arXiv subjects

Xiaohu Wu

Publications and source records attributed to Xiaohu Wu.

At least 19 recordsLinked to original sources

arXiv2026

CFPO: Counterfactual Policy Optimization for Multimodal Reasoning

Large Vision-Language Models (LVLMs) have demonstrated remarkable capabilities in multimodal reasoning. However, prevailing reinforcement learning (RL) paradigms lack explicit counterfactual enhancement and causal learning mechanisms. This fundamental deficiency results in severe grounding failures, manifesting as a tendency to ignore visual evidence in favor of language priors or exhibiting hallucination drift during long chain-of-thought reasoning. To address this root cause, we propose CounterFactual Policy Optimization (CFPO), a novel framework that enforces causal consistency between visual perception and textual reasoning. CFPO introduces a cross-modal counterfactual enhancement mechanism, which regularizes the policy by maximizing the discrepancy between the model's predictions and those from a counterfactual state where critical visual cues are suppressed. This approach seamlessly integrates with standard algorithms like GRPO and DAPO without requiring external reward models or additional supervision. Extensive experiments demonstrate that CFPO significantly improves reasoning fidelity, achieving consistent gains of 3.17%-6.25% over standard RL baselines and 1.32%-2.13% over the state-of-the-art perception-aware method (PAPO). Code is available at https://github.com/Raven-July/CFPO.

cs.CV↗

arXiv2026

Multi-site Radar Systems for High-Precision Indoor Positioning and Tracking

This paper introduces a high-precision indoor positioning and tracking method that utilizes multi-site single-input single-output (SISO) radar systems. We propose a novel velocity synthesis-assisted (VSA) localization algorithm that iteratively refines target position estimates within range bins by fusing radial velocity measurements from multiple radars. This approach ensures enhanced accuracy in both velocity and position estimation. Moreover, the inherent geometric constraints introduced by velocity synthesis enable the proposed algorithm to remain robust under low signal-to-noise ratio (SNR), severe multipath propagation, and large synchronization latency. Notably, our method eliminates the use of multiple-input-multiple-output (MIMO) configurations and stringent phase synchronization requirements, substantially reducing hardware complexity while maintaining high positioning accuracy. We define standardized reference trajectories to facilitate a comprehensive and reproducible performance evaluation. Extensive simulations and experimental validations demonstrate that our multi-site radar systems achieve centimeter-level tracking accuracy for human subjects, outperforming existing methods in complex trajectory tracking.

eess.SP↗

arXiv2026

Stabilized Fine-Tuning with LoRA in Federated Learning: Mitigating the Side Effect of Client Size and Rank via the Scaling Factor

Large Language Models (LLMs) are pivotal in natural language processing. The impracticality of full fine-tuning has prompted Parameter-Efficient Fine-Tuning (PEFT) methods like Low-Rank Adaptation (LoRA), optimizing low-rank matrices A and B. In distributed scenarios where privacy constraints necessitate Federated Learning (FL), however, the integration of LoRA is often unstable. Specifically, we identify that aggregating updates from multiple clients introduces statistical variance that scales with the client count, causing gradient collapse when using high-rank adapters. Existing scaling factor candidates, such as the one used by Rank-Stabilized LoRA, ignore the interaction caused by the aggregation process. To bridge this gap, this paper introduces Stabilized Federated LoRA (SFed-LoRA), a framework that theoretically characterizes the interaction between adapter rank and federated aggregation. We derive an optimal scaling factor designed to effectively mitigate the aggregation error accumulating across N clients. By correcting the scaling mismatch inherent in previous approaches, SFed-LoRA restores the efficacy of high-rank adaptation without altering the original model architecture or increasing inference latency. Extensive experiments in diverse tasks, model architectures, and heterogeneous data distributions are conducted to validate our results. We demonstrate that SFed-LoRA prevents high-rank collapse, and achieves significantly improved stability and faster convergence compared with state-of-the-art baselines for high-rank adaptation.

