Searcharxiv⌕ Search

arXiv subjects

Yan Liu

Publications and source records attributed to Yan Liu.

At least 181 records · Page 10Linked to original sources
arXiv2025

InstaSHAP: Interpretable Additive Models Explain Shapley Values Instantly

In recent years, the Shapley value and SHAP explanations have emerged as one of the most dominant paradigms for providing post-hoc explanations of black-box models. Despite their well-founded theoretical properties, many recent works have focused on the limitations in both their computational efficiency and their representation power. The underlying connection with additive models, however, is left critically under-emphasized in the current literature. In this work, we find that a variational perspective linking GAM models and SHAP explanations is able to provide deep insights into nearly all recent developments. In light of this connection, we borrow in the other direction to develop a new method to train interpretable GAM models which are automatically purified to compute the Shapley value in a single forward pass. Finally, we provide theoretical results showing the limited representation power of GAM models is the same Achilles' heel existing in SHAP and discuss the implications for SHAP's modern usage in CV and NLP.

cs.LG↗
arXiv2025

TimeDiT: General-purpose Diffusion Transformers for Time Series Foundation Model

Foundation models, particularly Large Language Models (LLMs), have revolutionized text and video processing, yet time series data presents distinct challenges for such approaches due to domain-specific features such as missing values, multi-resolution characteristics, etc. Furthermore, the de-facto autoregressive transformers tend to learn deterministic temporal dependencies within pre-trained data while overlooking inherent uncertainties and lacking integration of physical constraints. In this paper, we introduce TimeDiT, a diffusion transformer model that synergistically combines transformer-based temporal dependency learning with diffusion-based probabilistic sampling. TimeDiT employs a unified masking mechanism to harmonize the training and inference process across diverse tasks while introducing a theoretically grounded, finetuning-free model editing strategy that enables flexible integration of external knowledge during sampling. Acknowledging the challenges of unifying multiple downstream tasks under a single model, our systematic evaluation demonstrates TimeDiT's effectiveness both in fundamental tasks, i.e., forecasting and imputation, through zero-shot/fine-tuning; and in domain tasks, i.e., multi-resolution forecasting, anomaly detection, and data generation, establishing it as a \textit{proto-foundation model} that bridges the gap between general-purpose and domain-specific models.

cs.LG↗
arXiv2025

On the extension of analytic solutions of first-order difference equations

We will consider first-order difference equations of the form \[ y(z+1) = \frac{λy(z)+a_2(z)y(z)^2+\cdots+a_p(z)y(z)^p}{1 + b_1(z)y(z)+\cdots+b_q(z)y(z)^q}, \] where $λ\in\mathbb{C}\setminus\{0\}$ and the coefficients $a_j(z)$ and $b_k(z)$ are meromorphic. When existence of an analytic solution can be proved for large negative values of $\Re(z)$, the equation determines a unique extension to a global meromorphic solution. In this paper we prove the existence of non-constant meromorphic solutions when the coefficients satisfy $|a_{j}(z)|\leq ν^{|z|}$ and $|b_{k}(z)|\leq ν^{|z|}$ for some $ν<|λ|$ in a half-plane. Furthermore, when a solution exists that is analytic for large positive values of $\Re(z)$, the equation determines a unique extension to a global solution that will generically have algebraic branch points. We analyse a particular constant coefficient equation, $y(z+1)=λy(z)+y(z)^2$, $0<λ<1$, and describe in detail the infinitely-sheeted Riemann surface for such a solution. We also describe solutions with natural boundaries found by Mahler.

math.CV↗
arXiv2025

Model-based temporal unmixing towards quantitative photo-switching optoacoustic tomography

Optoacoustic (OA) imaging combined with reversibly photoswitchable proteins has emerged as a promising technology for the high-sensitivity and multiplexed imaging of cells in live tissues in preclinical research. Through carefully-designed illumination schedules of ON and OFF laser pulses, the resulting OA signal is a multiplex of different reporter species and the background. We propose a model-based variational framework to computationally unmix and image different species of photo-switching reporters using optoacoustic tomography. It is based on a detailed mathematical description of the photo-switching mechanism, which models how relevant physical parameters such as the kinetic constants and light fluence impact the switching signal. We introduce an algorithm that operates on images, as opposed to traditional pixelwise approaches. It takes the form of an iterative inversion combined with tailored $\ell_1$ and total-variation regularization to increase the robustness to noise and to improve the unmixing quality. We show that our method is able to disentangle multiple spatially overlapping labels and to recover continuous maps of quantities of interest on controlled phantoms and mice experiments.

