arXiv subjects

Wei Huang

Publications and source records attributed to Wei Huang.

At least 181 records · Page 10Linked to original sources

arXiv2025

MindOmni: Unleashing Reasoning Generation in Vision Language Models with RGPO

Recent text-to-image systems face limitations in handling multimodal inputs and complex reasoning tasks. We introduce MindOmni, a unified multimodal large language model that addresses these challenges by incorporating reasoning generation through reinforcement learning. MindOmni leverages a three-phase training strategy: i) design of a unified vision language model with a decoder-only diffusion module, ii) supervised fine-tuning with Chain-of-Thought (CoT) instruction data, and iii) our proposed Reasoning Generation Policy Optimization (RGPO) algorithm, utilizing multimodal feedback to effectively guide policy updates. Experimental results demonstrate that MindOmni outperforms existing models, achieving impressive performance on both understanding and generation benchmarks, meanwhile showcasing advanced fine-grained reasoning generation capabilities, especially with mathematical reasoning instruction. All codes will be made public at https://github.com/TencentARC/MindOmni

cs.AI↗

arXiv2025

Quantifying the Optimization and Generalization Advantages of Graph Neural Networks Over Multilayer Perceptrons

Graph neural networks (GNNs) have demonstrated remarkable capabilities in learning from graph-structured data, often outperforming traditional Multilayer Perceptrons (MLPs) in numerous graph-based tasks. Although existing works have demonstrated the benefits of graph convolution through Laplacian smoothing, expressivity or separability, there remains a lack of quantitative analysis comparing GNNs and MLPs from an optimization and generalization perspective. This study aims to address this gap by examining the role of graph convolution through feature learning theory. Using a signal-noise data model, we conduct a comparative analysis of the optimization and generalization between two-layer graph convolutional networks (GCNs) and their MLP counterparts. Our approach tracks the trajectory of signal learning and noise memorization in GNNs, characterizing their post-training generalization. We reveal that GNNs significantly prioritize signal learning, thus enhancing the regime of {low test error} over MLPs by $D^{q-2}$ times, where $D$ denotes a node's expected degree and $q$ is the power of ReLU activation function with $q>2$. This finding highlights a substantial and quantitative discrepancy between GNNs and MLPs in terms of optimization and generalization, a conclusion further supported by our empirical simulations on both synthetic and real-world datasets.

cs.LG↗

arXiv2025

GRU: Mitigating the Trade-off between Unlearning and Retention for LLMs

Large language model (LLM) unlearning has demonstrated its essential role in removing privacy and copyright-related responses, crucial for their legal and safe applications. However, the pursuit of complete unlearning often comes with substantial costs due to its compromises in their general functionality, leading to a notorious trade-off between unlearning and retention. It motivates this paper to explore enhanced unlearning schemes that can mitigate this trade-off. Specifically, we propose Gradient Rectified Unlearning (GRU), an improved framework that regulates the directions of gradient updates during the unlearning procedure such that their side impacts on other, unrelated responses can be minimized. GRU is easy and general to implement, demonstrating practical effectiveness across a variety of well-established unlearning benchmarks.

cs.LG↗

arXiv2025

Neural Jumps for Option Pricing

Recognizing the importance of jump risk in option pricing, we propose a neural jump stochastic differential equation model in this paper, which integrates neural networks as parameter estimators in the conventional jump diffusion model. To overcome the problem that the backpropagation algorithm is not compatible with the jump process, we use the Gumbel-Softmax method to make the jump parameter gradient learnable. We examine the proposed model using both simulated data and S&P 500 index options. The findings demonstrate that the incorporation of neural jump components substantially improves the accuracy of pricing compared to existing benchmark models.

q-fin.GN↗

arXiv2025

Online Learning for Function Placement in Serverless Computing

We study the placement of virtual functions aimed at minimizing the cost. We propose a novel algorithm, using ideas based on multi-armed bandits. We prove that these algorithms learn the optimal placement policy rapidly, and their regret grows at a rate at most $O( N M \sqrt{T\ln T} )$ while respecting the feasibility constraints with high probability, where $T$ is total time slots, $M$ is the number of classes of function and $N$ is the number of computation nodes. We show through numerical experiments that the proposed algorithm both has good practical performance and modest computational complexity. We propose an acceleration technique that allows the algorithm to achieve good performance also in large networks where computational power is limited. Our experiments are fully reproducible, and the code is publicly available.

