arXiv subjects

Zichao Li

Publications and source records attributed to Zichao Li.

At least 37 records · Page 2Linked to original sources

arXiv2025

BigDocs: An Open Dataset for Training Multimodal Models on Document and Code Tasks

Multimodal AI has the potential to significantly enhance document-understanding tasks, such as processing receipts, understanding workflows, extracting data from documents, and summarizing reports. Code generation tasks that require long-structured outputs can also be enhanced by multimodality. Despite this, their use in commercial applications is often limited due to limited access to training data and restrictive licensing, which hinders open access. To address these limitations, we introduce BigDocs-7.5M, a high-quality, open-access dataset comprising 7.5 million multimodal documents across 30 tasks. We use an efficient data curation process to ensure our data is high-quality and license-permissive. Our process emphasizes accountability, responsibility, and transparency through filtering rules, traceable metadata, and careful content analysis. Additionally, we introduce BigDocs-Bench, a benchmark suite with 10 novel tasks where we create datasets that reflect real-world use cases involving reasoning over Graphical User Interfaces (GUI) and code generation from images. Our experiments show that training with BigDocs-Bench improves average performance up to 25.8% over closed-source GPT-4o in document reasoning and structured output tasks such as Screenshot2HTML or Image2Latex generation. Finally, human evaluations showed a preference for outputs from models trained on BigDocs over GPT-4o. This suggests that BigDocs can help both academics and the open-source community utilize and improve AI tools to enhance multimodal capabilities and document reasoning. The project is hosted at https://bigdocs.github.io .

cs.LG↗

arXiv2024

Dissipation Dilution-Driven Topology Optimization for Maximizing the $Q$ Factor of Nanomechanical Resonators

The quality factor ($Q$ factor) of nanomechanical resonators is influenced by geometry and stress, a phenomenon called dissipation dilution. Studies have explored maximizing this effect, leading to softly-clamped resonator designs. This paper proposes a topology optimization methodology to design two-dimensional nanomechanical resonators with high $Q$ factors by maximizing dissipation dilution. A formulation based on the ratio of geometrically nonlinear to linear modal stiffnesses of a prestressed finite element model is used, with its corresponding adjoint sensitivity analysis formulation. Systematic design in square domains yields geometries with comparable $Q$ factors to literature. We analyze the trade-offs between resonance frequency and quality factor, and how these are reflected in the geometry of resonators. We further apply the methodology to optimize a resonator on a full hexagonal domain. By using the entire mesh -- i.e., without assuming any symmetries -- we find that the optimizer converges to a two-axis symmetric design comprised of four tethers.

cond-mat.mes-hall↗

arXiv2024

Seg2Act: Global Context-aware Action Generation for Document Logical Structuring

Document logical structuring aims to extract the underlying hierarchical structure of documents, which is crucial for document intelligence. Traditional approaches often fall short in handling the complexity and the variability of lengthy documents. To address these issues, we introduce Seg2Act, an end-to-end, generation-based method for document logical structuring, revisiting logical structure extraction as an action generation task. Specifically, given the text segments of a document, Seg2Act iteratively generates the action sequence via a global context-aware generative model, and simultaneously updates its global context and current logical structure based on the generated actions. Experiments on ChCatExt and HierDoc datasets demonstrate the superior performance of Seg2Act in both supervised and transfer learning settings.

cs.CL↗

arXiv2024

The Connection between the Stochastic Schrödinger Equation and Boltzmann Equation

The heavy quarks present in the quark-gluon plasma (QGP) can act as a probe of relativistic heavy ion collisions as they retain the memory of their interaction history. In a previous study, a stochastic Schrödinger equation (SSE) has been applied to describe the transport process of heavy quarks, where an external field with random phases is used to simulate the thermal medium. In this work, we study the connection between the SSE and the Boltzmann equation (BE) approach in the Keldysh Green's function formalism. By comparing the Green's function of the heavy quark from the SSE and the Keldysh Green's functions leading to the Boltzmann equation, we demonstrate that the SSE is consistent with the Boltzmann equation in the weak coupling limit. We subsequently confirm their consistency through numerical calculations.

