arXiv subjects

Qi Wang

Publications and source records attributed to Qi Wang.

At least 289 records · Page 16Linked to original sources

arXiv2025

Multi-perspective Contrastive Logit Distillation

In previous studies on knowledge distillation, the significance of logit distillation has frequently been overlooked. To revitalize logit distillation, we present a novel perspective by reconsidering its computation based on the semantic properties of logits and exploring how to utilize it more efficiently. Logits often contain a substantial amount of high-level semantic information; however, the conventional approach of employing logits to compute Kullback-Leibler (KL) divergence does not account for their semantic properties. Furthermore, this direct KL divergence computation fails to fully exploit the potential of logits. To address these challenges, we introduce a novel and efficient logit distillation method, Multi-perspective Contrastive Logit Distillation (MCLD), which substantially improves the performance and efficacy of logit distillation. In comparison to existing logit distillation methods and complex feature distillation methods, MCLD attains state-of-the-art performance in image classification, and transfer learning tasks across multiple datasets, including CIFAR-100, ImageNet, Tiny-ImageNet, and STL-10. Additionally, MCLD exhibits superior training efficiency and outstanding performance with distilling on Vision Transformers, further emphasizing its notable advantages. This study unveils the vast potential of logits in knowledge distillation and seeks to offer valuable insights for future research.

cs.CV↗

arXiv2025

A Benchmark for Multi-Lingual Vision-Language Learning in Remote Sensing Image Captioning

Remote Sensing Image Captioning (RSIC) is a cross-modal field bridging vision and language, aimed at automatically generating natural language descriptions of features and scenes in remote sensing imagery. Despite significant advances in developing sophisticated methods and large-scale datasets for training vision-language models (VLMs), two critical challenges persist: the scarcity of non-English descriptive datasets and the lack of multilingual capability evaluation for models. These limitations fundamentally impede the progress and practical deployment of RSIC, particularly in the era of large VLMs. To address these challenges, this paper presents several significant contributions to the field. First, we introduce and analyze BRSIC (Bilingual Remote Sensing Image Captioning), a comprehensive bilingual dataset that enriches three established English RSIC datasets with Chinese descriptions, encompassing 13,634 images paired with 68,170 bilingual captions. Building upon this foundation, we develop a systematic evaluation framework that addresses the prevalent inconsistency in evaluation protocols, enabling rigorous assessment of model performance through standardized retraining procedures on BRSIC. Furthermore, we present an extensive empirical study of eight state-of-the-art large vision-language models (LVLMs), examining their capabilities across multiple paradigms including zero-shot inference, supervised fine-tuning, and multi-lingual training. This comprehensive evaluation provides crucial insights into the strengths and limitations of current LVLMs in handling multilingual remote sensing tasks. Additionally, our cross-dataset transfer experiments reveal interesting findings. The code and data will be available at https://github.com/mrazhou/BRSIC.

cs.CV↗

arXiv2025

Red Emission from Strain-Relaxed Bulk InGaN Active Region

High-In-content InGaN quantum wells (QWs) in red light-emitting diodes (LEDs) are typically grown at low temperatures to ensure effective In incorporation. In this study, red LEDs based on bulk InGaN active region were demonstrated. The growth temperature of bulk InGaN was ~800C, which is over 100C higher than the typical growth temperature of red QWs. By introducing high-density trench structures in the underlying green multi-quantum wells (MQWs), the compressive strain in bulk InGaN was relaxed by ~96%. With strain relaxation, phase separation occurred in the bulk InGaN, forming low-In-content (blue) and high-In-content (red) phases. The red phase acted as carrier localization centers, enabling red light emission under electrical injection. The red LEDs based on bulk InGaN exhibited a peak wavelength of 645 nm at 20 mA, with on-wafer peak external quantum efficiency of 0.32%. This study presents a new epitaxial strategy for red InGaN LEDs.

cond-mat.mtrl-sci↗

arXiv2025

PhyMPGN: Physics-encoded Message Passing Graph Network for spatiotemporal PDE systems

