Searcharxiv⌕ Search

arXiv subjects

Wenhao Yuan

Publications and source records attributed to Wenhao Yuan.

At least 19 recordsLinked to original sources

Reflection Is Not Always Worth It: Budgeted Reflection Allocation for Recommendation Agents

This work aims to make recommendation agents more efficient by reducing unnecessary LLM reflection while preserving full-catalog ranking and inference reranking. Since BRAVE changes only how training-time reflection is allocated, it does not introduce new user data requirements or additional LLM exposure beyond the base agent protocol. The main potential risk is that a poorly calibrated allocator may assign less reflection to users whose preferences are sparse, niche, or under-represented, which could weaken personalization for those users or indirectly affect item exposure. This risk can be mitigated through deployment-time auditing and conservative allocation design. In practice, reflection budgets should be evaluated not only by aggregate Recall or NDCG, but also across user-history lengths, item popularity groups, and application-relevant cohorts when such analysis is permitted. The allocator should rely on task-side ranking evidence rather than sensitive attributes, and fallback policies can reserve a small portion of the budget for random or fairness-aware coverage when subgroup robustness is important. Privacy risks can be controlled with the same protections required by the base recommendation agent: minimizing user text sent to the LLM controller, anonymizing user identifiers, retaining only necessary interaction evidence, and applying standard access-control and logging policies. Overall, BRAVE is designed as a cost-aware allocation layer, and its ethical deployment depends on validating that the saved computation does not come at the expense of vulnerable users or responsible exposure.

cs.IR↗

Take a Step Back: A Dual-Granularity Raw Feature Empowered Intermediate Fusion Graph Convolutional Network for Multimodal Recommendation

Although multimodal recommendations have shown the ability to learn user preferences and item properties by leveraging explicit multimodal information, they remain constrained by two critical limitations: low-quality representation learning and modality fusion. For the former, existing solutions primarily focus on multi-granularity representation learning; however, we argue that training such representations is difficult due to the inherent data sparsity problem in recommendation scenarios. For the latter, existing solutions often rely on contrastive learning to align representations of different modalities to facilitate modality fusion, yet alignment-only objectives may over-compress valuable modality-specific information. To this end, we suggest \underline{``Take a Step Back"} and propose a \textbf{D}ual-granularity raw feature empowered \textbf{I}ntermediate fusion \textbf{G}raph \textbf{C}onvolutional \textbf{N}etwork (\textbf{DIGCN}) for multimodal recommendation. DIGCN leverages the multimodal understanding capabilities of Large Language Models (LLMs) to construct dual-granularity raw features directly. Furthermore, DIGCN introduces an intermediate fusion graph convolutional network equipped with dynamic cross-modality weight correction, designed to capture cross-modality signals and achieve effective modality fusion. Comprehensive experiments on four real-world datasets validate that DIGCN consistently outperforms a variety of strong baselines. Additional analyses confirm its superiority under varying levels of data sparsity and cold-start scenarios. Notably, DIGCN demonstrates high extensibility, capable of further benefiting from additional contrastive learning-based alignment tasks.

cs.IR↗

Beyond Successor Accuracy: State Retention for Recursive Self-Improvement in Recommendation

Recommendation recursive self-improvement (Rec-RSI) feeds recommender outputs into subsequent training. Evaluating each round solely through its latest model assumes that the successor consolidates the update, although pre- and post-update models may retain complementary ranking decisions. We term this \emph{distributed progress} and quantify it using cross-generation advantage (CGA), a marginally matched contrast between cross- and within-generation model pairs. A rank-separation statistic, label-free at selection time, predicts which family to retain. Across four datasets and three sequential recommendation encoders, the preferred retention regime varies by architecture: cross-generation pairing benefits GRU4Rec and SASRec, whereas FMLP initially favors within-generation pairing and shifts toward cross-generation pairing after a second update. Rank separation selects the stronger family in 12/12 first-update and 5/6 second-update dataset-encoder settings; on held-out tests, the selected family outperforms the direct successor in 34/36 trajectories. Five transfer mechanisms do not consistently reproduce these gains in one model. These findings establish state retention as a distinct Rec-RSI problem: progress may reside in relations between generations as well as in the latest model. Code is available at \href{https://github.com/Jinfeng-Xu/RecRSI}{https://github.com/Jinfeng-Xu/RecRSI}.