cs.LG↗

arXiv2025

Projection Pursuit Density Ratio Estimation

Density ratio estimation (DRE) is a paramount task in machine learning, for its broad applications across multiple domains, such as covariate shift adaptation, causal inference, independence tests and beyond. Parametric methods for estimating the density ratio possibly lead to biased results if models are misspecified, while conventional non-parametric methods suffer from the curse of dimensionality when the dimension of data is large. To address these challenges, in this paper, we propose a novel approach for DRE based on the projection pursuit (PP) approximation. The proposed method leverages PP to mitigate the impact of high dimensionality while retaining the model flexibility needed for the accuracy of DRE. We establish the consistency and the convergence rate for the proposed estimator. Experimental results demonstrate that our proposed method outperforms existing alternatives in various applications.

stat.ML↗

arXiv2025

UAVPairs: A Challenging Benchmark for Match Pair Retrieval of Large-scale UAV Images

The primary contribution of this paper is a challenging benchmark dataset, UAVPairs, and a training pipeline designed for match pair retrieval of large-scale UAV images. First, the UAVPairs dataset, comprising 21,622 high-resolution images across 30 diverse scenes, is constructed; the 3D points and tracks generated by SfM-based 3D reconstruction are employed to define the geometric similarity of image pairs, ensuring genuinely matchable image pairs are used for training. Second, to solve the problem of expensive mining cost for global hard negative mining, a batched nontrivial sample mining strategy is proposed, leveraging the geometric similarity and multi-scene structure of the UAVPairs to generate training samples as to accelerate training. Third, recognizing the limitation of pair-based losses, the ranked list loss is designed to improve the discrimination of image retrieval models, which optimizes the global similarity structure constructed from the positive set and negative set. Finally, the effectiveness of the UAVPairs dataset and training pipeline is validated through comprehensive experiments on three distinct large-scale UAV datasets. The experiment results demonstrate that models trained with the UAVPairs dataset and the ranked list loss achieve significantly improved retrieval accuracy compared to models trained on existing datasets or with conventional losses. Furthermore, these improvements translate to enhanced view graph connectivity and higher quality of reconstructed 3D models. The models trained by the proposed approach perform more robustly compared with hand-crafted global features, particularly in challenging repetitively textured scenes and weakly textured scenes. For match pair retrieval of large-scale UAV images, the trained image retrieval models offer an effective solution. The dataset would be made publicly available at https://github.com/json87/UAVPairs.

cs.CV↗

arXiv2025

Deep Reinforcement Learning-Based Resource Allocation for Hybrid Bit and Generative Semantic Communications in Space-Air-Ground Integrated Networks

In this paper, we introduce a novel framework consisting of hybrid bit-level and generative semantic communications for efficient downlink image transmission within space-air-ground integrated networks (SAGINs). The proposed model comprises multiple low Earth orbit (LEO) satellites, unmanned aerial vehicles (UAVs), and ground users. Considering the limitations in signal coverage and receiver antennas that make the direct communication between satellites and ground users unfeasible in many scenarios, thus UAVs serve as relays and forward images from satellites to the ground users. Our hybrid communication framework effectively combines bit-level transmission with several semantic-level image generation modes, optimizing bandwidth usage to meet stringent satellite link budget constraints and ensure communication reliability and low latency under low signal-to-noise ratio (SNR) conditions. To reduce the transmission delay while ensuring reconstruction quality for the ground user, we propose a novel metric to measure delay and reconstruction quality in the proposed system, and employ a deep reinforcement learning (DRL)-based strategy to optimize resource allocation in the proposed network. Simulation results demonstrate the superiority of the proposed framework in terms of communication resource conservation, reduced latency, and maintaining high image quality, significantly outperforming traditional solutions. Therefore, the proposed framework can ensure that real-time image transmission requirements in SAGINs, even under dynamic network conditions and user demand.

