arXiv subjects

Lan Li

Publications and source records attributed to Lan Li.

At least 37 records · Page 2Linked to original sources

arXiv2024

On-Chip Vectorial Structured Light Manipulation via Inverse Design

On-chip structured light, with potentially infinite complexity, has emerged as a linchpin in the realm of integrated photonics. However, the realization of arbitrarily tailoring a multitude of light field dimensions in complex media remains a challenge1, Through associating physical light fields and mathematical function spaces by introducing a mapping operator, we proposed a data-driven inverse design method to precisely manipulate between any two structured light fields in the on-chip high-dimensional Hilbert space. To illustrate, light field conversion in on-chip topological photonics was achieved. High-performance topological coupling devices with minimal insertion loss and customizable topological routing devices were designed and realized. Our method provides a new paradigm to enable precise manipulation over the on-chip vectorial structured light and paves the way for the realization of complex photonic functions.

physics.optics↗

arXiv2024

Reconciling Conflicting Data Curation Actions: Transparency Through Argumentation

We propose a new approach for modeling and reconciling conflicting data cleaning actions. Such conflicts arise naturally in collaborative data curation settings where multiple experts work independently and then aim to put their efforts together to improve and accelerate data cleaning. The key idea of our approach is to model conflicting updates as a formal \emph{argumentation framework}(AF). Such argumentation frameworks can be automatically analyzed and solved by translating them to a logic program $P_{AF}$ whose declarative semantics yield a transparent solution with many desirable properties, e.g., uncontroversial updates are accepted, unjustified ones are rejected, and the remaining ambiguities are exposed and presented to users for further analysis. After motivating the problem, we introduce our approach and illustrate it with a detailed running example introducing both well-founded and stable semantics to help understand the AF solutions. We have begun to develop open source tools and Jupyter notebooks that demonstrate the practicality of our approach. In future work we plan to develop a toolkit for conflict resolution that can be used in conjunction with OpenRefine, a popular interactive data cleaning tool.

cs.DB↗

arXiv2024

Unlocking Insights: Semantic Search in Jupyter Notebooks

Semantic search, a process aimed at delivering highly relevant search results by comprehending the searcher's intent and the contextual meaning of terms within a searchable dataspace, plays a pivotal role in information retrieval. In this paper, we investigate the application of large language models to enhance semantic search capabilities, specifically tailored for the domain of Jupyter Notebooks. Our objective is to retrieve generated outputs, such as figures or tables, associated functions and methods, and other pertinent information. We demonstrate a semantic search framework that achieves a comprehensive semantic understanding of the entire notebook's contents, enabling it to effectively handle various types of user queries. Key components of this framework include: 1). A data preprocessor is designed to handle diverse types of cells within Jupyter Notebooks, encompassing both markdown and code cells. 2). An innovative methodology is devised to address token size limitations that arise with code-type cells. We implement a finer-grained approach to data input, transitioning from the cell level to the function level, effectively resolving these issues.

cs.IR↗

arXiv2024

An objective comparison of methods for augmented reality in laparoscopic liver resection by preoperative-to-intraoperative image fusion

Augmented reality for laparoscopic liver resection is a visualisation mode that allows a surgeon to localise tumours and vessels embedded within the liver by projecting them on top of a laparoscopic image. Preoperative 3D models extracted from CT or MRI data are registered to the intraoperative laparoscopic images during this process. In terms of 3D-2D fusion, most of the algorithms make use of anatomical landmarks to guide registration. These landmarks include the liver's inferior ridge, the falciform ligament, and the occluding contours. They are usually marked by hand in both the laparoscopic image and the 3D model, which is time-consuming and may contain errors if done by a non-experienced user. Therefore, there is a need to automate this process so that augmented reality can be used effectively in the operating room. We present the Preoperative-to-Intraoperative Laparoscopic Fusion Challenge (P2ILF), held during the Medical Imaging and Computer Assisted Interventions (MICCAI 2022) conference, which investigates the possibilities of detecting these landmarks automatically and using them in registration. The challenge was divided into two tasks: 1) A 2D and 3D landmark detection task and 2) a 3D-2D registration task. The teams were provided with training data consisting of 167 laparoscopic images and 9 preoperative 3D models from 9 patients, with the corresponding 2D and 3D landmark annotations. A total of 6 teams from 4 countries participated, whose proposed methods were evaluated on 16 images and two preoperative 3D models from two patients. All the teams proposed deep learning-based methods for the 2D and 3D landmark segmentation tasks and differentiable rendering-based methods for the registration task. Based on the experimental outcomes, we propose three key hypotheses that determine current limitations and future directions for research in this domain.

