arXiv subjects

Huan Liu

Publications and source records attributed to Huan Liu.

At least 127 records · Page 7Linked to original sources

arXiv2025

Constrained Gaussian Wasserstein Optimal Transport with Commutative Covariance Matrices

Optimal transport has found widespread applications in signal processing and machine learning. Among its many equivalent formulations, optimal transport seeks to reconstruct a random variable/vector with a prescribed distribution at the destination while minimizing the expected distortion relative to a given random variable/vector at the source. However, in practice, certain constraints may render the optimal transport plan infeasible. In this work, we consider three types of constraints: rate constraints, dimension constraints, and channel constraints, motivated by perception-aware lossy compression, generative principal component analysis, and deep joint source-channel coding, respectively. Special attenion is given to the setting termed Gaussian Wasserstein optimal transport, where both the source and reconstruction variables are multivariate Gaussian, and the end-to-end distortion is measured by the mean squared error. We derive explicit results for the minimum achievable mean squared error under the three aforementioned constraints when the covariance matrices of the source and reconstruction variables commute.

cs.IT↗

arXiv2025

Can LLMs Improve Multimodal Fact-Checking by Asking Relevant Questions?

Traditional fact-checking relies on humans to formulate relevant and targeted fact-checking questions (FCQs), search for evidence, and verify the factuality of claims. While Large Language Models (LLMs) have been commonly used to automate evidence retrieval and factuality verification at scale, their effectiveness for fact-checking is hindered by the absence of FCQ formulation. To bridge this gap, we seek to answer two research questions: (1) Can LLMs generate relevant FCQs? (2) Can LLM-generated FCQs improve multimodal fact-checking? We therefore introduce a framework LRQ-FACT for using LLMs to generate relevant FCQs to facilitate evidence retrieval and enhance fact-checking by probing information across multiple modalities. Through extensive experiments, we verify if LRQ-FACT can generate relevant FCQs of different types and if LRQ-FACT can consistently outperform baseline methods in multimodal fact-checking. Further analysis illustrates how each component in LRQ-FACT works toward improving the fact-checking performance.

cs.CL↗

arXiv2025

Comprehensive scaling laws across animals, microorganisms and plants

Scaling laws illuminate Nature's fundamental biological principles and guide bioinspired materials and structural designs. In simple cases they are based on the fundamental principle that all laws of nature remain unchanged (i.e., invariant) under a change of units. A more general framework is a change of variables for the governing laws that takes all equations, boundary, and interaction conditions into themselves. We consider an accepted macroscale system of partial differential equations including coupled fluid dynamics, nonlinear elasticity, and rigid body mechanics for a complex organism. We show that there is a set of scaling laws where length, time, density, elastic modulus, viscosity, and gravitational constant undergo nontrivial scaling (Table 1). We compare these results to extensive data sets mined from the literature on beating frequency of flying, swimming, and running animals, speed of bacteria, insects, fish, mammals and reptiles, leg stiffness of mammals, and modulus of elasticity of plants. The uniform agreement of the scaling laws with the dynamics of fauna, flora, and microorganisms supports the dominating role of coupled nonlinear elasticity and fluid dynamics in evolutionary development. We conclude with predictions for some prehistoric cases for which observations are unavailable.

physics.bio-ph↗

arXiv2025

MIND-EEG: Multi-granularity Integration Network with Discrete Codebook for EEG-based Emotion Recognition

Emotion recognition using electroencephalogram (EEG) signals has broad potential across various domains. EEG signals have ability to capture rich spatial information related to brain activity, yet effectively modeling and utilizing these spatial relationships remains a challenge. Existing methods struggle with simplistic spatial structure modeling, failing to capture complex node interactions, and lack generalizable spatial connection representations, failing to balance the dynamic nature of brain networks with the need for discriminative and generalizable features. To address these challenges, we propose the Multi-granularity Integration Network with Discrete Codebook for EEG-based Emotion Recognition (MIND-EEG). The framework employs a multi-granularity approach, integrating global and regional spatial information through a Global State Encoder, an Intra-Regional Functionality Encoder, and an Inter-Regional Interaction Encoder to comprehensively model brain activity. Additionally, we introduce a discrete codebook mechanism for constructing network structures via vector quantization, ensuring compact and meaningful brain network representations while mitigating over-smoothing and enhancing model generalization. The proposed framework effectively captures the dynamic and diverse nature of EEG signals, enabling robust emotion recognition. Extensive comparisons and analyses demonstrate the effectiveness of MIND-EEG, and the source code is publicly available at https://anonymous.4open.science/r/MIND_EEG.

