arXiv subjects

Xue Wang

Publications and source records attributed to Xue Wang.

At least 55 records · Page 3Linked to original sources

arXiv2025

RePO: Understanding Preference Learning Through ReLU-Based Optimization

Aligning large language models (LLMs) with human preferences is critical for real-world deployment, yet existing methods like RLHF face computational and stability challenges. While DPO establishes an offline paradigm with single hyperparameter $β$, subsequent methods like SimPO reintroduce complexity through dual parameters ($β$, $γ$). We propose {ReLU-based Preference Optimization (RePO)}, a streamlined algorithm that eliminates $β$ via two advances: (1) retaining SimPO's reference-free margins but removing $β$ through gradient analysis, and (2) adopting a ReLU-based max-margin loss that naturally filters trivial pairs. Theoretically, RePO is characterized as SimPO's limiting case ($β\to \infty$), where the logistic weighting collapses to binary thresholding, forming a convex envelope of the 0-1 loss. Empirical results on AlpacaEval 2 and Arena-Hard show that RePO outperforms DPO and SimPO across multiple base models, requiring only one hyperparameter to tune.

cs.LG↗

arXiv2025

Dual-Arm Hierarchical Planning for Laboratory Automation: Vibratory Sieve Shaker Operations

This paper addresses the challenges of automating vibratory sieve shaker operations in a materials laboratory, focusing on three critical tasks: 1) dual-arm lid manipulation in 3 cm clearance spaces, 2) bimanual handover in overlapping workspaces, and 3) obstructed powder sample container delivery with orientation constraints. These tasks present significant challenges, including inefficient sampling in narrow passages, the need for smooth trajectories to prevent spillage, and suboptimal paths generated by conventional methods. To overcome these challenges, we propose a hierarchical planning framework combining Prior-Guided Path Planning and Multi-Step Trajectory Optimization. The former uses a finite Gaussian mixture model to improve sampling efficiency in narrow passages, while the latter refines paths by shortening, simplifying, imposing joint constraints, and B-spline smoothing. Experimental results demonstrate the framework's effectiveness: planning time is reduced by up to 80.4%, and waypoints are decreased by 89.4%. Furthermore, the system completes the full vibratory sieve shaker operation workflow in a physical experiment, validating its practical applicability for complex laboratory automation.

cs.RO↗

arXiv2025

Extrapolating Exclusive Charmonium Photoproduction to the Forward Regime Using Gaussian Process

Accessing the forward kinematic regime of exclusive vector meson photoproduction is essential for probing the structure of the proton, yet this region is often experimentally inaccessible. We present a novel extrapolation of near-threshold $γp \to J/ψp$ differential cross section data to the forward regime $dσ/dt|_{t=0}$ by applying a non-parametric Gaussian Process (GP) regression. By employing a two-dimensional GP dependent on both the squared momentum transfer $t$ and the center-of-mass energy $W$, we perform a coherent analysis of world data and provide a robust quantification of the extrapolation uncertainties. Furthermore, we apply the GP in the determination of the proton mass radius from the $J/ψ$ photoproduction data. We find that the extracted radius is subject to large systematic uncertainties, highlighting the challenge in precisely constraining this quantity with current experimental precision. This work demonstrates that GP is a powerful and systematic tool for phenomenological studies in hadron physics, particularly for extrapolations into unmeasured kinematic domains.

hep-ph↗

arXiv2025

Adaptive extended Kalman filter and laser link acquisition in the detection of gravitational waves in space

An alternative, new laser link acquisition scheme for the triangular constellation of spacecraft (SCs) in deep space in the detection of gravitational waves is considered. In place of a wide field CCD camera in the initial stage of laser link acquisition adopted in the conventional scheme, an extended Kalman filter based on precision orbit determination is incorporated in the point ahead angle mechanism (PAAM) to steer the laser beam in such a way to narrow the uncertainty cone and at the same time avoids the heating problem generated by the CCD camera.A quadrant photodetector (QPD) based on the Differential Power Sensing (DPS) technique, which offers a higher dynamic range than differential wavefront sensing (DWS), is employed as the readout of the laser beam spot. The conventional two stages (coarse acquisition and fine acquisition) are integrated into a single control loop. The payload structure of the ATP control loop is simplified and numerical simulations, based on a colored measurement noise model that closely mimics the prospective on-orbit conditions, demonstrate that the AEKF significantly reduces the initial uncertainty region by predicting the point ahead angle (PAA) even when the worst case scenario in SC position (navigation) error is considered.