physics.optics↗
arXiv2025

Mixture of Knowledge Minigraph Agents for Literature Review Generation

Literature reviews play a crucial role in scientific research for understanding the current state of research, identifying gaps, and guiding future studies on specific topics. However, the process of conducting a comprehensive literature review is yet time-consuming. This paper proposes a novel framework, collaborative knowledge minigraph agents (CKMAs), to automate scholarly literature reviews. A novel prompt-based algorithm, the knowledge minigraph construction agent (KMCA), is designed to identify relations between concepts from academic literature and automatically constructs knowledge minigraphs. By leveraging the capabilities of large language models on constructed knowledge minigraphs, the multiple path summarization agent (MPSA) efficiently organizes concepts and relations from different viewpoints to generate literature review paragraphs. We evaluate CKMAs on three benchmark datasets. Experimental results show the effectiveness of the proposed method, further revealing promising applications of LLMs in scientific research.

cs.CL↗
arXiv2025

Data-Efficient Model for Psychological Resilience Prediction based on Neurological Data

Psychological resilience, defined as the ability to rebound from adversity, is crucial for mental health. Compared with traditional resilience assessments through self-reported questionnaires, resilience assessments based on neurological data offer more objective results with biological markers, hence significantly enhancing credibility. This paper proposes a novel data-efficient model to address the scarcity of neurological data. We employ Neuro Kolmogorov-Arnold Networks as the structure of the prediction model. In the training stage, a new trait-informed multimodal representation algorithm with a smart chunk technique is proposed to learn the shared latent space with limited data. In the test stage, a new noise-informed inference algorithm is proposed to address the low signal-to-noise ratio of the neurological data. The proposed model not only shows impressive performance on both public datasets and self-constructed datasets but also provides some valuable psychological hypotheses for future research.

cs.CE↗
arXiv2025

Universal Catalyst Design Framework for Electrochemical Hydrogen Peroxide Synthesis Facilitated by Local Atomic Environment Descriptors

Developing a universal and precise design framework is crucial to search high-performance catalysts, but it remains a giant challenge due to the diverse structures and sites across various types of catalysts. To address this challenge, herein, we developed a novel framework by the refined local atomic environment descriptors (i.e., weighted Atomic Center Symmetry Function, wACSF) combined with machine learning (ML), microkinetic modeling, and computational high-throughput screening. This framework is successfully integrated into the Digital Catalysis Database (DigCat), enabling efficient screening for 2e- water oxidation reaction (2e- WOR) catalysts across four material categories (i.e., metal alloys, metal oxides and perovskites, and single-atom catalysts) within a ML model. The proposed wACSF descriptors integrating both geometric and chemical features are proven effective in predicting the adsorption free energies with ML. Excitingly, based on the wACSF descriptors, the ML models accurately predict the adsorption free energies of hydroxyl (ΔGOH*) and oxygen (ΔGO*) for such a wide range of catalysts, achieving R2 values of 0.84 and 0.91, respectively. Through density functional theory calculations and microkinetic modeling, a universal 2e- WOR microkinetic volcano model was derived with excellent agreement with experimental observations reported to date, which was further used to rapidly screen high-performance catalysts with the input of ML-predicted ΔGOH*. Most importantly, this universal framework can significantly improve the efficiency of catalyst design by considering multiple types of materials at the same time, which can dramatically accelerate the screening of high-performance catalysts.

cond-mat.mtrl-sci↗
arXiv2025

Progressive Document-level Text Simplification via Large Language Models

Research on text simplification has primarily focused on lexical and sentence-level changes. Long document-level simplification (DS) is still relatively unexplored. Large Language Models (LLMs), like ChatGPT, have excelled in many natural language processing tasks. However, their performance on DS tasks is unsatisfactory, as they often treat DS as merely document summarization. For the DS task, the generated long sequences not only must maintain consistency with the original document throughout, but complete moderate simplification operations encompassing discourses, sentences, and word-level simplifications. Human editors employ a hierarchical complexity simplification strategy to simplify documents. This study delves into simulating this strategy through the utilization of a multi-stage collaboration using LLMs. We propose a progressive simplification method (ProgDS) by hierarchically decomposing the task, including the discourse-level, topic-level, and lexical-level simplification. Experimental results demonstrate that ProgDS significantly outperforms existing smaller models or direct prompting with LLMs, advancing the state-of-the-art in the document simplification task.

cs.CL↗
arXiv2024

Improving Generated and Retrieved Knowledge Combination Through Zero-shot Generation

Open-domain Question Answering (QA) has garnered substantial interest by combining the advantages of faithfully retrieved passages and relevant passages generated through Large Language Models (LLMs). However, there is a lack of definitive labels available to pair these sources of knowledge. In order to address this issue, we propose an unsupervised and simple framework called Bi-Reranking for Merging Generated and Retrieved Knowledge (BRMGR), which utilizes re-ranking methods for both retrieved passages and LLM-generated passages. We pair the two types of passages using two separate re-ranking methods and then combine them through greedy matching. We demonstrate that BRMGR is equivalent to employing a bipartite matching loss when assigning each retrieved passage with a corresponding LLM-generated passage. The application of our model yielded experimental results from three datasets, improving their performance by +1.7 and +1.6 on NQ and WebQ datasets, respectively, and obtaining comparable result on TriviaQA dataset when compared to competitive baselines.