cs.HC↗

arXiv2025

A machine-learning optimized vertical-axis wind turbine

Vertical-axis wind turbines (VAWTs) have garnered increasing attention in the field of renewable energy due to their unique advantages over traditional horizontal-axis wind turbines (HAWTs). However, traditional VAWTs including Darrieus and Savonius types suffer from significant drawbacks -- negative torque regions exist during rotation. In this work, we propose a new design of VAWT, which combines design principles from both Darrieus and Savonius but addresses their inherent defects. The performance of the proposed VAWT is evaluated through numerical simulations and validated by experimental testing. The results demonstrate that its power output is approximately three times greater than that of traditional Savonius VAWTs of comparable size. The performance of the proposed VAWT is further optimized using machine learning techniques, including Gaussian process regression and neural networks, based on extensive supercomputer simulations. This optimization leads to a 30% increase in power output.

eess.SP↗

arXiv2025

Sibyl: Empowering Empathetic Dialogue Generation in Large Language Models via Sensible and Visionary Commonsense Inference

Recently, there has been a heightened interest in building chatbots based on Large Language Models (LLMs) to emulate human-like qualities in multi-turn conversations. Despite having access to commonsense knowledge to better understand the psychological aspects and causality of dialogue context, even these powerful LLMs struggle to achieve the goals of empathy and emotional support. Current commonsense knowledge derived from dialogue contexts is inherently limited and often fails to adequately anticipate the future course of a dialogue. This lack of foresight can mislead LLMs and hinder their ability to provide effective support. In response to this challenge, we present an innovative framework named Sensible and Visionary Commonsense Knowledge (Sibyl). Designed to concentrate on the immediately succeeding dialogue, this paradigm equips LLMs with the capability to uncover the implicit requirements of the conversation, aiming to elicit more empathetic responses. Experimental results demonstrate that incorporating our paradigm for acquiring commonsense knowledge into LLMs comprehensively enhances the quality of their responses.

cs.CL↗

arXiv2025

A Multi-Label EEG Dataset for Mental Attention State Classification in Online Learning

Attention is a vital cognitive process in the learning and memory environment, particularly in the context of online learning. Traditional methods for classifying attention states of online learners based on behavioral signals are prone to distortion, leading to increased interest in using electroencephalography (EEG) signals for authentic and accurate assessment. However, the field of attention state classification based on EEG signals in online learning faces challenges, including the scarcity of publicly available datasets, the lack of standardized data collection paradigms, and the requirement to consider the interplay between attention and other psychological states. In light of this, we present the Multi-label EEG dataset for classifying Mental Attention states (MEMA) in online learning. We meticulously designed a reliable and standard experimental paradigm with three attention states: neutral, relaxing, and concentrating, considering human physiological and psychological characteristics. This paradigm collected EEG signals from 20 subjects, each participating in 12 trials, resulting in 1,060 minutes of data. Emotional state labels, basic personal information, and personality traits were also collected to investigate the relationship between attention and other psychological states. Extensive quantitative and qualitative analysis, including a multi-label correlation study, validated the quality of the EEG attention data. The MEMA dataset and analysis provide valuable insights for advancing research on attention in online learning. The dataset is publicly available at \url{https://github.com/GuanjianLiu/MEMA}.