astro-ph.IM↗

arXiv2025

Debiasing Multimodal Large Language Models via Penalization of Language Priors

In the realms of computer vision and natural language processing, Multimodal Large Language Models (MLLMs) have become indispensable tools, proficient in generating textual responses based on visual inputs. Despite their advancements, our investigation reveals a noteworthy bias: the generated content is often driven more by the inherent priors of the underlying Large Language Models (LLMs) than by the input image. Empirical experiments underscore the persistence of this bias, as MLLMs often provide confident answers even in the absence of relevant images or given incongruent visual inputs. To rectify these biases and redirect the model's focus toward visual information, we propose two simple, training-free strategies. First, for tasks such as classification or multi-choice question answering, we introduce a "Post-Hoc Debias" method using an affine calibration step to adjust the output distribution. This approach ensures uniform answer scores when the image is absent, acting as an effective regularization technique to alleviate the influence of LLM priors. For more intricate open-ended generation tasks, we extend this method to "Visual Debias Decoding", which mitigates bias by contrasting token log-probabilities conditioned on a correct image versus a meaningless one. Additionally, our investigation sheds light on the instability of MLLMs across various decoding configurations. Through systematic exploration of different settings, we achieve significant performance improvements--surpassing previously reported results--and raise concerns about the fairness of current evaluation practices. Comprehensive experiments substantiate the effectiveness of our proposed strategies in mitigating biases. These strategies not only prove beneficial in minimizing hallucinations but also contribute to the generation of more helpful and precise illustrations.

cs.CV↗

arXiv2025

Residual Prior-driven Frequency-aware Network for Image Fusion

Image fusion aims to integrate complementary information across modalities to generate high-quality fused images, thereby enhancing the performance of high-level vision tasks. While global spatial modeling mechanisms show promising results, constructing long-range feature dependencies in the spatial domain incurs substantial computational costs. Additionally, the absence of ground-truth exacerbates the difficulty of capturing complementary features effectively. To tackle these challenges, we propose a Residual Prior-driven Frequency-aware Network, termed as RPFNet. Specifically, RPFNet employs a dual-branch feature extraction framework: the Residual Prior Module (RPM) extracts modality-specific difference information from residual maps, thereby providing complementary priors for fusion; the Frequency Domain Fusion Module (FDFM) achieves efficient global feature modeling and integration through frequency-domain convolution. Additionally, the Cross Promotion Module (CPM) enhances the synergistic perception of local details and global structures through bidirectional feature interaction. During training, we incorporate an auxiliary decoder and saliency structure loss to strengthen the model's sensitivity to modality-specific differences. Furthermore, a combination of adaptive weight-based frequency contrastive loss and SSIM loss effectively constrains the solution space, facilitating the joint capture of local details and global features while ensuring the retention of complementary information. Extensive experiments validate the fusion performance of RPFNet, which effectively integrates discriminative features, enhances texture details and salient objects, and can effectively facilitate the deployment of the high-level vision task.

cs.CV↗

arXiv2025

AlphaDPO: Adaptive Reward Margin for Direct Preference Optimization

Aligning large language models (LLMs) with human values and intentions is crucial for their utility, honesty, and safety. Reinforcement learning from human feedback (RLHF) is a popular approach to achieve this alignment, but it faces challenges in computational efficiency and training stability. Recent methods like Direct Preference Optimization (DPO) and Simple Preference Optimization (SimPO) have proposed offline alternatives to RLHF, simplifying the process by reparameterizing the reward function. However, DPO depends on a potentially suboptimal reference model, and SimPO's assumption of a fixed target reward margin may lead to suboptimal decisions in diverse data settings. In this work, we propose $α$-DPO, an adaptive preference optimization algorithm designed to address these limitations by introducing a dynamic reward margin. Specifically, $α$-DPO employs an adaptive preference distribution, balancing the policy model and the reference model to achieve personalized reward margins. We provide theoretical guarantees for $α$-DPO, demonstrating its effectiveness as a surrogate optimization objective and its ability to balance alignment and diversity through KL divergence control. Empirical evaluations on AlpacaEval 2 and Arena-Hard show that $α$-DPO consistently outperforms DPO and SimPO across various model settings, establishing it as a robust approach for fine-tuning LLMs. Our method achieves significant improvements in win rates, highlighting its potential as a powerful tool for LLM alignment. The code is available at https://github.com/junkangwu/alpha-DPO

cs.LG↗

arXiv2025

Output Scaling: YingLong-Delayed Chain of Thought in a Large Pretrained Time Series Forecasting Model