Solving partial differential equations (PDEs) serves as a cornerstone for modeling complex dynamical systems. Recent progresses have demonstrated grand benefits of data-driven neural-based models for predicting spatiotemporal dynamics (e.g., tremendous speedup gain compared with classical numerical methods). However, most existing neural models rely on rich training data, have limited extrapolation and generalization abilities, and suffer to produce precise or reliable physical prediction under intricate conditions (e.g., irregular mesh or geometry, complex boundary conditions, diverse PDE parameters, etc.). To this end, we propose a new graph learning approach, namely, Physics-encoded Message Passing Graph Network (PhyMPGN), to model spatiotemporal PDE systems on irregular meshes given small training datasets. Specifically, we incorporate a GNN into a numerical integrator to approximate the temporal marching of spatiotemporal dynamics for a given PDE system. Considering that many physical phenomena are governed by diffusion processes, we further design a learnable Laplace block, which encodes the discrete Laplace-Beltrami operator, to aid and guide the GNN learning in a physically feasible solution space. A boundary condition padding strategy is also designed to improve the model convergence and accuracy. Extensive experiments demonstrate that PhyMPGN is capable of accurately predicting various types of spatiotemporal dynamics on coarse unstructured meshes, consistently achieves the state-of-the-art results, and outperforms other baselines with considerable gains.

cs.LG↗

arXiv2025

DCI: A Coordinated Allocation and Filling Workload-Aware Dual-Cache Allocation GNN Inference Acceleration System

Graph Neural Networks (GNNs) are powerful tools for processing graph-structured data, increasingly used for large-scale real-world graphs via sampling-based inference methods. However, inherent characteristics of neighbor sampling lead to redundant data loading during GNN inference, compounded by inefficient data transfers between host and GPU memory, resulting in slow inference and low resource utilization. Existing methods to accelerate GNN inference face several challenges: (1) low practical GPU memory utilization, (2) overlooking adjacency matrix locality, and (3) long preprocessing time. To address these challenges, we introduce DCI, an efficient workload-aware dual-cache allocation system for GNN inference acceleration. DCI allocates cache capacities for both node features and adjacency matrices based on workload patterns during the pre-sampling phase, leveraging a lightweight cache-filling algorithm to optimize data loading efficiency. Experimental results demonstrate that DCI accelerates sampling and node feature loading, achieving end-to-end inference speedups of 1.18$\times$ to 11.26$\times$ compared to DGL, and 1.14$\times$ to 13.68$\times$ over RAIN, while reducing preprocessing time by 52.8\% to 98.7\%. Additionally, DCI outperforms state-of-the-art single-cache inference systems by achieving speedup of 1.08$\times$ to 1.32$\times$. We also compared DCI with DUCATI's dual-cache population strategy. Our lightweight population algorithm allows DCI to achieve nearly the same inference speed while keeping preprocessing time to less than 20\% of that required by DUCATI.

cs.AR↗

arXiv2025

Charge Dynamics of an Unconventional Three-Dimensional Charge Density Wave in Kagome FeGe

We report on the charge dynamics of kagome FeGe, an antiferromagnet with a charge density wave (CDW) transition at $T_{\mathrm{CDW}} \simeq 105$ K, using polarized infrared spectroscopy and band structure calculations. We reveal pronounced optical anisotropy along the $a$- and $c$-axis, as well as an unusual response associated with three-dimensional CDW order. Above $T_{\mathrm{CDW}}$, there is a notable transfer of spectral weight (SW) from high to low energies, promoted by the magnetic splitting-induced shift in bands. Across the CDW transition, we observe a sudden SW transfer from low to high energies over a broad range, along with the emergence of new excitations around 1200 cm$^{-1}$. These results contrast with observations from other kagome metals like CsV$_3$Sb$_5$, where the nesting of VHSs leads to a clear CDW gap feature. Instead, our findings can be accounted for by a $2\times2\times2$ CDW ground state driven by a first-order structural transition involving large partial Ge1-dimerization. Our study thus unveils a complex interplay among structure, magnetism, and charge order, offering valuable insights for a comprehensive understanding of CDW order in FeGe.