cs.HC↗

arXiv2025

Riemann--Hilbert method to the Ablowitz--Ladik equation: higher-order case

We focused on the Ablowitz--Ladik equation on a zero background, specifically considering the scenario of $N$ pairs of multiple poles. Our first goal was to establish a mapping between the initial data and the scattering data. This allowed us to introduce a direct problem by analyzing the discrete spectrum associated with $N$ pairs of higher-order zeros. Next, we constructed another mapping from the scattering data to a $2\times2$ matrix Riemann--Hilbert problem equipped with several residue conditions set at $N$ pairs of multiple poles. By characterizing the inverse problem based on this Riemann--Hilbert problem, we were able to derive higher-order soliton solutions in the reflectionless case. Furthermore, we expressed an infinite-order soliton solution using a special Riemann--Hilbert problem formulation.

nlin.SI↗

arXiv2025

Real-Valued Vector Modified Korteweg--de Vries Equation: Solitons Featuring Multiple Poles

We delve into the inverse scattering transform of the real-valued vector modified Korteweg--de Vries equation, emphasizing the challenges posed by $N$ pairs of higher-order poles in the transmission coefficient and the enhanced spectral symmetry stemming from real-valued constraints. Utilizing the generalized vector cross product, we formulate an $(n+1)\times(n+1)$ matrix-valued Riemann--Hilbert problem to tackle the complexities inherent in multi-component systems. We subsequently demonstrate the existence and uniqueness of solutions for a singularity-free equivalent problem, adeptly handling the intricacies of multiple poles. In reflectionless cases, we reconstruct multi-pole soliton solutions through a system of linear algebraic equations.

nlin.PS↗

arXiv2025

Visual Large Language Models for Generalized and Specialized Applications

Visual-language models (VLM) have emerged as a powerful tool for learning a unified embedding space for vision and language. Inspired by large language models, which have demonstrated strong reasoning and multi-task capabilities, visual large language models (VLLMs) are gaining increasing attention for building general-purpose VLMs. Despite the significant progress made in VLLMs, the related literature remains limited, particularly from a comprehensive application perspective, encompassing generalized and specialized applications across vision (image, video, depth), action, and language modalities. In this survey, we focus on the diverse applications of VLLMs, examining their using scenarios, identifying ethics consideration and challenges, and discussing future directions for their development. By synthesizing these contents, we aim to provide a comprehensive guide that will pave the way for future innovations and broader applications of VLLMs. The paper list repository is available: https://github.com/JackYFL/awesome-VLLMs.

cs.CV↗

arXiv2024

Revisiting MLLMs: An In-Depth Analysis of Image Classification Abilities

With the rapid advancement of Multimodal Large Language Models (MLLMs), a variety of benchmarks have been introduced to evaluate their capabilities. While most evaluations have focused on complex tasks such as scientific comprehension and visual reasoning, little attention has been given to assessing their fundamental image classification abilities. In this paper, we address this gap by thoroughly revisiting the MLLMs with an in-depth analysis of image classification. Specifically, building on established datasets, we examine a broad spectrum of scenarios, from general classification tasks (e.g., ImageNet, ObjectNet) to more fine-grained categories such as bird and food classification. Our findings reveal that the most recent MLLMs can match or even outperform CLIP-style vision-language models on several datasets, challenging the previous assumption that MLLMs are bad at image classification \cite{VLMClassifier}. To understand the factors driving this improvement, we conduct an in-depth analysis of the network architecture, data selection, and training recipe used in public MLLMs. Our results attribute this success to advancements in language models and the diversity of training data sources. Based on these observations, we further analyze and attribute the potential reasons to conceptual knowledge transfer and enhanced exposure of target concepts, respectively. We hope our findings will offer valuable insights for future research on MLLMs and their evaluation in image classification tasks.