cs.CL↗
arXiv2024

Clusterability test for categorical data

The objective of clusterability evaluation is to check whether a clustering structure exists within the data set. As a crucial yet often-overlooked issue in cluster analysis, it is essential to conduct such a test before applying any clustering algorithm. If a data set is unclusterable, any subsequent clustering analysis would not yield valid results. Despite its importance, the majority of existing studies focus on numerical data, leaving the clusterability evaluation issue for categorical data as an open problem. Here we present TestCat, a testing-based approach to assess the clusterability of categorical data in terms of an analytical $p$-value. The key idea underlying TestCat is that clusterable categorical data possess many strongly associated attribute pairs and hence the sum of chi-squared statistics of all attribute pairs is employed as the test statistic for $p$-value calculation. We apply our method to a set of benchmark categorical data sets, showing that TestCat outperforms those solutions based on existing clusterability evaluation methods for numeric data. To the best of our knowledge, our work provides the first way to effectively recognize the clusterability of categorical data in a statistically sound manner.

cs.LG↗
arXiv2024

Political-LLM: Large Language Models in Political Science

In recent years, large language models (LLMs) have been widely adopted in political science tasks such as election prediction, sentiment analysis, policy impact assessment, and misinformation detection. Meanwhile, the need to systematically understand how LLMs can further revolutionize the field also becomes urgent. In this work, we--a multidisciplinary team of researchers spanning computer science and political science--present the first principled framework termed Political-LLM to advance the comprehensive understanding of integrating LLMs into computational political science. Specifically, we first introduce a fundamental taxonomy classifying the existing explorations into two perspectives: political science and computational methodologies. In particular, from the political science perspective, we highlight the role of LLMs in automating predictive and generative tasks, simulating behavior dynamics, and improving causal inference through tools like counterfactual generation; from a computational perspective, we introduce advancements in data preparation, fine-tuning, and evaluation methods for LLMs that are tailored to political contexts. We identify key challenges and future directions, emphasizing the development of domain-specific datasets, addressing issues of bias and fairness, incorporating human expertise, and redefining evaluation criteria to align with the unique requirements of computational political science. Political-LLM seeks to serve as a guidebook for researchers to foster an informed, ethical, and impactful use of Artificial Intelligence in political science. Our online resource is available at: http://political-llm.org/.

cs.CL↗
arXiv2024

Active Sequential Posterior Estimation for Sample-Efficient Simulation-Based Inference

Computer simulations have long presented the exciting possibility of scientific insight into complex real-world processes. Despite the power of modern computing, however, it remains challenging to systematically perform inference under simulation models. This has led to the rise of simulation-based inference (SBI), a class of machine learning-enabled techniques for approaching inverse problems with stochastic simulators. Many such methods, however, require large numbers of simulation samples and face difficulty scaling to high-dimensional settings, often making inference prohibitive under resource-intensive simulators. To mitigate these drawbacks, we introduce active sequential neural posterior estimation (ASNPE). ASNPE brings an active learning scheme into the inference loop to estimate the utility of simulation parameter candidates to the underlying probabilistic model. The proposed acquisition scheme is easily integrated into existing posterior estimation pipelines, allowing for improved sample efficiency with low computational overhead. We further demonstrate the effectiveness of the proposed method in the travel demand calibration setting, a high-dimensional inverse problem commonly requiring computationally expensive traffic simulators. Our method outperforms well-tuned benchmarks and state-of-the-art posterior estimation methods on a large-scale real-world traffic network, as well as demonstrates a performance advantage over non-active counterparts on a suite of SBI benchmark environments.

cs.LG↗
arXiv2024

Point-Spread-Function Engineering in MINFLUX: Optimality of Donut and Half-Moon Excitation Patterns

Localization microscopy enables imaging with resolutions that surpass the conventional optical diffraction limit. Notably, the MINFLUX method achieves super-resolution by shaping the excitation point-spread function (PSF) to minimize the required photon flux for a given precision. Various beam shapes have recently been proposed to improve localization efficiency, yet their optimality remains an open question. In this work, we deploy a numerical and theoretical framework to determine optimal excitation patterns for MINFLUX. Such a computational approach allows us to search for new beam patterns in a fast and low-cost fashion, and to avoid time-consuming and expensive experimental explorations. We show that the conventional donut beam is a robust optimum when the excitation beams are all constrained to the same shape. Further, our PSF engineering framework yields two pairs of half-moon beams (orthogonal to each other) which can improve the theoretical localization precision by a factor of about two.