nucl-th↗

arXiv2024

Finite Element-based Nonlinear Dynamic Optimization of Nanomechanical Resonators

Nonlinear dynamic simulations of mechanical resonators have been facilitated by the advent of computational techniques that generate nonlinear reduced order models (ROMs) using the finite element (FE) method. However, designing devices with specific nonlinear characteristics remains inefficient since it requires manual adjustment of the design parameters and can result in suboptimal designs. Here, we integrate an FE-based nonlinear ROM technique with a derivative-free optimization algorithm to enable the design of nonlinear mechanical resonators. The resulting methodology is used to optimize the support design of high-stress nanomechanical Si3N4 string resonators, in the presence of conflicting objectives such as simultaneous enhancement of Q-factor and nonlinear Duffing constant. To that end, we generate Pareto frontiers that highlight the trade-offs between optimization objectives and validate the results both numerically and experimentally. To further demonstrate the capability of multi-objective optimization for practical design challenges, we simultaneously optimize the design of nanoresonators for three key figure-of-merits in resonant sensing: power consumption, sensitivity and response time. The presented methodology can facilitate and accelerate designing (nano)mechanical resonators with optimized performance for a wide variety of applications.

physics.app-ph↗

arXiv2024

Research on Feature Extraction Data Processing System For MRI of Brain Diseases Based on Computer Deep Learning

Most of the existing wavelet image processing techniques are carried out in the form of single-scale reconstruction and multiple iterations. However, processing high-quality fMRI data presents problems such as mixed noise and excessive computation time. This project proposes the use of matrix operations by combining mixed noise elimination methods with wavelet analysis to replace traditional iterative algorithms. Functional magnetic resonance imaging (fMRI) of the auditory cortex of a single subject is analyzed and compared to the wavelet domain signal processing technology based on repeated times and the world's most influential SPM8. Experiments show that this algorithm is the fastest in computing time, and its detection effect is comparable to the traditional iterative algorithm. However, this has a higher practical value for the processing of FMRI data. In addition, the wavelet analysis method proposed signal processing to speed up the calculation rate.

eess.IV↗

arXiv2024

Scaling (Down) CLIP: A Comprehensive Analysis of Data, Architecture, and Training Strategies

This paper investigates the performance of the Contrastive Language-Image Pre-training (CLIP) when scaled down to limited computation budgets. We explore CLIP along three dimensions: data, architecture, and training strategies. With regards to data, we demonstrate the significance of high-quality training data and show that a smaller dataset of high-quality data can outperform a larger dataset with lower quality. We also examine how model performance varies with different dataset sizes, suggesting that smaller ViT models are better suited for smaller datasets, while larger models perform better on larger datasets with fixed compute. Additionally, we provide guidance on when to choose a CNN-based architecture or a ViT-based architecture for CLIP training. We compare four CLIP training strategies - SLIP, FLIP, CLIP, and CLIP+Data Augmentation - and show that the choice of training strategy depends on the available compute resource. Our analysis reveals that CLIP+Data Augmentation can achieve comparable performance to CLIP using only half of the training data. This work provides practical insights into how to effectively train and deploy CLIP models, making them more accessible and affordable for practical use in various applications.

cs.CV↗

arXiv2024

On the Adversarial Robustness of Camera-based 3D Object Detection

In recent years, camera-based 3D object detection has gained widespread attention for its ability to achieve high performance with low computational cost. However, the robustness of these methods to adversarial attacks has not been thoroughly examined, especially when considering their deployment in safety-critical domains like autonomous driving. In this study, we conduct the first comprehensive investigation of the robustness of leading camera-based 3D object detection approaches under various adversarial conditions. We systematically analyze the resilience of these models under two attack settings: white-box and black-box; focusing on two primary objectives: classification and localization. Additionally, we delve into two types of adversarial attack techniques: pixel-based and patch-based. Our experiments yield four interesting findings: (a) bird's-eye-view-based representations exhibit stronger robustness against localization attacks; (b) depth-estimation-free approaches have the potential to show stronger robustness; (c) accurate depth estimation effectively improves robustness for depth-estimation-based methods; (d) incorporating multi-frame benign inputs can effectively mitigate adversarial attacks. We hope our findings can steer the development of future camera-based object detection models with enhanced adversarial robustness.

cs.CV↗

arXiv2023

Evaluating Dependencies in Fact Editing for Language Models: Specificity and Implication Awareness

The potential of using a large language model (LLM) as a knowledge base (KB) has sparked significant interest. To manage the knowledge acquired by LLMs, we need to ensure that the editing of learned facts respects internal logical constraints, which are known as dependency of knowledge. Existing work on editing LLMs has partially addressed the issue of dependency, when the editing of a fact should apply to its lexical variations without disrupting irrelevant ones. However, they neglect the dependency between a fact and its logical implications. We propose an evaluation protocol with an accompanying question-answering dataset, DepEdit, that provides a comprehensive assessment of the editing process considering the above notions of dependency. Our protocol involves setting up a controlled environment in which we edit facts and monitor their impact on LLMs, along with their implications based on If-Then rules. Extensive experiments on DepEdit show that existing knowledge editing methods are sensitive to the surface form of knowledge, and that they have limited performance in inferring the implications of edited facts.