cs.CV↗

arXiv2023

Twice Class Bias Correction for Imbalanced Semi-Supervised Learning

Differing from traditional semi-supervised learning, class-imbalanced semi-supervised learning presents two distinct challenges: (1) The imbalanced distribution of training samples leads to model bias towards certain classes, and (2) the distribution of unlabeled samples is unknown and potentially distinct from that of labeled samples, which further contributes to class bias in the pseudo-labels during training. To address these dual challenges, we introduce a novel approach called \textbf{T}wice \textbf{C}lass \textbf{B}ias \textbf{C}orrection (\textbf{TCBC}). We begin by utilizing an estimate of the class distribution from the participating training samples to correct the model, enabling it to learn the posterior probabilities of samples under a class-balanced prior. This correction serves to alleviate the inherent class bias of the model. Building upon this foundation, we further estimate the class bias of the current model parameters during the training process. We apply a secondary correction to the model's pseudo-labels for unlabeled samples, aiming to make the assignment of pseudo-labels across different classes of unlabeled samples as equitable as possible. Through extensive experimentation on CIFAR10/100-LT, STL10-LT, and the sizable long-tailed dataset SUN397, we provide conclusive evidence that our proposed TCBC method reliably enhances the performance of class-imbalanced semi-supervised learning.

cs.LG↗

arXiv2023

CLAF: Contrastive Learning with Augmented Features for Imbalanced Semi-Supervised Learning

Due to the advantages of leveraging unlabeled data and learning meaningful representations, semi-supervised learning and contrastive learning have been progressively combined to achieve better performances in popular applications with few labeled data and abundant unlabeled data. One common manner is assigning pseudo-labels to unlabeled samples and selecting positive and negative samples from pseudo-labeled samples to apply contrastive learning. However, the real-world data may be imbalanced, causing pseudo-labels to be biased toward the majority classes and further undermining the effectiveness of contrastive learning. To address the challenge, we propose Contrastive Learning with Augmented Features (CLAF). We design a class-dependent feature augmentation module to alleviate the scarcity of minority class samples in contrastive learning. For each pseudo-labeled sample, we select positive and negative samples from labeled data instead of unlabeled data to compute contrastive loss. Comprehensive experiments on imbalanced image classification datasets demonstrate the effectiveness of CLAF in the context of imbalanced semi-supervised learning.

cs.CV↗

arXiv2023

"Zero change" platform for monolithic back-end-of-line integration of phase change materials in silicon photonics

Monolithic integration of novel materials for unprecedented device functions without modifying the existing photonic component library is the key to advancing heterogeneous silicon photonic integrated circuits. To achieve this, the introduction of a silicon nitride etching stop layer at selective area, coupled with low-loss oxide trench to waveguide surface, enables the incorporation of various functional materials without disrupting the reliability of foundry-verified devices. As an illustration, two distinct chalcogenide phase change materials (PCM) with remarkable nonvolatile modulation capabilities, namely Sb2Se3 and Ge2Sb2Se4Te1, were monolithic back-end-of-line integrated into silicon photonics. The PCM enables compact phase and intensity tuning units with zero-static power consumption. Taking advantage of these building blocks, the phase error of a push-pull Mach-Zehnder interferometer optical switch could be trimmed by a nonvolatile phase shifter with a 48% peak power consumption reduction. Mirco-ring filters with a rejection ratio >25dB could be applied for >5-bit wavelength selective intensity modulation, and waveguide-based >7-bit intensity-modulation photonic attenuators could achieve >39dB broadband attenuation. The advanced "Zero change" back-end-of-line integration platform could not only facilitate the integration of PCMs for integrated reconfigurable photonics but also open up the possibilities for integrating other excellent optoelectronic materials in the future silicon photonic process design kits.