cs.IR↗

Dude: A Dual-Detection Multi-Agent System for Paper-Code Discrepancy Detection

LLM-empowered paper-code discrepancy detection has received growing concern since the scaling of research submissions exceeds the manual review capability. However, the limited context capacity and one-sided discrepancy detection of existing single-agent LLM paradigms lead to an inferior recall performance in detecting discrepancies. In this paper, we propose Dude, the first Dual-Detection Multi-Agent System for paper-code discrepancy detection. We discover that the granularity asymmetry of the paper-language and code-language introduces over-interpretation and over-reporting challenges in a multi-agent system design for discrepancy detection, resulting in increasing false positives. To address this, we propose a granularity-aligned negotiation and a two-stage salience-filtering mechanism in Dude, which effectively prevents agents from falsely reporting discrepancies. Experimental results in real-world paper-code discrepancy datasets showcase Dude's significant recall and precision improvement by up to 22.8%, increasing F1 score by up to 18.7% compared to baseline methods.

cs.AI↗

A compact vapor-cell optical frequency reference with fractional frequency instability around $10^{-16}$

Compact optical frequency reference with high stability is essential for field applications such as navigation and geodesy, yet vapor cell systems have remained confined to fractional instabilities over $10^{-15}$. Here, we report a molecular iodine reference that reaches an instability of $7 \times 10^{-16}$ at 1000 s and operates at the $10^{-16}$ level from 200 to 2000 s, surpassing the best reported vapor cell standards by approximately a factor of three. This achievement is enabled by a monolithic, drift immune spectroscopic unit bonded to an ultra low expansion glass substrate with precision control of key parameters.The entire system occupies only 25 L.The system achieves $5 \times 10^{-15}$ instability at 1 s and reaches the $10^{-16}$ level over the 200 to 2000 s averaging-time range, representing the first medium term stability at the $10^{-16}$ level from a compact, field ready vapor-cell reference. Our work demonstrates that $10^{-16}$ instability can be engineered into portable systems, opening a path to high precision time-keeping beyond the laboratory.

physics.atom-ph↗

When Is Shallow Enough? Adaptive Split Federated Learning with Client-Specific Sufficiency Estimation

\textit{Split Federated Learning} (SFL) enables distributed model training by splitting networks between the server and clients. However, under client heterogeneity, the conventional static split strategy may be suboptimal because clients can differ in data distributions, adaptation dynamics, and representation learning progress, making a single split point insufficient to accommodate client-specific training states. In this paper, we propose \textsc{FedSGA}, a \textbf{S}ufficiency-\textbf{G}uided \textbf{A}daptive split \textbf{Fed}erated learning framework that addresses this question through client-specific shallow sufficiency estimation. First, we introduce a client-specific adaptation channel based on private prompt tokens, which tracks local adaptation dynamics separately from the shared backbone and provides a lightweight signal for detecting whether client adaptation remains active. To further avoid repeated online probing over multiple candidate depths, we design a shallow sufficiency estimator that combines cross-client semantic alignment, temporal interface stability, and prompt-state variation to estimate whether the shallowest split is already sufficient. Finally, we introduce a split-compatible interface harmonization module that projects activations from different split depths into a shared semantic space, improving the comparability of heterogeneous client interfaces before server-side prediction. Extensive experiments on multiple heterogeneous benchmarks demonstrate the effectiveness of \textsc{FedSGA} in improving model performance compared with state-of-the-art methods while reducing unnecessary client-side computation.