cond-mat.str-el↗

arXiv2025

Inverse Rendering using Multi-Bounce Path Tracing and Reservoir Sampling

We present MIRReS, a novel two-stage inverse rendering framework that jointly reconstructs and optimizes the explicit geometry, material, and lighting from multi-view images. Unlike previous methods that rely on implicit irradiance fields or simplified path tracing algorithms, our method extracts an explicit geometry (triangular mesh) in stage one, and introduces a more realistic physically-based inverse rendering model that utilizes multi-bounce path tracing and Monte Carlo integration. By leveraging multi-bounce path tracing, our method effectively estimates indirect illumination, including self-shadowing and internal reflections, which improves the intrinsic decomposition of shape, material, and lighting. Moreover, we incorporate reservoir sampling into our framework to address the noise in Monte Carlo integration, enhancing convergence and facilitating gradient-based optimization with low sample counts. Through qualitative and quantitative evaluation of several scenarios, especially in challenging scenarios with complex shadows, we demonstrate that our method achieves state-of-the-art performance on decomposition results. Additionally, our optimized explicit geometry enables applications such as scene editing, relighting, and material editing with modern graphics engines or CAD software. The source code is available at https://brabbitdousha.github.io/MIRReS/

cs.CV↗

arXiv2025

A Large Language Model Guided Topic Refinement Mechanism for Short Text Modeling

Modeling topics effectively in short texts, such as tweets and news snippets, is crucial to capturing rapidly evolving social trends. Existing topic models often struggle to accurately capture the underlying semantic patterns of short texts, primarily due to the sparse nature of such data. This nature of texts leads to an unavoidable lack of co-occurrence information, which hinders the coherence and granularity of mined topics. This paper introduces a novel model-agnostic mechanism, termed Topic Refinement, which leverages the advanced text comprehension capabilities of Large Language Models (LLMs) for short-text topic modeling. Unlike traditional methods, this post-processing mechanism enhances the quality of topics extracted by various topic modeling methods through prompt engineering. We guide LLMs in identifying semantically intruder words within the extracted topics and suggesting coherent alternatives to replace these words. This process mimics human-like identification, evaluation, and refinement of the extracted topics. Extensive experiments on four diverse datasets demonstrate that Topic Refinement boosts the topic quality and improves the performance in topic-related text classification tasks.

cs.CL↗

arXiv2025

GenComUI: Exploring Generative Visual Aids as Medium to Support Task-Oriented Human-Robot Communication

This work investigates the integration of generative visual aids in human-robot task communication. We developed GenComUI, a system powered by large language models that dynamically generates contextual visual aids (such as map annotations, path indicators, and animations) to support verbal task communication and facilitate the generation of customized task programs for the robot. This system was informed by a formative study that examined how humans use external visual tools to assist verbal communication in spatial tasks. To evaluate its effectiveness, we conducted a user experiment (n = 20) comparing GenComUI with a voice-only baseline. The results demonstrate that generative visual aids, through both qualitative and quantitative analysis, enhance verbal task communication by providing continuous visual feedback, thus promoting natural and effective human-robot communication. Additionally, the study offers a set of design implications, emphasizing how dynamically generated visual aids can serve as an effective communication medium in human-robot interaction. These findings underscore the potential of generative visual aids to inform the design of more intuitive and effective human-robot communication, particularly for complex communication scenarios in human-robot interaction and LLM-based end-user development.

cs.HC↗

arXiv2025

Group & Reweight: A Novel Cost-Sensitive Approach to Mitigating Class Imbalance in Network Traffic Classification

Internet services have led to the eruption of network traffic, and machine learning on these Internet data has become an indispensable tool, especially when the application is risk-sensitive. This paper focuses on network traffic classification in the presence of severe class imbalance. Such a distributional trait mostly drifts the optimal decision boundary and results in an unsatisfactory solution. This raises safety concerns in the network traffic field when previous class imbalance methods hardly deal with numerous minority malicious classes. To alleviate these effects, we design a group & reweight strategy for alleviating class imbalance. Inspired by the group distributionally optimization framework, our approach heuristically clusters classes into groups, iteratively updates the non-parametric weights for separate classes, and optimizes the learning model by minimizing reweighted losses. We theoretically interpret the optimization process from a Stackelberg game and perform extensive experiments on typical benchmarks. Results show that our approach can not only suppress the negative effect of class imbalance but also improve the comprehensive performance in prediction.