cs.LG↗

arXiv2025

Casimir radiation with Weyl semimetals

When Casimir friction torque acts upon a rotated nanoparticle (NP), mechanical energy can be transformed into thermal energy, known as Casimir radiation, which significantly affects the thermal performance of nanoelectromechanical systems. In this work, we investigate Casimir radiation with nonreciprocal Weyl semimetals (WSM) NP levitated on a plate. WSM NP with inherent nonreciprocity has a radiative heat flux 27 times higher than NP with degenerate modes. The underlying physics is elucidated by the coupling and decoupling of the electromagnetic local density of states between nonreciprocal WSN NP and the plate in the near-field. The three-fold localized plasmon modes of WSM NP split into localized circular modes with strong gyrotropic response, which opens up new channels for Casimir radiation. This work provides a new method for nanoscale energy conversion in NP systems.

physics.optics↗

arXiv2025

iDPA: Instance Decoupled Prompt Attention for Incremental Medical Object Detection

Existing prompt-based approaches have demonstrated impressive performance in continual learning, leveraging pre-trained large-scale models for classification tasks; however, the tight coupling between foreground-background information and the coupled attention between prompts and image-text tokens present significant challenges in incremental medical object detection tasks, due to the conceptual gap between medical and natural domains. To overcome these challenges, we introduce the \method~framework, which comprises two main components: 1) Instance-level Prompt Generation (\ipg), which decouples fine-grained instance-level knowledge from images and generates prompts that focus on dense predictions, and 2) Decoupled Prompt Attention (\dpa), which decouples the original prompt attention, enabling a more direct and efficient transfer of prompt information while reducing memory usage and mitigating catastrophic forgetting. We collect 13 clinical, cross-modal, multi-organ, and multi-category datasets, referred to as \dataset, and experiments demonstrate that \method~outperforms existing SOTA methods, with FAP improvements of 5.44\%, 4.83\%, 12.88\%, and 4.59\% in full data, 1-shot, 10-shot, and 50-shot settings, respectively.

cs.CV↗

arXiv2025

Voronoi-grid-based Pareto Front Learning and Its Application to Collaborative Federated Learning

Multi-objective optimization (MOO) exists extensively in machine learning, and aims to find a set of Pareto-optimal solutions, called the Pareto front, e.g., it is fundamental for multiple avenues of research in federated learning (FL). Pareto-Front Learning (PFL) is a powerful method implemented using Hypernetworks (PHNs) to approximate the Pareto front. This method enables the acquisition of a mapping function from a given preference vector to the solutions on the Pareto front. However, most existing PFL approaches still face two challenges: (a) sampling rays in high-dimensional spaces; (b) failing to cover the entire Pareto Front which has a convex shape. Here, we introduce a novel PFL framework, called as PHN-HVVS, which decomposes the design space into Voronoi grids and deploys a genetic algorithm (GA) for Voronoi grid partitioning within high-dimensional space. We put forward a new loss function, which effectively contributes to more extensive coverage of the resultant Pareto front and maximizes the HV Indicator. Experimental results on multiple MOO machine learning tasks demonstrate that PHN-HVVS outperforms the baselines significantly in generating Pareto front. Also, we illustrate that PHN-HVVS advances the methodologies of several recent problems in the FL field. The code is available at https://github.com/buptcmm/phnhvvs}{https://github.com/buptcmm/phnhvvs.

cs.LG↗

arXiv2025

Personalized Federated Learning via Learning Dynamic Graphs

Personalized Federated Learning (PFL) aims to train a personalized model for each client that is tailored to its local data distribution, learning fails to perform well on individual clients due to variations in their local data distributions. Most existing PFL methods focus on personalizing the aggregated global model for each client, neglecting the fundamental aspect of federated learning: the regulation of how client models are aggregated. Additionally, almost all of them overlook the graph structure formed by clients in federated learning. In this paper, we propose a novel method, Personalized Federated Learning with Graph Attention Network (pFedGAT), which captures the latent graph structure between clients and dynamically determines the importance of other clients for each client, enabling fine-grained control over the aggregation process. We evaluate pFedGAT across multiple data distribution scenarios, comparing it with twelve state of the art methods on three datasets: Fashion MNIST, CIFAR-10, and CIFAR-100, and find that it consistently performs well.

cs.LG↗

arXiv2025

Free-Rider and Conflict Aware Collaboration Formation for Cross-Silo Federated Learning