cs.DC↗

Beyond Memory Majority: Latent-Source Reasoning for Multi-Agent Memory Arbitration

Long-term multi-agent systems continuously accumulate the memories produced by different agents. Existing memory methods typically treat retrieved memories as independent evidence and combine them through voting or weighting. However, this independence assumption often fails in multi-agent settings: memories written by different agents may inherit the same upstream source or shared bias, causing correlated evidence to be repeatedly counted and creating a false majority. We term this failure mode \textit{Memory Correlation Bias}. To address the issue, we propose the \textbf{C}orrelation-\textbf{A}ware \textbf{M}emory \textbf{A}rbitration (CAMA) framework that jointly decouples retrieved memories and recovers missing independent evidence. We model the retrieved memories as query-conditioned evidence groups and combine neural dependency inference with provenance-based symbolic priors to estimate the effective number of independent evidence sources, thereby preventing correlated memories from forming a false majority. Since critical independent evidence may be absent from the initial retrieval set, \textsc{CAMA} further learns a sequential recovery policy that actively retrieves alternative evidence or traces upstream sources before making the final decision, aiming to recover sufficient independent evidence for reliable arbitration while minimizing retrieval cost. Experiments on multiple benchmarks demonstrate the superiority of our method over the state-of-the-art baseline methods, suppressing false majorities induced by correlated memories.

cs.AI↗

Learning What to Activate: Combinatorial Capability Allocation for Long-Horizon Multimodal Agents

Long-horizon multimodal agents rely on specialized capabilities for perception, retrieval, reasoning, verification, and execution. Existing designs typically activate a fixed capability set or invoke a predefined workflow, incurring substantial computational overhead while failing to accommodate stage-dependent capability demands. In this paper, we study the \textit{combinatorial capability allocation} problem for long-horizon multimodal agent systems, where the system selects a cost-sensitive subset of specialized capabilities at each interaction stage, which is nontrivial since capability values depend on the selected subset, while previous allocations alter the states encountered by subsequent decisions. We introduce \textsc{CoCA}, an on-policy learning framework that recovers a deployable capability-subset policy from sparse conditional comparisons. On states visited by the student policy, the stronger teacher compares the marginal net values of candidate capabilities, conditioned on the currently selected subset. Then, we adopt a conditional utility model to transform such comparisons into an autoregressive capability-subset policy, avoiding explicit enumeration. We further introduce dual-level on-policy distillation to address distribution mismatch both across environment states and within the partial subsets encountered during set construction. Finally, trajectory-level reinforcement learning refines the distilled policy toward task success, activation cost, and allocation stability. At inference time, allocation is performed solely by the lightweight student policy without teacher queries or online updates. Experiments on long-horizon multimodal environments and controlled capability-demand shifts demonstrate the superiority of our method over the state-of-the-art baseline methods.

cs.AI↗

Neural Tree Collaborative Filtering: Rethinking Graph Collaborative Filtering as Tree Collaborative Filtering with Curvature-Aware Propagation Depth

Graph Collaborative Filtering (GCF) has become the dominant paradigm in modern recommender systems by modeling user-item interactions as a bipartite graph and propagating embeddings through a fixed number of message-passing layers. However, applying a uniform propagation depth to every node ignores a fundamental property of real interaction graphs: nodes differ substantially in their local connectivity, so peripheral nodes quickly suffer from over-smoothing while hub-like nodes remain under-explored beyond their immediate neighborhood. In this paper, we revisit GCF from a tree-structured perspective and propose Neural Tree Collaborative Filtering (NTCF), a framework that re-interprets each node's local neighborhood as a rooted tree and assigns a node-specific propagation depth based on a closed-form local-degree-imbalance score that serves as a discrete Ricci-curvature proxy. We provide a theoretical analysis showing that (i) NTCF strictly generalizes NGCF, degenerating to NGCF when all curvature-induced depth adjustments vanish (a lower bound on its representation power), and (ii) the curvature-aware schedule retains strictly more discriminative information at deep layers on positively-curved (peripheral) nodes than uniform-depth propagation. NTCF can achieve higher performance than most widely used GCF backbone models and can be integrated into existing advanced self-supervised models as a backbone, replacing their original backbone to achieve enhanced performance. Extensive experiments on three public datasets demonstrate the superiority of NTCF.