cs.CL↗

arXiv2023

f-Divergence Minimization for Sequence-Level Knowledge Distillation

Knowledge distillation (KD) is the process of transferring knowledge from a large model to a small one. It has gained increasing attention in the natural language processing community, driven by the demands of compressing ever-growing language models. In this work, we propose an f-DISTILL framework, which formulates sequence-level knowledge distillation as minimizing a generalized f-divergence function. We propose four distilling variants under our framework and show that existing SeqKD and ENGINE approaches are approximations of our f-DISTILL methods. We further derive step-wise decomposition for our f-DISTILL, reducing intractable sequence-level divergence to word-level losses that can be computed in a tractable manner. Experiments across four datasets show that our methods outperform existing KD approaches, and that our symmetric distilling losses can better force the student to learn from the teacher distribution.

cs.CL↗

arXiv2023

Tied-Augment: Controlling Representation Similarity Improves Data Augmentation

Data augmentation methods have played an important role in the recent advance of deep learning models, and have become an indispensable component of state-of-the-art models in semi-supervised, self-supervised, and supervised training for vision. Despite incurring no additional latency at test time, data augmentation often requires more epochs of training to be effective. For example, even the simple flips-and-crops augmentation requires training for more than 5 epochs to improve performance, whereas RandAugment requires more than 90 epochs. We propose a general framework called Tied-Augment, which improves the efficacy of data augmentation in a wide range of applications by adding a simple term to the loss that can control the similarity of representations under distortions. Tied-Augment can improve state-of-the-art methods from data augmentation (e.g. RandAugment, mixup), optimization (e.g. SAM), and semi-supervised learning (e.g. FixMatch). For example, Tied-RandAugment can outperform RandAugment by 2.0% on ImageNet. Notably, using Tied-Augment, data augmentation can be made to improve generalization even when training for a few epochs and when fine-tuning. We open source our code at https://github.com/ekurtulus/tied-augment/tree/main.

cs.CV↗

arXiv2022

On Curie temperature of B20-MnSi films

B20-type MnSi is the prototype magnetic skyrmion material. Thin films of MnSi show a higher Curie temperature than their bulk counterpart. However, it is not yet clear what mechanism leads to the increase of the Curie temperature. In this work, we grow MnSi films on Si(100) and Si(111) substrates with a broad variation in their structures. By controlling the Mn thickness and annealing parameters, the pure MnSi phase of polycrystalline and textured nature as well as the mixed phase of MnSi and MnSi1.7 are obtained. Surprisingly, all these MnSi films show an increased Curie temperature of up to around 43 K. The Curie temperature is likely independent of the structural parameters within our accessibility including the film thickness above a threshold, strain, cell volume and the mixture with MnSi1.7. However, a pronounced phonon softening is observed for all samples, which can tentatively be attributed to slight Mn excess from stoichiometry, leading to the increased Curie temperature.

cond-mat.mtrl-sci↗

arXiv2022

Bag of Tricks for FGSM Adversarial Training

Adversarial training (AT) with samples generated by Fast Gradient Sign Method (FGSM), also known as FGSM-AT, is a computationally simple method to train robust networks. However, during its training procedure, an unstable mode of "catastrophic overfitting" has been identified in arXiv:2001.03994 [cs.LG], where the robust accuracy abruptly drops to zero within a single training step. Existing methods use gradient regularizers or random initialization tricks to attenuate this issue, whereas they either take high computational cost or lead to lower robust accuracy. In this work, we provide the first study, which thoroughly examines a collection of tricks from three perspectives: Data Initialization, Network Structure, and Optimization, to overcome the catastrophic overfitting in FGSM-AT. Surprisingly, we find that simple tricks, i.e., a) masking partial pixels (even without randomness), b) setting a large convolution stride and smooth activation functions, or c) regularizing the weights of the first convolutional layer, can effectively tackle the overfitting issue. Extensive results on a range of network architectures validate the effectiveness of each proposed trick, and the combinations of tricks are also investigated. For example, trained with PreActResNet-18 on CIFAR-10, our method attains 49.8% accuracy against PGD-50 attacker and 46.4% accuracy against AutoAttack, demonstrating that pure FGSM-AT is capable of enabling robust learners. The code and models are publicly available at https://github.com/UCSC-VLAA/Bag-of-Tricks-for-FGSM-AT.