stat.ML↗

arXiv2025

Prompt-Driven Continual Graph Learning

Continual Graph Learning (CGL), which aims to accommodate new tasks over evolving graph data without forgetting prior knowledge, is garnering significant research interest. Mainstream solutions adopt the memory replay-based idea, ie, caching representative data from earlier tasks for retraining the graph model. However, this strategy struggles with scalability issues for constantly evolving graphs and raises concerns regarding data privacy. Inspired by recent advancements in the prompt-based learning paradigm, this paper introduces a novel prompt-driven continual graph learning (PROMPTCGL) framework, which learns a separate prompt for each incoming task and maintains the underlying graph neural network model fixed. In this way, PROMPTCGL naturally avoids catastrophic forgetting of knowledge from previous tasks. More specifically, we propose hierarchical prompting to instruct the model from both feature- and topology-level to fully address the variability of task graphs in dynamic continual learning. Additionally, we develop a personalized prompt generator to generate tailored prompts for each graph node while minimizing the number of prompts needed, leading to constant memory consumption regardless of the graph scale. Extensive experiments on four benchmarks show that PROMPTCGL achieves superior performance against existing CGL approaches while significantly reducing memory consumption. Our code is available at https://github.com/QiWang98/PromptCGL.

cs.LG↗

arXiv2025

Positive temperature-dependent thermal conductivity induced by wavelike phonons in complex Ag-based argyrodites

The phonon transport mechanisms and the anomalous temperature-dependent lattice thermal conductivities (kL) in Ag-based argyrodites have not been fully understood. Herein, we systematically study the phonon thermal transport of five Ag-based crystalline argyrodites Ag7PS6, Ag7AsS6, Ag8SnS6, Ag8GeS6 and Ag9GaS6 utilizing perturbation theory and the unified theory thermal transport model. Our results show that, as the complexity of the unit cell increases, the proportion of the population terms falls while the coherence contributions become more significant, leading to the relatively weak temperature-dependent kL of Ag7PS6 and Ag7AsS6, while the more complex crystalline argyrodites, Ag8SnS6, Ag8GeS6 and Ag9GaS6, exhibiting a glass-like behavior in their temperature dependence of kL. We attribute the positive temperature-dependent and ultralow kL of Ag8SnS6, Ag8GeS6 and Ag9GaS6 to the dominance of wavelike phonons and the strong phonon broadening. Furthermore, using laser flash measurements and the homogeneous non-equilibrium molecular dynamics simulations based on accurate machine learning neuroevolution potentials, we provide further evidence for the glass-like temperature-dependent kL of Ag8SnS6 and Ag8GeS6.

cond-mat.mtrl-sci↗

arXiv2025

High-pressure modulation of breathing kagome lattice: Cascade of Lifshitz transitions and evolution of the electronic structure

The interplay between electronic correlations, density wave orders, and magnetism gives rise to several fascinating phenomena. In recent years, kagome metals have emerged as an excellent platform for investigating these unique properties, which stem from their itinerant carriers arranged in a kagome lattice. Here, we show that electronic structure of the prototypical kagome metal, Fe$_3$Sn$_2$, can be tailored by manipulating the breathing distortion of its kagome lattice with external pressure. The breathing distortion is suppressed around 15 GPa and reversed at higher pressures. These changes lead to a series of Lifshitz transitions that we detect using broadband and transient optical spectroscopy. Remarkably, the strength of the electronic correlations and the tendency to carrier localization are enhanced as the kagome network becomes more regular, suggesting that breathing distortion can be a unique control parameter for the microscopic regime of the kagome metals and their electron dynamics.

cond-mat.str-el↗

arXiv2025

Cogito, ergo sum: A Neurobiologically-Inspired Cognition-Memory-Growth System for Code Generation

Large language models based Multi Agent Systems (MAS) have demonstrated promising performance for enhancing the efficiency and accuracy of code generation tasks. However,most existing methods follow a conventional sequence of planning, coding, and debugging,which contradicts the growth-driven nature of human learning process. Additionally,the frequent information interaction between multiple agents inevitably involves high computational costs. In this paper,we propose Cogito,a neurobiologically inspired multi-agent framework to enhance the problem-solving capabilities in code generation tasks with lower cost. Specifically,Cogito adopts a reverse sequence: it first undergoes debugging, then coding,and finally planning. This approach mimics human learning and development,where knowledge is acquired progressively. Accordingly,a hippocampus-like memory module with different functions is designed to work with the pipeline to provide quick retrieval in similar tasks. Through this growth-based learning model,Cogito accumulates knowledge and cognitive skills at each stage,ultimately forming a Super Role an all capable agent to perform the code generation task. Extensive experiments against representative baselines demonstrate the superior performance and efficiency of Cogito. The code is publicly available at https://anonymous.4open.science/r/Cogito-0083.

cs.SE↗

arXiv2025

Walk in Their Shoes to Navigate Your Own Path: Learning About Procrastination Through A Serious Game