We present a joint forecasting framework for time series prediction that contrasts with traditional direct or recursive methods. This framework achieves state-of-the-art performance for our designed foundation model, YingLong, and reveals a novel scaling effect: longer outputs significantly enhance model accuracy due to delayed chain-of-thought reasoning in our non-causal approach. YingLong is a non-causal, bidirectional attention encoder-only transformer trained through masked token recovery, aligning more effectively with language understanding tasks than with generation tasks. Additionally, we boost performance by tackling output variance with a multi-input ensemble. We release four foundation models ranging from 6M to 300M parameters, demonstrating superior results in zero-shot tasks on the ETT and Weather datasets. YingLong achieves more than 60% best performance. To ensure generalizability, we assessed the models using the GIFT-Eval benchmark, which comprises 23 time series datasets across 7 domains. Yinglong significantly outperformed the best time-series foundation models, end-to-end trained models by 14% and 44% in rank respectively.The pretrained 300M model is available at https://huggingface.co/qcw1314/YingLong_300m

cs.LG↗

arXiv2025

Ergodicity for the fractional Magneto-Hydrodynamic equations driven by a degenerate pure jump noise

This paper is concerned with the ergodicity for stochastic 2D fractional magneto-hydrodynamic equations on the two-dimensional torus driven by a highly degenerate pure jump Lévy noise. We focus on the challenging case where the noise acts in as few as four directions, establishing new results for such high degeneracy. We first employ Malliavin calculus and anticipative stochastic calculus to demonstrate the equi-continuity of the semigroup (or so-called the e-property), and then verify the weak irreducibility of the solution process. Therefore, the uniqueness of invariant measure is proven.

math.PR↗

arXiv2025

Dynamics of discrete random Burgers-Huxley systems: attractor convergence and finite-dimensional approximations

In this paper, we apply the implicit Euler scheme to discretize the (random) Burgers-Huxley equation and prove the existence of a numerical attractor for the discrete Burgers-Huxley system. We establish upper semi-convergence of the numerical attractor to the global attractor as the step size tends to zero. We also provide finite-dimensional approximations for the three attractors (global, numerical and random) and prove the existence of truncated attractors as the state space dimension goes to infinity. Finally, we prove the existence of a random attractor and establish that the truncated random attractor upper semi-converges to the truncated global attractor as the noise intensity tends to zero.

math.AP↗

arXiv2025

Larger or Smaller Reward Margins to Select Preferences for Alignment?

Preference learning is critical for aligning large language models (LLMs) with human values, with the quality of preference datasets playing a crucial role in this process. While existing metrics primarily assess data quality based on either explicit or implicit reward margins, they often provide contradictory evaluations for the same data. To address this issue, we introduce the alignment potential metric, which quantifies the gap from the model's current implicit reward margin to the target explicit reward margin, thereby estimating the model's potential to align with the preference data. Empirical results demonstrate that training on data selected by this metric consistently enhances alignment performance, surpassing existing metrics across different base models and optimization objectives. Furthermore, our method extends to self-play data generation frameworks, where the metric is used to identify high-quality data within the self-generated content by LLMs. Under this data generation scenario, our method surpasses current state-of-the-art (SOTA) results across various training settings and demonstrates continuous improvements in alignment performance as dataset size and training iterations increase.

cs.LG↗

arXiv2025

MM-RLHF: The Next Step Forward in Multimodal LLM Alignment

Despite notable advancements in Multimodal Large Language Models (MLLMs), most state-of-the-art models have not undergone thorough alignment with human preferences. This gap exists because current alignment research has primarily achieved progress in specific areas (e.g., hallucination reduction), while the broader question of whether aligning models with human preferences can systematically enhance MLLM capability remains largely unexplored. To this end, we introduce MM-RLHF, a dataset containing $\mathbf{120k}$ fine-grained, human-annotated preference comparison pairs. This dataset represents a substantial advancement over existing resources, offering superior size, diversity, annotation granularity, and quality. Leveraging this dataset, we propose several key innovations to improve both the quality of reward models and the efficiency of alignment algorithms. Notably, we introduce a Critique-Based Reward Model, which generates critiques of model outputs before assigning scores, offering enhanced interpretability and more informative feedback compared to traditional scalar reward mechanisms. Additionally, we propose Dynamic Reward Scaling, a method that adjusts the loss weight of each sample according to the reward signal, thereby optimizing the use of high-quality comparison pairs. Our approach is rigorously evaluated across $\mathbf{10}$ distinct dimensions and $\mathbf{27}$ benchmarks, with results demonstrating significant and consistent improvements in model performance. Specifically, fine-tuning LLaVA-ov-7B with MM-RLHF and our alignment algorithm leads to a $\mathbf{19.5}$% increase in conversational abilities and a $\mathbf{60}$% improvement in safety. We have open-sourced the preference dataset, reward model, training and evaluation code, as well as reward modeling and safety benchmarks. For more details, please visit our project page: https://mm-rlhf.github.io.