cs.IR↗

StereoGS: Sparse-View 3D Gaussian Splatting via Stereo Priors

3D Gaussian Splatting (3DGS) has achieved remarkable success in real-time novel view synthesis, yet it suffers from severe overfitting under sparse-view settings due to insufficient geometric constraints. While recent methods introduce monocular depth priors to mitigate this, they inherently struggle with scale ambiguity and cross-view inconsistency, leading to defective geometry. In this paper, we propose StereoGS, a novel sparse-view 3DGS framework that integrates stereo priors to establish reliable binocular consistency. Unlike scale-agnostic monocular constraints, StereoGS introduces a Stereo Depth Regularization by constructing virtual stereo pairs during optimization and leveraging a foundation stereo model to enforce absolute scale and binocular-consistent structures. To further suppress overfitting and eliminate redundant primitives, we design a Gradient-Aware Opacity Decay strategy that dynamically penalizes Gaussians based on their relative opacity gradient magnitudes. Combined with a Consistency-Aware Dense Initialization using zero-shot multi-view depth estimation, StereoGS effectively anchors primitives to accurate scene surfaces. Extensive experiments on LLFF, DTU, Mip-NeRF360, and Blender datasets demonstrate that StereoGS achieves state-of-the-art performance in sparse-view settings without incurring any additional inference overhead. Project Page: https://stringerywh00.github.io/StereoGS_project_page/

cs.CV↗

Fisher-Routed Mixture of Experts for Federated Class-Incremental Learning

Federated Learning (FL) emerged as a promising distributed machine learning paradigm. However, extending FL to the class incremental learning scenarios introduces unique challenges: 1) Capacity conflict and catastrophic forgetting from the shared model overloading, 2) Heterogeneity from Non-Independent and Identically Distributed (Non-IID) data, and 3) Synchronized class misalignment. In this paper, we propose \textbf{F}isher-Routed \textbf{M}i\textbf{X}ture of Experts for \textbf{Fed}erated Class-Incremental Learning (\textsc{FedFMX}), a novel framework to address these challenges via adaptive expert specialization across clients. The crucial insight is to route each sample to an expert subset that jointly optimizes knowledge acquisition and retention. Specifically, we introduce a Fisher-Routed Expert Scoring (FRES) module to estimate expert importance via Fisher-based stability cost and gradient-based plasticity gain. Then, we design an Adaptive Expert Selection (AES) module by quantifying marginal contributions for adaptive expert subset determination. Finally, by the routing-aware regularization (RAR), we achieve load balance and efficient FL training. We theoretically prove the $\mathcal{O}(T^{-1})$ convergence rate. Extensive experiments on multiple benchmarks compared with state-of-the-art methods demonstrate the superiority of \textsc{FedFMX}.

cs.LG↗

Belief-Guided Inference Control for Large Language Model Services via Verifiable Observations

In black-box large language model (LLM) services, response reliability is often only partially observable at decision time, while stronger inference pathways incur substantial computational cost, inducing a budgeted sequential decision problem: for each request, the system should decide whether the default low-cost response is sufficiently reliable or whether additional computation should be allocated to improve response quality. In this paper, we propose \textbf{Ver}ifiable \textbf{O}bservations for Risk-aware \textbf{I}nference \textbf{C}ontrol (\textsc{Veroic}), a framework for adaptive inference control in black-box LLM settings, which formulates request-time control as a \textit{partially observable Markov decision process} to capture partial observability and sequential budget coupling. It constructs a lightweight verifiable observation channel from the input-output pair by aggregating heterogeneous quality signals into a belief state over latent response reliability, which is then used by a budget-aware policy to decide whether to return the default output or trigger a higher-cost inference pathway. Experiments on diverse tasks show that \textsc{Veroic} achieves improved quality-cost trade-offs, stronger risk estimation and calibration, and more robust long-horizon inference control than competitive baselines.