Procrastination, the voluntary delay of tasks despite potential negative consequences, has prompted numerous time and task management interventions in the HCI community. While these interventions have shown promise in addressing specific behaviors, psychological theories suggest that learning about procrastination itself may help individuals develop their own coping strategies and build mental resilience. However, little research has explored how to support this learning process through HCI approaches. We present ProcrastiMate, a text adventure game where players learn about procrastination's causes and experiment with coping strategies by guiding in-game characters in managing relatable scenarios. Our field study with 27 participants revealed that ProcrastiMate facilitated learning and self-reflection while maintaining psychological distance, motivating players to integrate newly acquired knowledge in daily life. This paper contributes empirical insights on leveraging serious games to facilitate learning about procrastination and offers design implications for addressing psychological challenges through HCI approaches.

cs.HC↗

arXiv2025

MultiPDENet: PDE-embedded Learning with Multi-time-stepping for Accelerated Flow Simulation

Solving partial differential equations (PDEs) by numerical methods meet computational cost challenge for getting the accurate solution since fine grids and small time steps are required. Machine learning can accelerate this process, but struggle with weak generalizability, interpretability, and data dependency, as well as suffer in long-term prediction. To this end, we propose a PDE-embedded network with multiscale time stepping (MultiPDENet), which fuses the scheme of numerical methods and machine learning, for accelerated simulation of flows. In particular, we design a convolutional filter based on the structure of finite difference stencils with a small number of parameters to optimize, which estimates the equivalent form of spatial derivative on a coarse grid to minimize the equation's residual. A Physics Block with a 4th-order Runge-Kutta integrator at the fine time scale is established that embeds the structure of PDEs to guide the prediction. To alleviate the curse of temporal error accumulation in long-term prediction, we introduce a multiscale time integration approach, where a neural network is used to correct the prediction error at a coarse time scale. Experiments across various PDE systems, including the Navier-Stokes equations, demonstrate that MultiPDENet can accurately predict long-term spatiotemporal dynamics, even given small and incomplete training data, e.g., spatiotemporally down-sampled datasets. MultiPDENet achieves the state-of-the-art performance compared with other neural baseline models, also with clear speedup compared to classical numerical methods.

math.NA↗

arXiv2025

DynaPrompt: Dynamic Test-Time Prompt Tuning

Test-time prompt tuning enhances zero-shot generalization of vision-language models but tends to ignore the relatedness among test samples during inference. Online test-time prompt tuning provides a simple way to leverage the information in previous test samples, albeit with the risk of prompt collapse due to error accumulation. To enhance test-time prompt tuning, we propose DynaPrompt, short for dynamic test-time prompt tuning, exploiting relevant data distribution information while reducing error accumulation. Built on an online prompt buffer, DynaPrompt adaptively selects and optimizes the relevant prompts for each test sample during tuning. Specifically, we introduce a dynamic prompt selection strategy based on two metrics: prediction entropy and probability difference. For unseen test data information, we develop dynamic prompt appending, which allows the buffer to append new prompts and delete the inactive ones. By doing so, the prompts are optimized to exploit beneficial information on specific test data, while alleviating error accumulation. Experiments on fourteen datasets demonstrate the effectiveness of dynamic test-time prompt tuning.

cs.LG↗

arXiv2025

An Adaptive Cost-Sensitive Learning and Recursive Denoising Framework for Imbalanced SVM Classification

Category imbalance is one of the most popular and important issues in the domain of classification. Emotion classification model trained on imbalanced datasets easily leads to unreliable prediction. The traditional machine learning method tends to favor the majority class, which leads to the lack of minority class information in the model. Moreover, most existing models will produce abnormal sensitivity issues or performance degradation. We propose a robust learning algorithm based on adaptive cost-sensitivity and recursive denoising, which is a generalized framework and can be incorporated into most stochastic optimization algorithms. The proposed method uses the dynamic kernel distance optimization model between the sample and the decision boundary, which makes full use of the sample's prior information. In addition, we also put forward an effective method to filter noise, the main idea of which is to judge the noise by finding the nearest neighbors of the minority class. In order to evaluate the strength of the proposed method, we not only carry out experiments on standard datasets but also apply it to emotional classification problems with different imbalance rates (IR). Experimental results show that the proposed general framework is superior to traditional methods in Accuracy, G-mean, Recall and F1-score.

cs.CV↗