cs.CV↗

arXiv2024

Band Offsets at β/γ-$\mathrm{Ga}_{2}\mathrm{O}_{3}$ Interface

Ultrawide bandgap semiconductor gallium oxide (Ga2O3) and its polymorphs have recently attracted increasing attention across physics, materials science, and electronics communities. In particular, the self-organized formation of the beta/gamma-Ga2O3 double polymorph structures was demonstrated recently [A. Azarov et al., Nat. Commun. 14, 4855 (2023)], paving the way for prospective applications of such structures in electronics. Consequently, determining the conduction band offset in such structures is crucial since it dictates the behavior of conduction electrons at the interface and, consequently, the potential functionality of such interfaces. Thus, in this work, we calculate the band offsets at the beta/gamma-Ga2O3 interface using density functional theory in correlation with the data provided by the experimental atomistic interface analysis. Specifically, to unravel the strain state of the beta/gamma-Ga2O3 interface, nanoscale strain maps were recorded using high-resolution transmission electron microscopy. In its turn, theoretically, lineup potential and vacuum alignment methods were used to analyze the band offsets, with and without strain, at the beta/gamma-Ga2O3 interface. Altogether, the collected results suggest that the band offsets between the beta and gamma phases are likely not exceeding a few hundred meV, remaining highly sensitive to the strain state at the interface. At this end, we conclude that even though the formation of a two-dimensional electron gas (2DEG) at the beta/gamma interface is theoretically possible, the gradual strain relaxation--if it occurs as a function of the distance from the interface--poses a significant challenge, as it may shift the 2DEG localization or even reduce the overall probability of its formation.

cond-mat.mtrl-sci↗

arXiv2024

Assessing the Impact of Conspiracy Theories Using Large Language Models

Measuring the relative impact of CTs is important for prioritizing responses and allocating resources effectively, especially during crises. However, assessing the actual impact of CTs on the public poses unique challenges. It requires not only the collection of CT-specific knowledge but also diverse information from social, psychological, and cultural dimensions. Recent advancements in large language models (LLMs) suggest their potential utility in this context, not only due to their extensive knowledge from large training corpora but also because they can be harnessed for complex reasoning. In this work, we develop datasets of popular CTs with human-annotated impacts. Borrowing insights from human impact assessment processes, we then design tailored strategies to leverage LLMs for performing human-like CT impact assessments. Through rigorous experiments, we textit{discover that an impact assessment mode using multi-step reasoning to analyze more CT-related evidence critically produces accurate results; and most LLMs demonstrate strong bias, such as assigning higher impacts to CTs presented earlier in the prompt, while generating less accurate impact assessments for emotionally charged and verbose CTs.

cs.CL↗

arXiv2024

C2P-CLIP: Injecting Category Common Prompt in CLIP to Enhance Generalization in Deepfake Detection

This work focuses on AIGC detection to develop universal detectors capable of identifying various types of forgery images. Recent studies have found large pre-trained models, such as CLIP, are effective for generalizable deepfake detection along with linear classifiers. However, two critical issues remain unresolved: 1) understanding why CLIP features are effective on deepfake detection through a linear classifier; and 2) exploring the detection potential of CLIP. In this study, we delve into the underlying mechanisms of CLIP's detection capabilities by decoding its detection features into text and performing word frequency analysis. Our finding indicates that CLIP detects deepfakes by recognizing similar concepts (Fig. \ref{fig:fig1} a). Building on this insight, we introduce Category Common Prompt CLIP, called C2P-CLIP, which integrates the category common prompt into the text encoder to inject category-related concepts into the image encoder, thereby enhancing detection performance (Fig. \ref{fig:fig1} b). Our method achieves a 12.41\% improvement in detection accuracy compared to the original CLIP, without introducing additional parameters during testing. Comprehensive experiments conducted on two widely-used datasets, encompassing 20 generation models, validate the efficacy of the proposed method, demonstrating state-of-the-art performance. The code is available at \url{https://github.com/chuangchuangtan/C2P-CLIP-DeepfakeDetection}