physics.optics↗
arXiv2024

3D Scene Graph Guided Vision-Language Pre-training

3D vision-language (VL) reasoning has gained significant attention due to its potential to bridge the 3D physical world with natural language descriptions. Existing approaches typically follow task-specific, highly specialized paradigms. Therefore, these methods focus on a limited range of reasoning sub-tasks and rely heavily on the hand-crafted modules and auxiliary losses. This highlights the need for a simpler, unified and general-purpose model. In this paper, we leverage the inherent connection between 3D scene graphs and natural language, proposing a 3D scene graph-guided vision-language pre-training (VLP) framework. Our approach utilizes modality encoders, graph convolutional layers and cross-attention layers to learn universal representations that adapt to a variety of 3D VL reasoning tasks, thereby eliminating the need for task-specific designs. The pre-training objectives include: 1) Scene graph-guided contrastive learning, which leverages the strong correlation between 3D scene graphs and natural language to align 3D objects with textual features at various fine-grained levels; and 2) Masked modality learning, which uses cross-modality information to reconstruct masked words and 3D objects. Instead of directly reconstructing the 3D point clouds of masked objects, we use position clues to predict their semantic categories. Extensive experiments demonstrate that our pre-training model, when fine-tuned on several downstream tasks, achieves performance comparable to or better than existing methods in tasks such as 3D visual grounding, 3D dense captioning, and 3D question answering.

cs.CV↗
arXiv2024

Accessing Excitation of Many-body Systems via Single-Mode Approximation within Quantum Monte Carlo Simulations

We extend the single-mode Approximation (SMA) into quantum Monte Carlo simulations to provides an efficient and fast method to obtain the dynamical dispersion of quantum many-body systems. Based on stochastic series expansion (SSE) and its projector algorithms, the SMA + SSE method can simply extract the dispersion of the dynamical dispersion in the long wave-length limit and the upper bound of the dispersion elsewhere, without external calculations and high technique barriers. Meanwhile, numerical analytic continuation methods require the fine data of imaginary time correlations and complex programming. Therefore, our method can approach the excitation dispersion of large systems, e.g., we take the two-dimensional Heisenberg model on a $512 \times 512$ square lattice. We demonstrate the effectiveness and efficiency of our method with high precision via additional examples. We also demonstrate that SMA combined with SSE goes beyond spin-wave theory with numerical results. We further illustrate that SMA is able to extract useful information in strongly correlated systems with competing states.

cond-mat.str-el↗
arXiv2024

Cavity-enhanced acousto-optic modulators on polymer-loaded lithium niobate integrated platform

On chip acousto-optic (AO) modulation represents a significant advancement in the development of highly integrated information processing systems. However, conventional photonic devices face substantial challenges in achieving efficient conversion due to the limited overlap between acoustic waves and optical waves. In this study, we address this limitation by demonstrating an enhanced conversion effect of photonic crystal nanobeam cavities (PCNBCs) in AO modulation on a polymer-loaded lithium niobate integrated platform. Attributed to the high ratio of quality factor (Q) to mode volume (V) and optimal light-sound overlap within the nanocavity, PCNBCs-based AO modulator exhibits a significantly enhanced extinction ratio of 38 dB with a threshold RF power below -50 dBm, which is two orders of magnitude lower than that based on micro-ring resonator (MRRs). In addition, robust digital amplitude shift keying modulations using selected RF and optical channels of the PCNBCs-enhanced AO modulators. These findings validate the compelling properties of the PCNBCs photonic platform, establishing it as a promising candidate for on-chip integrated microwave photonics, optical transceivers, and computing applications.

physics.optics↗
arXiv2024

An Open API Architecture to Discover the Trustworthy Explanation of Cloud AI Services

This article presents the design of an open-API-based explainable AI (XAI) service to provide feature contribution explanations for cloud AI services. Cloud AI services are widely used to develop domain-specific applications with precise learning metrics. However, the underlying cloud AI services remain opaque on how the model produces the prediction. We argue that XAI operations are accessible as open APIs to enable the consolidation of the XAI operations into the cloud AI services assessment. We propose a design using a microservice architecture that offers feature contribution explanations for cloud AI services without unfolding the network structure of the cloud models. We can also utilize this architecture to evaluate the model performance and XAI consistency metrics showing cloud AI services trustworthiness. We collect provenance data from operational pipelines to enable reproducibility within the XAI service. Furthermore, we present the discovery scenarios for the experimental tests regarding model performance and XAI consistency metrics for the leading cloud vision AI services. The results confirm that the architecture, based on open APIs, is cloud-agnostic. Additionally, data augmentations result in measurable improvements in XAI consistency metrics for cloud AI services.

cs.DC↗