B-Instruct over its base model.

cs.AI↗

arXiv2026

Nested Instrumental Variables Analysis: Switcher Average Treatment Effect, Identification, Efficient Estimation and Generalizability

Instrumental variables (IVs) are widely used to estimate causal effects from non-randomized data. A canonical example is a randomized trial with noncompliance, in which the randomized treatment assignment serves as an IV for the non-ignorable treatment received. Under a monotonicity assumption, a valid IV nonparametrically identifies the average treatment effect among a latent complier subgroup, whose generalizability is often under debate. In many studies, there exist multiple versions of an IV, for instance, different nudges to take the same treatment in different study sites in a multicenter clinical trial. These different versions of an IV may result in different compliance rates and offer a unique opportunity to study IV estimates' generalizability. In this article, we introduce a novel nested IV assumption and study identification of the average treatment effect among two latent subgroups: always-compliers and switchers, who are defined based on the joint potential treatment received under two versions of a binary IV. We derive the efficient influence function for the SWitcher Average Treatment Effect (SWATE) under a nonparametric model and propose efficient estimators. We then propose formal statistical tests of the generalizability of IV estimates under the nested IV framework. The proposed tests are flexible nonparametric generalizations of classical overidentification tests that allow estimating nuisance parameters using machine learning tools. We apply the proposed method to the Prostate, Lung, Colorectal and Ovarian (PLCO) Cancer Screening Trial and study the causal effect of colorectal cancer screening and its generalizability.

stat.ME↗

arXiv2026

Robust identification of drive-by sensing ride-hailing market with Points of Interest monitoring under uncertain ride demand

Taxi-based mobile sensing has emerged as a cost-efficient paradigm for large-scale urban environmental monitoring. In practice, both passive and active sensing strategies are adopted by ride-hailing platforms. Passive sensing, conducted during passenger-serving trips, is constrained by stochastic and spatially imbalanced ride demand, leading to limited and uneven coverage. Active sensing, executed by vacant taxis, provides greater control over sensing operations but incurs additional operational costs, and is thus typically treated as a supplementary strategy. To address the inefficiencies of the conventional "passive-first, active-second" paradigm, which may delay the monitoring of critical Points of Interest (POIs) and increase system-wide costs, we propose a Distributionally Robust Optimization (DRO)-based framework for active mobile sensing. First, we develop an enhanced A*-based drive-by sensing routing policy that integrates vehicle-task matching while capturing both global routing efficiency and local sensing opportunities. Second, we formulate the active sensing problem as a DRO model that explicitly accounts for uncertainty in ride demand through an ambiguity set of probability distributions, enabling robust decision-making for vacant taxi routing and vehicle-task matching. The proposed framework is evaluated on both static and dynamic mobile sensing settings using real-world data. Computational results demonstrate that our approach achieves better performance in terms of sensing coverage, operational cost, and robustness compared to benchmark strategies, highlighting the value of integrating distributional robustness into taxi-based sensing operations.

math.OC↗

arXiv2026

Robust Causal Inference for EHR-based Studies of Point Exposures with Missingness in Eligibility Criteria

Missingness in variables that define study eligibility criteria is a seldom addressed challenge in electronic health record (EHR)-based settings. Patients with incomplete eligibility information are typically excluded from analysis without consideration of the (implicit) assumptions being made, leaving study conclusions subject to potential selection bias. In an effort to ascertain eligibility for more patients, researchers may look back further in time prior to study baseline, inappropriately including individuals who, unbeknownst to the researcher, would fail to meet eligibility at baseline. To the best of our knowledge, however, little work has been done to mitigate these concerns. We propose a robust and efficient estimator of the causal average treatment effect on the treated, defined in the study-eligible population, where eligibility-defining covariates are missing at random. The approach facilitates flexible machine-learning strategies for component nuisance functions while maintaining valid asymptotic inference. This method is applied to EHR data from Kaiser Permanente on 14,809 patients undergoing bariatric surgery, comparing two surgical interventions for long-term weight and glycemic outcomes among severely obese patients with type II diabetes mellitus. Our results confirm a weight-loss advantage for Roux-en-Y gastric bypass over sleeve gastrectomy, but are less suggestive of a diabetes remission advantage than complete-case analyses indicate.