physics.optics↗

arXiv2023

Graphene/silicon heterojunction for reconfigurable phase-relevant activation function in coherent optical neural networks

Optical neural networks (ONNs) herald a new era in information and communication technologies and have implemented various intelligent applications. In an ONN, the activation function (AF) is a crucial component determining the network performances and on-chip AF devices are still in development. Here, we first demonstrate on-chip reconfigurable AF devices with phase activation fulfilled by dual-functional graphene/silicon (Gra/Si) heterojunctions. With optical modulation and detection in one device, time delays are shorter, energy consumption is lower, reconfigurability is higher and the device footprint is smaller than other on-chip AF strategies. The experimental modulation voltage (power) of our Gra/Si heterojunction achieves as low as 1 V (0.5 mW), superior to many pure silicon counterparts. In the photodetection aspect, a high responsivity of over 200 mA/W is realized. Special nonlinear functions generated are fed into a complex-valued ONN to challenge handwritten letters and image recognition tasks, showing improved accuracy and potential of high-efficient, all-component-integration on-chip ONN. Our results offer new insights for on-chip ONN devices and pave the way to high-performance integrated optoelectronic computing circuits.

physics.optics↗

arXiv2023

KAER: A Knowledge Augmented Pre-Trained Language Model for Entity Resolution

Entity resolution has been an essential and well-studied task in data cleaning research for decades. Existing work has discussed the feasibility of utilizing pre-trained language models to perform entity resolution and achieved promising results. However, few works have discussed injecting domain knowledge to improve the performance of pre-trained language models on entity resolution tasks. In this study, we propose Knowledge Augmented Entity Resolution (KAER), a novel framework named for augmenting pre-trained language models with external knowledge for entity resolution. We discuss the results of utilizing different knowledge augmentation and prompting methods to improve entity resolution performance. Our model improves on Ditto, the existing state-of-the-art entity resolution method. In particular, 1) KAER performs more robustly and achieves better results on "dirty data", and 2) with more general knowledge injection, KAER outperforms the existing baseline models on the textual dataset and dataset from the online product domain. 3) KAER achieves competitive results on highly domain-specific datasets, such as citation datasets, requiring the injection of expert knowledge in future work.

cs.CL↗

arXiv2022

Optimal Boxes: Boosting End-to-End Scene Text Recognition by Adjusting Annotated Bounding Boxes via Reinforcement Learning

Text detection and recognition are essential components of a modern OCR system. Most OCR approaches attempt to obtain accurate bounding boxes of text at the detection stage, which is used as the input of the text recognition stage. We observe that when using tight text bounding boxes as input, a text recognizer frequently fails to achieve optimal performance due to the inconsistency between bounding boxes and deep representations of text recognition. In this paper, we propose Box Adjuster, a reinforcement learning-based method for adjusting the shape of each text bounding box to make it more compatible with text recognition models. Additionally, when dealing with cross-domain problems such as synthetic-to-real, the proposed method significantly reduces mismatches in domain distribution between the source and target domains. Experiments demonstrate that the performance of end-to-end text recognition systems can be improved when using the adjusted bounding boxes as the ground truths for training. Specifically, on several benchmark datasets for scene text understanding, the proposed method outperforms state-of-the-art text spotters by an average of 2.0% F-Score on end-to-end text recognition tasks and 4.6% F-Score on domain adaptation tasks.