cs.CL↗

arXiv2024

Self-Calibrated Dual Contrasting for Annotation-Efficient Bacteria Raman Spectroscopy Clustering and Classification

Raman scattering is based on molecular vibration spectroscopy and provides a powerful technology for pathogenic bacteria diagnosis using the unique molecular fingerprint information of a substance. The integration of deep learning technology has significantly improved the efficiency and accuracy of intelligent Raman spectroscopy (RS) recognition. However, the current RS recognition methods based on deep neural networks still require the annotation of a large amount of spectral data, which is labor-intensive. This paper presents a novel annotation-efficient Self-Calibrated Dual Contrasting (SCDC) method for RS recognition that operates effectively with few or no annotation. Our core motivation is to represent the spectrum from two different perspectives in two distinct subspaces: embedding and category. The embedding perspective captures instance-level information, while the category perspective reflects category-level information. Accordingly, we have implemented a dual contrastive learning approach from two perspectives to obtain discriminative representations, which are applicable for Raman spectroscopy recognition under both unsupervised and semi-supervised learning conditions. Furthermore, a self-calibration mechanism is proposed to enhance robustness. Validation of the identification task on three large-scale bacterial Raman spectroscopy datasets demonstrates that our SCDC method achieves robust recognition performance with very few (5$\%$ or 10$\%$) or no annotations, highlighting the potential of the proposed method for biospectral identification in annotation-efficient clinical scenarios.

eess.SP↗

arXiv2024

DiffRaman: A Conditional Latent Denoising Diffusion Probabilistic Model for Bacterial Raman Spectroscopy Identification Under Limited Data Conditions

Raman spectroscopy has attracted significant attention in various biochemical detection fields, especially in the rapid identification of pathogenic bacteria. The integration of this technology with deep learning to facilitate automated bacterial Raman spectroscopy diagnosis has emerged as a key focus in recent research. However, the diagnostic performance of existing deep learning methods largely depends on a sufficient dataset, and in scenarios where there is a limited availability of Raman spectroscopy data, it is inadequate to fully optimize the numerous parameters of deep neural networks. To address these challenges, this paper proposes a data generation method utilizing deep generative models to expand the data volume and enhance the recognition accuracy of bacterial Raman spectra. Specifically, we introduce DiffRaman, a conditional latent denoising diffusion probability model for Raman spectra generation. Experimental results demonstrate that synthetic bacterial Raman spectra generated by DiffRaman can effectively emulate real experimental spectra, thereby enhancing the performance of diagnostic models, especially under conditions of limited data. Furthermore, compared to existing generative models, the proposed DiffRaman offers improvements in both generation quality and computational efficiency. Our DiffRaman approach offers a well-suited solution for automated bacteria Raman spectroscopy diagnosis in data-scarce scenarios, offering new insights into alleviating the labor of spectroscopic measurements and enhancing rare bacteria identification.

cs.CV↗

arXiv2024

Adversarial Contrastive Domain-Generative Learning for Bacteria Raman Spectrum Joint Denoising and Cross-Domain Identification

Raman spectroscopy, as a label-free detection technology, has been widely utilized in the clinical diagnosis of pathogenic bacteria. However, Raman signals are naturally weak and sensitive to the condition of the acquisition process. The characteristic spectra of a bacteria can manifest varying signal-to-noise ratios and domain discrepancies under different acquisition conditions. Consequently, existing methods often face challenges when making identification for unobserved acquisition conditions, i.e., the testing acquisition conditions are unavailable during model training. In this article, a generic framework, namely, an adversarial contrastive domain-generative learning framework, is proposed for joint Raman spectroscopy denoising and cross-domain identification. The proposed method is composed of a domain generation module and a domain task module. Through adversarial learning between these two modules, it utilizes only a single available source domain spectral data to generate extended denoised domains that are semantically consistent with the source domain and extracts domain-invariant representations. Comprehensive case studies indicate that the proposed method can simultaneously conduct spectral denoising without necessitating noise-free ground-truth and can achieve improved diagnostic accuracy and robustness under cross-domain unseen spectral acquisition conditions. This suggests that the proposed method holds remarkable potential as a diagnostic tool in real clinical cases.