stat.ME↗

arXiv2026

MORA: Modeling Observed Changes for Drift-Robust Time-Series Anomaly Detection

Time-series anomaly detection (TSAD) identifies deviations from patterns learned from historical data. In non-stationary settings, distribution drift and true anomalies can cause similar local changes, making it difficult to tell whether a deviation reflects abnormality or evolving context. Existing methods typically adapt to detected shifts or learn drift-insensitive representations, but do not resolve this ambiguity. We define this problem as \emph{temporal change disambiguation}: determining whether a local deviation is explained by broader temporal evolution. We introduce MORA, a drift-robust TSAD framework that reconstructs the same local target from paired short- and long-term views. The reconstruction gap measures contextual support for a local deviation, and a data-dependent correction mechanism conservatively adjusts the primary local anomaly score. Context can only reduce the score when it improves reconstruction of the same target. MORA needs neither drift annotations nor online adaptation. Experiments on four TSAD benchmarks show strong robustness to non-stationarity while preserving sensitivity to genuine anomalies.

cs.LG↗

arXiv2026

Variational-Ising-Attention:Tailored Attention Matters for Science

Attention enables context modeling via query-key scoring with softmax normalization. Driven by industrial long-context demands, mainstream research has converged toward sparsity and efficiency, yet softmax's independence assumption persists. For scientific tasks unburdened by long-token constraints, however, richer structured coupling may often be essential, making tailored attention both viable and more appropriate. To this end, we propose Variational-Ising-Attention (VIA), which augments softmax normalization with an interacting Ising model; attention patterns emerge from learnable pairwise couplings via variational mean-field inference, extending attention from a ranking over isolated items to a collective state over interacting entities. We instantiate VIA on retrosynthesis reaction center prediction and, as a controlled internal ablation, on protein residue contact prediction, two structured prediction tasks governed by cooperative constraints: cooperative bond-breaking for retrosynthesis and inter-residue interactions for protein contact prediction. Comprehensive experiments across model variants, coupled with mechanistic analyses, demonstrate that VIA substantially outperforms standard softmax attention. More broadly, our findings suggest that for scientific problems, the optimal solution is not general-purpose efficiency, but appropriately tailored attention aligned with intrinsic domain structure. This work provides a theoretically grounded and empirically validated instantiation of this paradigm.

cs.LG↗

arXiv2026

Multi4D: High-Fidelity Dynamic Gaussian Splatting via Multi-Level Competitive Allocation

Dynamic 3D Gaussian splatting faces a fundamental tension between motion consistency and visual fidelity. Deformation-based approaches preserve temporal correspondence but suffer from motion over-factorization, oversmoothing high-frequency dynamics. In contrast, 4D-primitive methods capture fine visual details yet incur temporal overparameterization, breaking object identity and leading to severe storage overhead. To resolve this, we introduce Multi4D, a framework for high-fidelity dynamic Gaussian Splatting based on multi-level competitive allocation. Instead of a monolithic representation, we distribute modeling capacity across three structured levels: static structure, persistent dynamic geometry, and transient appearance primitives. Through shared rasterization and residual-driven optimization, these levels dynamically compete to explain photometric error, enabling adaptive specialization without pre-assigned decomposition. This allocation preserves long-term motion consistency while capturing fine dynamic detail, achieving state-of-the-art rendering quality and real-time performance with significantly fewer dynamic primitives. Furthermore, because our representation explicitly tracks compact persistent Gaussians over time, semantic features can be embedded afterward, enabling Multi4D to achieve state-of-the-art 4D segmentation accuracy with an order-of-magnitude speedup. Project page: https://batfacewayne.github.io/Multi4D.io/

cs.CV↗

arXiv2026

Know Thyself, Teach Thyself: Internal Information Flow for Selective Self-Distillation