Federated learning (FL) is a machine learning paradigm that allows multiple FL participants (FL-PTs) to collaborate on training models without sharing private data. Due to data heterogeneity, negative transfer may occur in the FL training process. This necessitates FL-PT selection based on their data complementarity. In cross-silo FL, organizations that engage in business activities are key sources of FL-PTs. The resulting FL ecosystem has two features: (i) self-interest, and (ii) competition among FL-PTs. This requires the desirable FL-PT selection strategy to simultaneously mitigate the problems of free riders and conflicts of interest among competitors. To this end, we propose an optimal FL collaboration formation strategy -- FedEgoists -- which ensures that: (1) a FL-PT can benefit from FL if and only if it benefits the FL ecosystem, and (2) a FL-PT will not contribute to its competitors or their supporters. It provides an efficient clustering solution to group FL-PTs into coalitions, ensuring that within each coalition, FL-PTs share the same interest. We theoretically prove that the FL-PT coalitions formed are optimal since no coalitions can collaborate together to improve the utility of any of their members. Extensive experiments on widely adopted benchmark datasets demonstrate the effectiveness of FedEgoists compared to nine state-of-the-art baseline methods, and its ability to establish efficient collaborative networks in cross-silos FL with FL-PTs that engage in business activities.

cs.GT↗

arXiv2024

Benchmarking Data Heterogeneity Evaluation Approaches for Personalized Federated Learning

There is growing research interest in measuring the statistical heterogeneity of clients' local datasets. Such measurements are used to estimate the suitability for collaborative training of personalized federated learning (PFL) models. Currently, these research endeavors are taking place in silos and there is a lack of a unified benchmark to provide a fair and convenient comparison among various approaches in common settings. We aim to bridge this important gap in this paper. The proposed benchmarking framework currently includes six representative approaches. Extensive experiments have been conducted to compare these approaches under five standard non-IID FL settings, providing much needed insights into which approaches are advantageous under which settings. The proposed framework offers useful guidance on the suitability of various data divergence measures in FL systems. It is beneficial for keeping related research activities on the right track in terms of: (1) designing PFL schemes, (2) selecting appropriate data heterogeneity evaluation approaches for specific FL application scenarios, and (3) addressing fairness issues in collaborative model training. The code is available at https://github.com/Xiaoni-61/DH-Benchmark.

cs.LG↗

arXiv2024

MLAE: Masked LoRA Experts for Visual Parameter-Efficient Fine-Tuning

In response to the challenges posed by the extensive parameter updates required for full fine-tuning of large-scale pre-trained models, parameter-efficient fine-tuning (PEFT) methods, exemplified by Low-Rank Adaptation (LoRA), have emerged. LoRA simplifies the fine-tuning process but may still struggle with a certain level of redundancy in low-rank matrices and limited effectiveness from merely increasing their rank. To address these issues, a natural idea is to enhance the independence and diversity of the learning process for the low-rank matrices. Therefore, we propose Masked LoRA Experts (MLAE), an innovative approach that applies the concept of masking to visual PEFT. Our method incorporates a cellular decomposition strategy that transforms a low-rank matrix into independent rank-1 submatrices, or "experts", thus enhancing independence. Additionally, we introduce a binary mask matrix that selectively activates these experts during training to promote more diverse and anisotropic learning, based on expert-level dropout strategies. Our investigations reveal that this selective activation not only enhances performance but also fosters a more diverse acquisition of knowledge with a marked decrease in parameter similarity among MLAE, significantly boosting the quality of the model. Remarkably, MLAE achieves new state-of-the-art (SOTA) performance with an average accuracy score of 78.8% on the VTAB-1k benchmark and 90.9% on the FGVC benchmark, surpassing the previous SOTA result by an average of 0.8% on both benchmarks with approximately half parameters. Our code is available at https://github.com/jie040109/MLAE.