cs.AI↗

DBGL: Decay-aware Bipartite Graph Learning for Irregular Medical Time Series Classification

Irregular Medical Time Series play a critical role in the clinical domain to better understand the patient's condition. However, inherent irregularity arising from heterogeneous sampling rates, asynchronous observations, and variable gaps poses key challenges for reliable modeling. Existing methods often distort temporal sampling irregularity and missingness patterns while failing to capture variable decay irregularity, resulting in suboptimal representations. To address these limitations, we introduce DBGL, Decay-Aware Bipartite Graph Learning for Irregular Medical Time Series. DBGL first introduces a patient-variable bipartite graph that simultaneously captures irregular sampling patterns without artificial alignment and adaptively models variable relationships for temporal sampling irregularity modeling, enhancing representation learning. To model variable decay irregularity, DBGL designs a novel node-specific temporal decay encoding mechanism that captures each variable's decay rates based on sampling interval, yielding a more accurate and faithful representation of irregular temporal dynamics. We evaluate the performance of DBGL on four publicly available datasets, and the results show that DBGL outperforms all baselines.

cs.LG↗

Verify Before You Commit: Towards Faithful Reasoning in LLM Agents via Self-Auditing

In large language model (LLM) agents, reasoning trajectories are treated as reliable internal beliefs for guiding actions and updating memory. However, coherent reasoning can still violate logical or evidential constraints, allowing unsupported beliefs repeatedly stored and propagated across decision steps, leading to systematic behavioral drift in long-horizon agentic systems. Most existing strategies rely on the consensus mechanism, conflating agreement with faithfulness. In this paper, inspired by the vulnerability of unfaithful intermediate reasoning trajectories, we propose \textbf{S}elf-\textbf{A}udited \textbf{Ve}rified \textbf{R}easoning (\textsc{SAVeR}), a novel framework that enforces verification over internal belief states within the agent before action commitment, achieving faithful reasoning. Concretely, we structurally generate persona-based diverse candidate beliefs for selection under a faithfulness-relevant structure space. To achieve reasoning faithfulness, we perform adversarial auditing to localize violations and repair through constraint-guided minimal interventions under verifiable acceptance criteria. Extensive experiments on six benchmark datasets demonstrate that our approach consistently improves reasoning faithfulness while preserving competitive end-task performance.

cs.AI↗

Prof. Robot: Differentiable Robot Rendering Without Static and Self-Collisions

Differentiable rendering has gained significant attention in the field of robotics, with differentiable robot rendering emerging as an effective paradigm for learning robotic actions from image-space supervision. However, the lack of physical world perception in this approach may lead to potential collisions during action optimization. In this work, we introduce a novel improvement on previous efforts by incorporating physical awareness of collisions through the learning of a neural robotic collision classifier. This enables the optimization of actions that avoid collisions with static, non-interactable environments as well as the robot itself. To facilitate effective gradient optimization with the classifier, we identify the underlying issue and propose leveraging Eikonal regularization to ensure consistent gradients for optimization. Our solution can be seamlessly integrated into existing differentiable robot rendering frameworks, utilizing gradients for optimization and providing a foundation for future applications of differentiable rendering in robotics with improved reliability of interactions with the physical world. Both qualitative and quantitative experiments demonstrate the necessity and effectiveness of our method compared to previous solutions.

cs.RO↗

A Game-Theoretic Framework for Privacy-Aware Client Sampling in Federated Learning