Self-distillation turns knowledge distillation into a closed learning loop and offers a path toward recursive self-improvement. Without an external teacher, however, the model must determine both what information can improve its supervision and which induced changes should be learned. Existing methods typically improve teacher-generated data or select training examples in isolation, leaving the information transferred between these stages unmeasured. We introduce InFlow, a retrieval-guided on-policy self-distillation framework that models this process as potential-to-realized information flow. InFlow first retrieves potentially informative sources using certainty-calibrated hidden-state trajectories, then measures their realized effect through the Jensen--Shannon divergence between the teacher's initial and retrieval-conditioned answer beliefs. Examples with larger belief shifts are selected for on-policy distillation. Our analysis formalizes the information optimized by retrieval and selection and relates the answer-level shift to the teacher--student distillation gap. Across four open-weight language models and three knowledge domains, InFlow achieves the strongest cross-model average among the compared selection methods, with ablations supporting both stages of the framework. Our code is available at https://github.com/1240148048/INFLOW.

cs.LG↗

arXiv2026

Who Is Your Agent Serving? Provider-Side Indirect Prompt Injection in Proactive Agents

Proactive personal agents increasingly decide what to recommend, how to personalize advice, and what follow-up assistance to offer, creating a new user-decision attack surface for provider-side indirect prompt injection. We show that an external provider need not access private user context, compromise the agent, or gain additional permissions: by controlling only content associated with its own target, it can redirect an otherwise benign agent to advance that target, recruit legitimately available user context to justify it, and proactively reduce the friction of adoption. We characterize this failure mode through Target Control, Private Binding, and Prospective Support, which respectively steer what the agent advances, how it connects the target to the user, and what target-specific assistance it offers next. Across three proactive-agent environments and six simulated user models, the full attack increases target authorization in all tested environment-user-model combinations, with a macro gain of up to 77.4 percentage points. Controlled replay shows that correct user-target binding is more consequential than additional proposal detail alone, while a multi-turn extension reveals that provider objectives can remain influential even without final authorization by reshaping how the agent responds to user constraints and resistance. These findings expose a broader trust boundary: capabilities designed to serve the user can be redirected toward objectives originating outside the user-agent relationship.

cs.CR↗

arXiv2026

EMODE: Dynamic Para-Semantic Experts for Emotion-Aware Speech Language Modeling

Large speech language models have demonstrated strong capabilities in unified cross-modal understanding and generation, yet paralinguistic cues, especially emotion, remain difficult to preserve. Existing systems typically rely on entangled acoustic representations, which allow the underlying language model to depend excessively on recovered lexical content instead of grounding its behavior in acoustic-prosodic evidence. We address this limitation with EMODE, an emotion-aware speech language model built around \textbf{Dynamic Para-Semantic Experts (DPSE)}. DPSE decomposes continuous speech features into semantic and paralinguistic pathways, routes them dynamically, and fuses them before integration into the language model. To turn this structural decomposition into functional specialization, EMODE is trained with a three-stage curriculum consisting of semantic warm-up, paralinguistic activation, and joint refinement, guided by Orthogonal Expert Guidance (OEG), Semantic-to-Acoustic Alignment (SAA), and Gating Diversity Regularization (GDR). Experiments on SER test, empathetic response evaluation, and the newly constructed bilingual MEPA benchmark show that EMODE improves the balance between lexical fidelity and emotional sensitivity, strengthens affect-grounded response generation, and exposes the value of explicit para-semantic factorization for robust cross-corpus emotion understanding.

cs.CL↗

arXiv2026

MedFeat: Model-Aware and Explainability-Driven Feature Engineering with LLMs for Tabular Prediction

In clinical tabular prediction, classical machine learning models with feature engineering often outperform neural methods. LLMs are increasingly used to automate this process, acting as domain experts that propose diverse feature transformations to boost downstream performance. However, the feature generation process of existing LLM-based methods is agnostic to the downstream learner: the LLM receives no signal about which features currently drive predictions or where the model's representational capacity falls short, so proposals are neither targeted to promising regions of the feature space nor tailored to the learner's inductive bias. This shortcoming is amplified in healthcare data, which simultaneously exhibits class imbalance, heterogeneous feature spaces, and strict interpretability requirements. In this paper, we propose MedFeat, the first feature engineering framework inspired by the workflow of machine learning practitioners, leveraging model-awareness and feature importance signals to iteratively guide feature discovery for clinical tabular learning. We evaluate MedFeat on a broad range of challenging real-world clinical tasks and show that it statistically significantly outperforms state-of-the-art baselines, with an average F1 improvement of more than 10% over the baseline across models with distinct inductive biases.