cs.CV↗

arXiv2022

Preliminary Steps Towards Federated Sentiment Classification

Automatically mining sentiment tendency contained in natural language is a fundamental research to some artificial intelligent applications, where solutions alternate with challenges. Transfer learning and multi-task learning techniques have been leveraged to mitigate the supervision sparsity and collaborate multiple heterogeneous domains correspondingly. Recent years, the sensitive nature of users' private data raises another challenge for sentiment classification, i.e., data privacy protection. In this paper, we resort to federated learning for multiple domain sentiment classification under the constraint that the corpora must be stored on decentralized devices. In view of the heterogeneous semantics across multiple parties and the peculiarities of word embedding, we pertinently provide corresponding solutions. First, we propose a Knowledge Transfer Enhanced Private-Shared (KTEPS) framework for better model aggregation and personalization in federated sentiment classification. Second, we propose KTEPS$^\star$ with the consideration of the rich semantic and huge embedding size properties of word vectors, utilizing Projection-based Dimension Reduction (PDR) methods for privacy protection and efficient transmission simultaneously. We propose two federated sentiment classification scenes based on public benchmarks, and verify the superiorities of our proposed methods with abundant experimental investigations.

cs.CL↗

arXiv2021

or2yw: Modeling and Visualizing OpenRefineHistories as YesWorkflow Diagrams

OpenRefine is a popular open-source data cleaning tool. It allows users to export a previously executed data cleaning workflow in a JSON format for possible reuse on other datasets. We have developed or2yw, a novel tool that maps a JSON-formatted OpenRefine operation history to a YesWorkflow (YW) model, which then can be visualized and queried using the YW tool. The latter was originally developed to allow researchers a simple way to annotate their program scripts in order to reveal the workflow steps and dataflow dependencies implicit in those scripts. With or2yw the user can automatically generate YW models from OpenRefine operation histories, thus providing a 'workflow view' on a previously executed sequence of data cleaning operations. The or2yw tool can generate different types of YesWorkflow models, e.g., a linear model which mirrors the sequential execution order of operations in OpenRefine, and a \emph{parallel model} which reveals independent workflow branches, based on a simple analysis of dependencies between steps: if two operations are independent of each other (e.g., when the columns they read and write do not overlap) then these can be viewed as parallel steps in the data cleaning workflow. The resulting YW models can be understood as a form of prospective provenance, i.e., knowledge artifacts that can be queried and visualized (i) to help authors document their own data cleaning workflows, thereby increasing transparency, and (ii) to help other users, who might want to reuse such workflows, to understand them better.

cs.DB↗

arXiv2020

I-BERT: Inductive Generalization of Transformer to Arbitrary Context Lengths

Self-attention has emerged as a vital component of state-of-the-art sequence-to-sequence models for natural language processing in recent years, brought to the forefront by pre-trained bi-directional Transformer models. Its effectiveness is partly due to its non-sequential architecture, which promotes scalability and parallelism but limits the model to inputs of a bounded length. In particular, such architectures perform poorly on algorithmic tasks, where the model must learn a procedure which generalizes to input lengths unseen in training, a capability we refer to as inductive generalization. Identifying the computational limits of existing self-attention mechanisms, we propose I-BERT, a bi-directional Transformer that replaces positional encodings with a recurrent layer. The model inductively generalizes on a variety of algorithmic tasks where state-of-the-art Transformer models fail to do so. We also test our method on masked language modeling tasks where training and validation sets are partitioned to verify inductive generalization. Out of three algorithmic and two natural language inductive generalization tasks, I-BERT achieves state-of-the-art results on four tasks.

cs.LG↗

arXiv2018

High-Q mid-infrared chalcogenide glass resonators

In this letter, we fabricated and characterized chalcogenide glass resonators monolithically integrated on mid-infrared transparent CaF2 substrates. The devices feature an intrinsic Q-factor of 4E5 at 5.2 micron wavelength, which represents the highest Q-factor reported in planar mid-infrared resonators. It is found that moisture can significantly impact the device performance when the device was exposed to an ambient environment, although the high-Q characteristics can be restored after undergoing an annealing treatment. Using these devices, we further demonstrated on-chip cavity-enhanced spectroscopy to quantify mid-IR absorption of ethanol solutions around 5.2 micron wavelength.