cs.CV↗

arXiv2022

Text Revision by On-the-Fly Representation Optimization

Text revision refers to a family of natural language generation tasks, where the source and target sequences share moderate resemblance in surface form but differentiate in attributes, such as text formality and simplicity. Current state-of-the-art methods formulate these tasks as sequence-to-sequence learning problems, which rely on large-scale parallel training corpus. In this paper, we present an iterative in-place editing approach for text revision, which requires no parallel data. In this approach, we simply fine-tune a pre-trained Transformer with masked language modeling and attribute classification. During inference, the editing at each iteration is realized by two-step span replacement. At the first step, the distributed representation of the text optimizes on the fly towards an attribute function. At the second step, a text span is masked and another new one is proposed conditioned on the optimized representation. The empirical experiments on two typical and important text revision tasks, text formalization and text simplification, show the effectiveness of our approach. It achieves competitive and even better performance than state-of-the-art supervised methods on text simplification, and gains better performance than strong unsupervised methods on text formalization \footnote{Code and model are available at \url{https://github.com/jingjingli01/OREO}}.

cs.CL↗

arXiv2022

Using Interactive Feedback to Improve the Accuracy and Explainability of Question Answering Systems Post-Deployment

Most research on question answering focuses on the pre-deployment stage; i.e., building an accurate model for deployment. In this paper, we ask the question: Can we improve QA systems further \emph{post-}deployment based on user interactions? We focus on two kinds of improvements: 1) improving the QA system's performance itself, and 2) providing the model with the ability to explain the correctness or incorrectness of an answer. We collect a retrieval-based QA dataset, FeedbackQA, which contains interactive feedback from users. We collect this dataset by deploying a base QA system to crowdworkers who then engage with the system and provide feedback on the quality of its answers. The feedback contains both structured ratings and unstructured natural language explanations. We train a neural model with this feedback data that can generate explanations and re-score answer candidates. We show that feedback data not only improves the accuracy of the deployed QA system but also other stronger non-deployed systems. The generated explanations also help users make informed decisions about the correctness of answers. Project page: https://mcgill-nlp.github.io/feedbackqa/

cs.CL↗

arXiv2022

Beam Search for Feature Selection

In this paper, we present and prove some consistency results about the performance of classification models using a subset of features. In addition, we propose to use beam search to perform feature selection, which can be viewed as a generalization of forward selection. We apply beam search to both simulated and real-world data, by evaluating and comparing the performance of different classification models using different sets of features. The results demonstrate that beam search could outperform forward selection, especially when the features are correlated so that they have more discriminative power when considered jointly than individually. Moreover, in some cases classification models could obtain comparable performance using only ten features selected by beam search instead of hundreds of original features.

cs.LG↗

arXiv2022

Classification with Nearest Disjoint Centroids

In this paper, we develop a new classification method based on nearest centroid, and it is called the nearest disjoint centroid classifier. Our method differs from the nearest centroid classifier in the following two aspects: (1) the centroids are defined based on disjoint subsets of features instead of all the features, and (2) the distance is induced by the dimensionality-normalized norm instead of the Euclidean norm. We provide a few theoretical results regarding our method. In addition, we propose a simple algorithm based on adapted k-means clustering that can find the disjoint subsets of features used in our method, and extend the algorithm to perform feature selection. We evaluate and compare the performance of our method to other classification methods on both simulated data and real-world gene expression datasets. The results demonstrate that our method is able to outperform other competing classifiers by having smaller misclassification rates and/or using fewer features in various settings and situations.

cs.LG↗

arXiv2022

Biclustering with Alternating K-Means

Biclustering is the task of simultaneously clustering the rows and columns of the data matrix into different subgroups such that the rows and columns within a subgroup exhibit similar patterns. In this paper, we consider the case of producing block-diagonal biclusters. We provide a new formulation of the biclustering problem based on the idea of minimizing the empirical clustering risk. We develop and prove a consistency result with respect to the empirical clustering risk. Since the optimization problem is combinatorial in nature, finding the global minimum is computationally intractable. In light of this fact, we propose a simple and novel algorithm that finds a local minimum by alternating the use of an adapted version of the k-means clustering algorithm between columns and rows. We evaluate and compare the performance of our algorithm to other related biclustering methods on both simulated data and real-world gene expression data sets. The results demonstrate that our algorithm is able to detect meaningful structures in the data and outperform other competing biclustering methods in various settings and situations.

cs.LG↗