cs.CV↗

arXiv2024

Near-field radiative heat transfer between graphene-covered Weyl semimetals

Polariton manipulations introduce novel approaches to modulate the near-field radiative heat transfer (NFRHT). Our theoretical investigation in this study centers on NFRHT in graphene-covered Weyl semimetals (WSMs). Our findings indicate variable heat flux enhancement or attenuation, contingent on chemical potential of graphene. Enhancement or attenuation mechanisms stem from the coupling or decoupling of surface plasmon polaritons (SPPs) in the graphene/WSM heterostructure. The graphene-covered WSM photon tunneling probabilities variation is demonstrated in detail. This research enhances our comprehension of SPPs within the graphene/WSM heterostructure and suggests methods for actively controlling NFRHT.

cond-mat.mes-hall↗

arXiv2024

Learning Structurally Stabilized Representations for Multi-modal Lossless DNA Storage

In this paper, we present Reed-Solomon coded single-stranded representation learning (RSRL), a novel end-to-end model for learning representations for multi-modal lossless DNA storage. In contrast to existing learning-based methods, the proposed RSRL is inspired by both error-correction codec and structural biology. Specifically, RSRL first learns the representations for the subsequent storage from the binary data transformed by the Reed-Solomon codec. Then, the representations are masked by an RS-code-informed mask to focus on correcting the burst errors occurring in the learning process. With the decoded representations with error corrections, a novel biologically stabilized loss is formulated to regularize the data representations to possess stable single-stranded structures. By incorporating these novel strategies, the proposed RSRL can learn highly durable, dense, and lossless representations for the subsequent storage tasks into DNA sequences. The proposed RSRL has been compared with a number of strong baselines in real-world tasks of multi-modal data storage. The experimental results obtained demonstrate that RSRL can store diverse types of data with much higher information density and durability but much lower error rates.

cs.LG↗

arXiv2024

High-rectification near-field radiative thermal diode using Weyl semimetals

Thermal diodes, which allow heat transfer in a preferential direction while being blocked in a reverse direction, have numerous applications in thermal management, information processing, energy harvesting, etc. Typical materials of thermal diodes in previous works include phase-change and magneto-optical materials. However, such thermal diodes highly depend on specific working temperatures or external magnetic fields. In this work, we propose a near-field radiative thermal diode (NFRTD) based on two Weyl semimetals (WSMs) nanoparticles (NPs) mediated by WSMs planar substrate, which works without external magnetic field and with flexible temperatures. Numerical results show that the maximum rectification ratio of NFRTD can be up to 2673 when the emitter is 200 K and receiver is 180 K, which exceeds the maximum value reported in previous works by more than 10 times. The underlying physical mechanism is the strong coupling of the localized plasmon modes in the NPs and nonreciprocal surface plasmon polaritons in the substrate. In addition, we calculate the distribution of the Green function and reflection coefficient to investigate nonreciprocal energy transfer in NFRTD. Finally, we discuss the effects of momentum-separation on the rectification performance of the NFRTD. This work demonstrates the great potential of WSMs in thermal rectification and paves a novel path in designing high-performance NFRTD.

physics.optics↗

arXiv2023

FedCompetitors: Harmonious Collaboration in Federated Learning with Competing Participants

Federated learning (FL) provides a privacy-preserving approach for collaborative training of machine learning models. Given the potential data heterogeneity, it is crucial to select appropriate collaborators for each FL participant (FL-PT) based on data complementarity. Recent studies have addressed this challenge. Similarly, it is imperative to consider the inter-individual relationships among FL-PTs where some FL-PTs engage in competition. Although FL literature has acknowledged the significance of this scenario, practical methods for establishing FL ecosystems remain largely unexplored. In this paper, we extend a principle from the balance theory, namely ``the friend of my enemy is my enemy'', to ensure the absence of conflicting interests within an FL ecosystem. The extended principle and the resulting problem are formulated via graph theory and integer linear programming. A polynomial-time algorithm is proposed to determine the collaborators of each FL-PT. The solution guarantees high scalability, allowing even competing FL-PTs to smoothly join the ecosystem without conflict of interest. The proposed framework jointly considers competition and data heterogeneity. Extensive experiments on real-world and synthetic data demonstrate its efficacy compared to five alternative approaches, and its ability to establish efficient collaboration networks among FL-PTs.

cs.AI↗

arXiv2023

Exploring Leximin Principle for Fair Core-Selecting Combinatorial Auctions: Payment Rule Design and Implementation