cs.LG↗

arXiv2026

The odd-parity altermagnetism induced reconstruction of the Chern-insulating phase in Haldane-Hubbard model

Odd-parity altermagnetism(ALM) extends compensated collinear magnetism beyond the even-parity spin splitting of conventional altermagnets, but its role in correlated topological phases remains largely unexplored. Using the cluster slave-spin method, we show that the odd-parity ALM appearing in the ALM Chern-insulating phase of Haldane-Hubbard model significantly reconstructs the local topology in the conventional Chern-insulating phase, while the total Chern number remains unchanged compared to the Chern-insulating phase. The Berry curvature becomes spin and valley selective; zigzag ribbons develop chiral-symmetry-breaking edge states; while armchair ribbons remain inversion symmetric. The optical response mirrors this separation between the local reconstruction and the global topology: low-energy spectra are governed by quasiparticles near the gap, whereas the low-frequency Hall conductivity stays quantized, $σ_{\rm T\uparrow}(Ω\to 0)=σ_{\rm T\downarrow}(Ω\to 0)=e^2/h$. These results establish the Haldane-Hubbard model as a minimal correlated platform for odd-parity altermagnetic topology.

cond-mat.str-el↗

arXiv2026

AnyStep-WAM: Budget-Aligned Distillation and Adaptive Inference for World Action Models

World-action models (WAMs) couple predictive visual modeling with action generation, typically relying on iterative denoising with a fixed denoising steps. However, manipulation tasks contain actions chunks with varying sensitivity to generation errors: critical actions require precision, while less sensitive actions allow faster generation with fewer denoising steps. Here we introduce AnyStep World Action Model, a general framework for tunable-budget prediction and scene-dependent computation allocation. Our budget-aligned teacher-trajectory distillation trains interval-conditioned flow maps using explicit frozen-teacher transitions and shared low-rank adapters, supporting action generation from one-step prediction to multi-step refinement. Building on this capability, a lightweight risk-benefit scheduler predicts teacher-curvature-based difficulty and budget-specific student-teacher fidelity from a single one-step preview, selecting the smallest budget predicted to satisfy risk-adaptive fidelity requirements. We evaluate our framework on three widely used WAMs Motus, FastWAM, and LingBotVA using RoboTwin 2.0. Our method reduces average denoising steps by 60.2%, 49.8%, and 85.28%, respectively, while maintaining baseline task success rates. In particular, our AnyStep training substantially improves model performance under a one-step denoising budget, increasing task success rates by 7.07%, 12.08%, and 8.94% on Motus, FastWAM, and LingBotVA, respectively. Experiments on six real-world manipulation tasks further validate its effectiveness.

cs.RO↗

arXiv2026

GraphCert: Bootstrap Agentic Graph Reasoning with Certified Evidence Rubrics

Graph agents extend large language models (LLMs) with the ability to actively explore and reason over knowledge graphs through multi-step interactions with graph tools. However, training capable graph agents typically requires large collections of question-answer pairs and reasoning trajectories, whose manual construction is costly and difficult to scale. Moreover, employing proprietary LLMs to generate such supervision further risks exposing sensitive graph data to external services. Therefore, we propose GraphCert to bootstrap agentic graph reasoning with certified evidence rubrics during post-training. Specifically, the Bootstrapped Graph Quizzer guided by generation controls produces graph-grounded QA pairs and marks supporting evidence, which undergo execution certification and semantic curation. The accepted evidence is then canonicalized into certified evidence rubrics that later reward Graph Solver evidence alignment alongside answer correctness during GRPO training. Experiments on five graph reasoning domains in GRBENCH demonstrate that GraphCert consistently outperforms substantially larger LLM agents and post-training method. Furthermore, our analysis demonstrates that the learned policy transfers robustly across heterogeneous graph domains, suggesting that GraphCert acquires reusable graph-reasoning capabilities rather than domain-specific patterns. These results establish executable self-certification as an effective approach to self-training compact graph reasoning agents. Our code will be made publicly available.

cs.AI↗