This paper aims to design a Privacy-aware Client Sampling framework in Federated learning, named FedPCS, to tackle the heterogeneous client sampling issues and improve model performance. First, we obtain a pioneering upper bound for the accuracy loss of the FL model with privacy-aware client sampling probabilities. Based on this, we model the interactions between the central server and participating clients as a two-stage Stackelberg game. In Stage I, the central server designs the optimal time-dependent reward for cost minimization by considering the trade-off between the accuracy loss of the FL model and the rewards allocated. In Stage II, each client determines the correction factor that dynamically adjusts its privacy budget based on the reward allocated to maximize its utility. To surmount the obstacle of approximating other clients' private information, we introduce the mean-field estimator to estimate the average privacy budget. We analytically demonstrate the existence and convergence of the fixed point for the mean-field estimator and derive the Stackelberg Nash Equilibrium to obtain the optimal strategy profile. By rigorously theoretical convergence analysis, we guarantee the robustness of FedPCS. Moreover, considering the conventional sampling strategy in privacy-preserving FL, we prove that the random sampling approach's PoA can be arbitrarily large. To remedy such efficiency loss, we show that the proposed privacy-aware client sampling strategy successfully reduces PoA, which is upper bounded by a reachable constant. To address the challenge of varying privacy requirements throughout different training phases in FL, we extend our model and analysis and derive the adaptive optimal sampling ratio for the central server. Experimental results on different datasets demonstrate the superiority of FedPCS compared with the existing SOTA FL strategies under IID and Non-IID datasets.

cs.GT↗

FedAgg: Adaptive Federated Learning with Aggregated Gradients

Federated Learning (FL) has emerged as a crucial distributed training paradigm, enabling discrete devices to collaboratively train a shared model under the coordination of a central server, while leveraging their locally stored private data. Nonetheless, the non-independent-and-identically-distributed (Non-IID) data generated on heterogeneous clients and the incessant information exchange among participants may significantly impede training efficacy, retard the model convergence rate and increase the risk of privacy leakage. To alleviate the divergence between the local and average model parameters and obtain a fast model convergence rate, we propose an adaptive FEDerated learning algorithm called FedAgg by refining the conventional stochastic gradient descent (SGD) methodology with an AGgregated Gradient term at each local training epoch and adaptively adjusting the learning rate based on a penalty term that quantifies the local model deviation. To tackle the challenge of information exchange among clients during local training and design a decentralized adaptive learning rate for each client, we introduce two mean-field terms to approximate the average local parameters and gradients over time. Through rigorous theoretical analysis, we demonstrate the existence and convergence of the mean-field terms and provide a robust upper bound on the convergence of our proposed algorithm. The extensive experimental results on real-world datasets substantiate the superiority of our framework in comparison with existing state-of-the-art FL strategies for enhancing model performance and accelerating convergence rate under IID and Non-IID datasets.

cs.LG↗

Deep Generative Models-Assisted Automated Labeling for Electron Microscopy Images Segmentation

The rapid advancement of deep learning has facilitated the automated processing of electron microscopy (EM) big data stacks. However, designing a framework that eliminates manual labeling and adapts to domain gaps remains challenging. Current research remains entangled in the dilemma of pursuing complete automation while still requiring simulations or slight manual annotations. Here we demonstrate tandem generative adversarial network (tGAN), a fully label-free and simulation-free pipeline capable of generating EM images for computer vision training. The tGAN can assimilate key features from new data stacks, thus producing a tailored virtual dataset for the training of automated EM analysis tools. Using segmenting nanoparticles for analyzing size distribution of supported catalysts as the demonstration, our findings showcased that the recognition accuracy of tGAN even exceeds the manually-labeling method by 5%. It can also be adaptively deployed to various data domains without further manual manipulation, which is verified by transfer learning from HAADF-STEM to BF-TEM. This generalizability may enable it to extend its application to a broader range of imaging characterizations, liberating microscopists and materials scientists from tedious dataset annotations.

cond-mat.mtrl-sci↗