Core-selecting combinatorial auctions (CAs) restrict the auction result in the core such that no coalitions could improve their utilities by engaging in collusion. The minimum-revenue-core (MRC) rule is a widely used core-selecting payment rule to maximize the total utilities of all bidders. However, the MRC rule can suffer from severe unfairness since it ignores individuals' utilities. To address this limitation, we propose to explore the leximin principle to achieve fairness in core-selecting CAs since the leximin principle prefers to maximize the utility of the worst-off; the resulting bidder-leximin-optimal (BLO) payment rule is then theoretically analyzed and an effective algorithm is further provided to compute the BLO outcome. Moreover, we conduct extensive experiments to show that our algorithm returns fairer utility distributions and is faster than existing algorithms of core-selecting payment rules.

cs.GT↗

arXiv2023

Efficient Algorithms for Scheduling Moldable Tasks

We study the problem of scheduling $n$ independent moldable tasks on $m$ processors that arises in large-scale parallel computations. When tasks are monotonic, the best known result is a $(\frac{3}{2}+ε)$-approximation algorithm for makespan minimization with a complexity linear in $n$ and polynomial in $\log{m}$ and $\frac{1}ε$ where $ε$ is arbitrarily small. We propose a new perspective of the existing speedup models: the speedup of a task $T_{j}$ is linear when the number $p$ of assigned processors is small (up to a threshold $δ_{j}$) while it presents monotonicity when $p$ ranges in $[δ_{j}, k_{j}]$; the bound $k_{j}$ indicates an unacceptable overhead when parallelizing on too many processors. The generality of this model is proved to be between the classic monotonic and linear-speedup models. For any given integer $δ\geq 5$, let $u=\left\lceil \sqrt[2]δ \right\rceil-1\geq 2$. In this paper, we propose a $\frac{1}{θ(δ)} (1+ε)$-approximation algorithm for makespan minimization where $θ(δ) = \frac{u+1}{u+2}\left( 1- \frac{k}{m} \right)$ ($m\gg k$). As a by-product, we also propose a $θ(δ)$-approximation algorithm for throughput maximization with a common deadline.

cs.DS↗

arXiv2022

Actively tuning anisotropic light-matter interaction in biaxial hyperbolic material $α$-MoO$_3$ using phase change material VO$_2$ and graphene

Anisotropic hyperbolic phonon polaritons (PhPs) in natural biaxial hyperbolic material MoO$_3$ has opened up new avenues for mid-infrared nanophotonics, while active tunability of $α$-MoO$_3$ PhPs is still an urgent problem needing to be solved.In this study, we present a theoretical demonstration of actively tuning $α$-MoO$_3$ PhPs using phase change material VO$_2$ and graphene. It is observed that $α$-MoO$_3$ PhPs are greatly depending on the propagation plane angle of PhPs. The metal-to-insulator phase transition of VO$_2$ has a significant effect on the hybridization PhPs of the $α$-MoO$_3$/VO$_2$ structure and allows to obtain an actively tunable $α$-MoO$_3$ PhPs, which is especially obvious when the propagation plane angle of PhPs is 90.

physics.app-ph↗

arXiv2022

Negative differential thermal conductance between Weyl semimetals nanoparticles through vacuum

In this work, the near-field radiative heat transfer (NFRHT) between two Weyl semimetal (WSM) nanoparticles (NPs) is investigated. The numerical results show that negative differential thermal conductance (NDTC) effect can be obtained in this system, i.e., when the temperature of the emitter is fixed, the heat flux does not decrease monotonically with the increase of the temperature of the receiver. Specifically, when the temperature of the emitter is 300 K, the heat flux is identical when the temperature of the receiver is 50 K or 280 K. The NDTC effect is attributed to the fact that the permittivity of the WSMs changes with the temperature. The coupling effects of polarizability of two WSM NPs have been further identified at different temperature to reveal the physical mechanism of the NDTC effect. In addition, the NFRHT between two Weyl WSM NPs can be greatly enhanced by exciting the localized plasmon and circular modes. This work indicates that the WSMs maybe promising candidate materials for manipulating NFRHT.

cond-mat.mes-hall↗