eess.IV↗

arXiv2024

UAV Virtual Antenna Array Deployment for Uplink Interference Mitigation in Data Collection Networks

Unmanned aerial vehicles (UAVs) have gained considerable attention as a platform for establishing aerial wireless networks and communications. However, the line-of-sight dominance in air-to-ground communications often leads to significant interference with terrestrial networks, reducing communication efficiency among terrestrial terminals. This paper explores a novel uplink interference mitigation approach based on the collaborative beamforming (CB) method in multi-UAV network systems. Specifically, the UAV swarm forms a UAV-enabled virtual antenna array (VAA) to achieve the transmissions of gathered data to multiple base stations (BSs) for data backup and distributed processing. However, there is a trade-off between the effectiveness of CB-based interference mitigation and the energy conservation of UAVs. Thus, by jointly optimizing the excitation current weights and hover position of UAVs as well as the sequence of data transmission to various BSs, we formulate an uplink interference mitigation multi-objective optimization problem (MOOP) to decrease interference affection, enhance transmission efficiency, and improve energy efficiency, simultaneously. In response to the computational demands of the formulated problem, we introduce an evolutionary computation method, namely chaotic non-dominated sorting genetic algorithm II (CNSGA-II) with multiple improved operators. The proposed CNSGA-II efficiently addresses the formulated MOOP, outperforming several other comparative algorithms, as evidenced by the outcomes of the simulations. Moreover, the proposed CB-based uplink interference mitigation approach can significantly reduce the interference caused by UAVs to non-receiving BSs.

cs.NE↗

arXiv2024

Style3D: Attention-guided Multi-view Style Transfer for 3D Object Generation

We present Style3D, a novel approach for generating stylized 3D objects from a content image and a style image. Unlike most previous methods that require case- or style-specific training, Style3D supports instant 3D object stylization. Our key insight is that 3D object stylization can be decomposed into two interconnected processes: multi-view dual-feature alignment and sparse-view spatial reconstruction. We introduce MultiFusion Attention, an attention-guided technique to achieve multi-view stylization from the content-style pair. Specifically, the query features from the content image preserve geometric consistency across multiple views, while the key and value features from the style image are used to guide the stylistic transfer. This dual-feature alignment ensures that spatial coherence and stylistic fidelity are maintained across multi-view images. Finally, a large 3D reconstruction model is introduced to generate coherent stylized 3D objects. By establishing an interplay between structural and stylistic features across multiple views, our approach enables a holistic 3D stylization process. Extensive experiments demonstrate that Style3D offers a more flexible and scalable solution for generating style-consistent 3D assets, surpassing existing methods in both computational efficiency and visual quality.

cs.CV↗

arXiv2024

Adaptive extended Kalman filter and point ahead angle prediction in the detection of gravitational waves in space

In the detection of gravitational waves in space, during the science phase of the mission, the point ahead angle mechanism (PAAM) serves to steer a laser beam to compensate for the angle generated by the relative motion of the two spacecrafts (SCs) during the approximately 10 seconds of flight time a laser beam will take from one SC to reach a distant SC of three million kilometers away. The common practice for pointing stability control of a laser beam is to first do a coarse tracking by the PAAM to steer a laser beam to compensate for the relative motion between two SCs, to be followed by a fine pointing stability control. In the present work, by exploiting the near-circular orbit structure of individual SC in the triangular constellation, the feasibility of inserting an adaptive Kalman filter (AEKF) into the PAAM control loop is investigated. By adopting a colored measurement noise model that closely resembles the prospective on orbit situation, numerical simulation suggests that the dynamic range of the PAAM may be reduced to the level of nano-radians using the prediction of the pointing head angle (PAA) by the AEKF. This will cut down on the TTL coupling noise and the position noise budget allocated to the PAAM. This in turn reduces the dynamic range of the fine pointing control and leaves room to improve its accuracy, thereby offers the prospect of reduction of the position noise budget allocated to the laser pointing instability as a whole.

astro-ph.IM↗