cond-mat.mtrl-sci↗

arXiv2017

Chalcogenide Glass-on-Graphene Photonics

Two-dimensional (2-D) materials are of tremendous interest to integrated photonics given their singular optical characteristics spanning light emission, modulation, saturable absorption, and nonlinear optics. To harness their optical properties, these atomically thin materials are usually attached onto prefabricated devices via a transfer process. In this paper, we present a new route for 2-D material integration with planar photonics. Central to this approach is the use of chalcogenide glass, a multifunctional material which can be directly deposited and patterned on a wide variety of 2-D materials and can simultaneously function as the light guiding medium, a gate dielectric, and a passivation layer for 2-D materials. Besides claiming improved fabrication yield and throughput compared to the traditional transfer process, our technique also enables unconventional multilayer device geometries optimally designed for enhancing light-matter interactions in the 2-D layers. Capitalizing on this facile integration method, we demonstrate a series of high-performance glass-on-graphene devices including ultra-broadband on-chip polarizers, energy-efficient thermo-optic switches, as well as graphene-based mid-infrared (mid-IR) waveguide-integrated photodetectors and modulators.

physics.optics↗

arXiv2016

Phase retrieval from multiple-window short-time Fourier measurements

In this paper, we introduce two symmetric directed graphs depending on supports of signals and windows, and we show that the connectivity of those graphs provides either necessary and sufficient conditions to phase retrieval of a signal from magnitude measurements of its multiple-window short-time Fourier transform. Also we propose an algebraic reconstruction algorithm, and provide an error estimate to our algorithm when magnitude measurements are corrupted by deterministic/random noises.

cs.IT↗

arXiv2013

High-Performance, High-Index-Contrast Chalcogenide Glass Photonics on Silicon and Unconventional Non-planar Substrates

This paper reports a versatile, roll-to-roll and backend compatible technique for the fabrication of high-index-contrast photonic structures on both silicon and plastic substrates. The fabrication technique combines low-temperature chalcogenide glass film deposition and resist-free single-step thermal nanoimprint to process low-loss (1.6 dB/cm), sub-micron single-mode waveguides with a smooth surface finish using simple contact photolithography. Using this approach, the first chalcogenide glass micro-ring resonators are fabricated by thermal nanoimprint. The devices exhibit an ultra-high quality-factor of 400,000 near 1550 nm wavelength, which represents the highest value reported in chalcogenide glass micro-ring resonators. Furthermore, sub-micron nanoimprint of chalcogenide glass films on non-planar plastic substrates is demonstrated, which establishes the method as a facile route for monolithic fabrication of high-index-contrast devices on a wide array of unconventional substrates.

physics.optics↗

arXiv2013

3-D Integrated Flexible Glass Photonics

Photonic integration on plastic substrates enables emerging applications ranging from flexible interconnects to conformal sensors on biological tissues. Such devices are traditionally fabricated using pattern transfer, which is complicated and has limited integration capacity. Here we pioneered a monolithic approach to realize flexible, high-index-contrast glass photonics with significantly improved processing throughput and yield. Noting that the conventional multilayer bending theory fails when laminates have large elastic mismatch, we derived a mechanics theory accounting for multiple neutral axes in one laminated structure to accurately predict its strain-optical coupling behavior. Through combining monolithic fabrication and local neutral axis designs, we fabricated devices that boast record optical performance (Q=460,000) and excellent mechanical flexibility enabling repeated bending down to sub-millimeter radius without measurable performance degradation, both of which represent major improvements over state-of-the-art. Further, we demonstrate that our technology offers a facile fabrication route for 3-D high-index-contrast photonics difficult to process using traditional methods.

physics.optics↗