cs.CV↗

arXiv2024

Large Language Models for Data Annotation and Synthesis: A Survey

Data annotation and synthesis generally refers to the labeling or generating of raw data with relevant information, which could be used for improving the efficacy of machine learning models. The process, however, is labor-intensive and costly. The emergence of advanced Large Language Models (LLMs), exemplified by GPT-4, presents an unprecedented opportunity to automate the complicated process of data annotation and synthesis. While existing surveys have extensively covered LLM architecture, training, and general applications, we uniquely focus on their specific utility for data annotation. This survey contributes to three core aspects: LLM-Based Annotation Generation, LLM-Generated Annotations Assessment, and LLM-Generated Annotations Utilization. Furthermore, this survey includes an in-depth taxonomy of data types that LLMs can annotate, a comprehensive review of learning strategies for models utilizing LLM-generated annotations, and a detailed discussion of the primary challenges and limitations associated with using LLMs for data annotation and synthesis. Serving as a key guide, this survey aims to assist researchers and practitioners in exploring the potential of the latest LLMs for data annotation, thereby fostering future advancements in this critical field.

cs.CL↗

arXiv2024

Inverse Scattering Transform for the Massive Thirring Model: Delving into Higher-Order Pole Dynamics

We investigate the inverse scattering problem for the massive Thirring model, focusing particularly on cases where the transmission coefficient exhibits $N$ pairs of higher-order poles. Our methodology involves transforming initial data into scattering data via the direct scattering problem. Utilizing two parameter transformations, we examine the asymptotic properties of the Jost functions at both vanishing and infinite parameters, yielding two equivalent spectral problems. We subsequently devise a mapping that translates the obtained scattering data into a $2 \times 2$ matrix Riemann--Hilbert problem, incorporating several residue conditions at $N$ pairs of multiple poles. Additionally, we construct an equivalent pole-free Riemann--Hilbert problem and demonstrate the existence and uniqueness of its solution. In the reflectionless case, the $N$-multipole solutions can be reconstructed by resolving two linear algebraic systems.

nlin.SI↗

arXiv2024

Spatio-temporal Causal Learning for Streamflow Forecasting

Streamflow plays an essential role in the sustainable planning and management of national water resources. Traditional hydrologic modeling approaches simulate streamflow by establishing connections across multiple physical processes, such as rainfall and runoff. These data, inherently connected both spatially and temporally, possess intrinsic causal relations that can be leveraged for robust and accurate forecasting. Recently, spatio-temporal graph neural networks (STGNNs) have been adopted, excelling in various domains, such as urban traffic management, weather forecasting, and pandemic control, and they also promise advances in streamflow management. However, learning causal relationships directly from vast observational data is theoretically and computationally challenging. In this study, we employ a river flow graph as prior knowledge to facilitate the learning of the causal structure and then use the learned causal graph to predict streamflow at targeted sites. The proposed model, Causal Streamflow Forecasting (CSF) is tested in a real-world study in the Brazos River basin in Texas. Our results demonstrate that our method outperforms regular spatio-temporal graph neural networks and achieves higher computational efficiency compared to traditional simulation methods. By effectively integrating river flow graphs with STGNNs, this research offers a novel approach to streamflow prediction, showcasing the potential of combining advanced neural network techniques with domain-specific knowledge for enhanced performance in hydrologic modeling.

cs.LG↗

arXiv2024

Evaluating LLMs Capabilities Towards Understanding Social Dynamics

Social media discourse involves people from different backgrounds, beliefs, and motives. Thus, often such discourse can devolve into toxic interactions. Generative Models, such as Llama and ChatGPT, have recently exploded in popularity due to their capabilities in zero-shot question-answering. Because these models are increasingly being used to ask questions of social significance, a crucial research question is whether they can understand social media dynamics. This work provides a critical analysis regarding generative LLM's ability to understand language and dynamics in social contexts, particularly considering cyberbullying and anti-cyberbullying (posts aimed at reducing cyberbullying) interactions. Specifically, we compare and contrast the capabilities of different large language models (LLMs) to understand three key aspects of social dynamics: language, directionality, and the occurrence of bullying/anti-bullying messages. We found that while fine-tuned LLMs exhibit promising results in some social media understanding tasks (understanding directionality), they presented mixed results in others (proper paraphrasing and bullying/anti-bullying detection). We also found that fine-tuning and prompt engineering mechanisms can have positive effects in some tasks. We believe that a understanding of LLM's capabilities is crucial to design future models that can be effectively used in social applications.

cs.LG↗