cs.IT↗

arXiv2025

SliM-LLM: Salience-Driven Mixed-Precision Quantization for Large Language Models

Post-training quantization (PTQ) is an effective technique for compressing large language models (LLMs). However, while uniform-precision quantization is computationally efficient, it often compromises model performance. To address this, we propose SliM-LLM, a salience-driven mixed-precision quantization framework that allocates bit-widths at the group-wise. Our approach leverages the observation that important weights follow a structured distribution and introduces two key components: \textbf{1)} \textit{Salience-Determined Bit Allocation} adaptively assigns bit-widths to groups within each layer based on their salience; and \textbf{2)} \textit{Salience-Weighted Quantizer Calibration} optimizes quantizer parameters by incorporating element-level salience. With its structured partitioning, SliM-LLM provides a hardware-friendly solution that matches the efficiency of uniform quantization methods while improving accuracy. Experiments show that SliM-LLM achieves superior performance across various LLMs at low bit-widths. For example, a 2-bit quantized LLaMA-7B model reduces memory usage by nearly 6x compared to the floating-point baseline, decreases perplexity by 48\% compared to state-of-the-art gradient-free PTQ methods, and maintains GPU inference speed. Additionally, the extended version, SliM-LLM$^+$, which incorporates gradient-based quantization, further reduces perplexity by 35.1\%. Our code is available at https://github.com/Aaronhuang-778/SliM-LLM

cs.LG↗

arXiv2025

On the Role of Label Noise in the Feature Learning Process

Deep learning with noisy labels presents significant challenges. In this work, we theoretically characterize the role of label noise from a feature learning perspective. Specifically, we consider a signal-noise data distribution, where each sample comprises a label-dependent signal and label-independent noise, and rigorously analyze the training dynamics of a two-layer convolutional neural network under this data setup, along with the presence of label noise. Our analysis identifies two key stages. In Stage I, the model perfectly fits all the clean samples (i.e., samples without label noise) while ignoring the noisy ones (i.e., samples with noisy labels). During this stage, the model learns the signal from the clean samples, which generalizes well on unseen data. In Stage II, as the training loss converges, the gradient in the direction of noise surpasses that of the signal, leading to overfitting on noisy samples. Eventually, the model memorizes the noise present in the noisy samples and degrades its generalization ability. Furthermore, our analysis provides a theoretical basis for two widely used techniques for tackling label noise: early stopping and sample selection. Experiments on both synthetic and real-world setups validate our theory.

stat.ML↗

arXiv2025

Causal Effect of Functional Treatment

We study the causal effect with a functional treatment variable, where practical applications often arise in neuroscience, biomedical sciences, etc. Previous research concerning the effect of a functional variable on an outcome is typically restricted to exploring correlation rather than causality. The generalized propensity score, which is often used to calibrate the selection bias, is not directly applicable to a functional treatment variable due to a lack of definition of probability density function for functional data. We propose three estimators for the average dose-response functional based on the functional linear model, namely, the functional stabilized weight estimator, the outcome regression estimator and the doubly robust estimator, each of which has its own merits. We study their theoretical properties, which are corroborated through extensive numerical experiments. A real data application on electroencephalography data and disease severity demonstrates the practical value of our methods.

stat.ME↗

arXiv2025

An effcient variational quantum Korkin-Zolotarev algorithm for solving shortest vector problems

Noisy intermediate-scale quantum cryptanalysis focuses on the capability of near-term quantum devices to solve the mathematical problems underlying cryptography, and serves as a cornerstone for the design of post-quantum cryptographic algorithms. For the shortest vector problem (SVP), which is one of the computationally hard problems in lattice-based cryptography, existing near-term quantum cryptanalysis algorithms map the problem onto a fully-connected quantum Ising Hamiltonian, and obtain the solution by optimizing for the first excited state. However, as the quantum system scales with the problem size, determining the first excited state becomes intractable due to the exponentially increased complexity for large-scale SVP instances. In this paper, we propose a variational quantum Korkin-Zolotarev (VQKZ) algorithm, which significantly reduces the qubit requirement for solving the SVP. Specifically, by transforming the original SVP into a series of subproblems on projected sublattices, the proposed VQKZ algorithm enables near-term quantum devices to solve SVP instances with lattice dimensions 61.39% larger than those solvable by previous methods. Furthermore, numerical simulations demonstrate that the proposed VQKZ algorithm can significantly outperform existing methods in terms of the length of solution vectors.

quant-ph↗

arXiv2025

Bridge the Domains: Large Language Models Enhanced Cross-domain Sequential Recommendation

Cross-domain Sequential Recommendation (CDSR) aims to extract the preference from the user's historical interactions across various domains. Despite some progress in CDSR, two problems set the barrier for further advancements, i.e., overlap dilemma and transition complexity. The former means existing CDSR methods severely rely on users who own interactions on all domains to learn cross-domain item relationships, compromising the practicability. The latter refers to the difficulties in learning the complex transition patterns from the mixed behavior sequences. With powerful representation and reasoning abilities, Large Language Models (LLMs) are promising to address these two problems by bridging the items and capturing the user's preferences from a semantic view. Therefore, we propose an LLMs Enhanced Cross-domain Sequential Recommendation model (LLM4CDSR). To obtain the semantic item relationships, we first propose an LLM-based unified representation module to represent items. Then, a trainable adapter with contrastive regularization is designed to adapt the CDSR task. Besides, a hierarchical LLMs profiling module is designed to summarize user cross-domain preferences. Finally, these two modules are integrated into the proposed tri-thread framework to derive recommendations. We have conducted extensive experiments on three public cross-domain datasets, validating the effectiveness of LLM4CDSR. We have released the code online.

cs.IR↗

arXiv2025

STNet: Prediction of Underwater Sound Speed Profiles with An Advanced Semi-Transformer Neural Network

Real time acquisition of accurate underwater sound velocity profile (SSP) is crucial for tracking the propagation trajectory of underwater acoustic signals, making it play a key role in ocean communication positioning. SSPs can be directly measured by instruments or inverted leveraging sound field data. Although measurement techniques provide a good accuracy, they are constrained by limited spatial coverage and require substantial time investment. The inversion method based on real-time measurement of acoustic field data improves operational efficiency, but loses the accuracy of SSP estimation and suffers from limited spatial applicability due to its stringent requirements for ocean observation infrastructure. To achieve accurate long-term ocean SSP estimation independent of real-time underwater data measurements, we propose a Semi-Transformer neural network (STNet) specifically designed for simulating sound velocity distribution patterns from the perspective of time series prediction. The proposed network architecture incorporates an optimized self-attention mechanism to effectively capture long-range temporal dependencies within historical sound velocity time-series data, facilitating accurate estimation of current SSPs or prediction of future SSPs. Through architectural optimization of the Transformer framework and integration of a time encoding mechanism, STNet could effectively improve computational efficiency. Comparative experimental results reveal that STNet outperforms state-of-the-art models in predictive accuracy and maintain good computational efficiency, demonstrating its potential for enabling accurate long-term full-depth ocean SSP forecasting.

cs.SD↗

arXiv2025

Molecular Determinants of Orthosteric-allosteric Dual Inhibition of PfHT1 by Computational Assessment

To overcome antimalarial drug resistance, carbohydrate derivatives as selective PfHT1 inhibitor have been suggested in recent experimental work with orthosteric and allosteric dual binding pockets. Inspired by this promising therapeutic strategy, herein, molecular dynamics simulations are performed to investigate the molecular determinants of co-administration on orthosteric and allosteric inhibitors targeting PfHT1. Our binding free energy analysis capture the essential trend of inhibitor binding affinity to protein from published experimental IC50 data in three sets of distinct characteristics. In particular, we rank the contribution of key residues as binding sites which categorized into three groups based on linker length, size of tail group, and sugar moiety of inhibitors. The pivotal roles of these key residues are further validated by mutant analysis where mutated to nonpolar alanine leading to reduced affinities to different degrees. The exception was fructose derivative, which exhibited a significant enhanced affinity to mutation on orthosteric sites due to strong changed binding poses. This study may provide useful information for optimized design of precision medicine to circumvent drug-resistant Plasmodium parasites with high efficacy.

physics.bio-ph↗

arXiv2025

A Multi-task Learning Balanced Attention Convolutional Neural Network Model for Few-shot Underwater Acoustic Target Recognition

Underwater acoustic target recognition (UATR) is of great significance for the protection of marine diversity and national defense security. The development of deep learning provides new opportunities for UATR, but faces challenges brought by the scarcity of reference samples and complex environmental interference. To address these issues, we proposes a multi-task balanced channel attention convolutional neural network (MT-BCA-CNN). The method integrates a channel attention mechanism with a multi-task learning strategy, constructing a shared feature extractor and multi-task classifiers to jointly optimize target classification and feature reconstruction tasks. The channel attention mechanism dynamically enhances discriminative acoustic features such as harmonic structures while suppressing noise. Experiments on the Watkins Marine Life Dataset demonstrate that MT-BCA-CNN achieves 97\% classification accuracy and 95\% $F1$-score in 27-class few-shot scenarios, significantly outperforming traditional CNN and ACNN models, as well as popular state-of-the-art UATR methods. Ablation studies confirm the synergistic benefits of multi-task learning and attention mechanisms, while a dynamic weighting adjustment strategy effectively balances task contributions. This work provides an efficient solution for few-shot underwater acoustic recognition, advancing research in marine bioacoustics and sonar signal processing.

cs.SD↗

arXiv2025

Scaling Limits of Stochastic Transport Equations on Manifolds

In this work, we generalize some results on scaling limits of stochastic transport equations on the torus, developed recently by Flandoli, Galeati and Luo in Galeati (2020); Flandoli and Luo (2020); Flandoli et al. (2024), to manifolds. We consider the stochastic transport equations driven by colored space-time noise (smooth in space, white in time) on a compact Riemannian manifold without boundary. Then we study the scaling limits of stochastic transport equations, tuning the noise in such a way that the space covariance of the noise on the diagonal goes to the identity matrix but the covariance operator itself goes to zero. This includes the large scale analysis regime with diffusive scaling. We obtain different scaling limits depending on the initial data. With space white noise as initial data, the solutions to the stochastic transport equations converge in distribution to the solution to a stochastic heat equation with additive noise. With square integrable initial data, the solutions to the stochastic transport equations converge to the solution to the deterministic heat equation, and we provide quantitative estimates on the convergence rate.

math.PR↗

arXiv2025

DiffusionCom: Structure-Aware Multimodal Diffusion Model for Multimodal Knowledge Graph Completion

Most current MKGC approaches are predominantly based on discriminative models that maximize conditional likelihood. These approaches struggle to efficiently capture the complex connections in real-world knowledge graphs, thereby limiting their overall performance. To address this issue, we propose a structure-aware multimodal Diffusion model for multimodal knowledge graph Completion (DiffusionCom). DiffusionCom innovatively approaches the problem from the perspective of generative models, modeling the association between the $(head, relation)$ pair and candidate tail entities as their joint probability distribution $p((head, relation), (tail))$, and framing the MKGC task as a process of gradually generating the joint probability distribution from noise. Furthermore, to fully leverage the structural information in MKGs, we propose Structure-MKGformer, an adaptive and structure-aware multimodal knowledge representation learning method, as the encoder for DiffusionCom. Structure-MKGformer captures rich structural information through a multimodal graph attention network (MGAT) and adaptively fuses it with entity representations, thereby enhancing the structural awareness of these representations. This design effectively addresses the limitations of existing MKGC methods, particularly those based on multimodal pre-trained models, in utilizing structural information. DiffusionCom is trained using both generative and discriminative losses for the generator, while the feature extractor is optimized exclusively with discriminative loss. This dual approach allows DiffusionCom to harness the strengths of both generative and discriminative models. Extensive experiments on the FB15k-237-IMG and WN18-IMG datasets demonstrate that DiffusionCom outperforms state-of-the-art models.

cs.IR↗