arXiv subjects

Si Chen

Publications and source records attributed to Si Chen.

At least 73 records · Page 4Linked to original sources

arXiv2024

Inclusive Emotion Technologies: Addressing the Needs of d/Deaf and Hard of Hearing Learners in Video-Based Learning

Accessibility efforts for d/Deaf and hard of hearing (DHH) learners in video-based learning have mainly focused on captions and interpreters, with limited attention to learners' emotional awareness--an important yet challenging skill for effective learning. Current emotion technologies are designed to support learners' emotional awareness and social needs; however, little is known about whether and how DHH learners could benefit from these technologies. Our study explores how DHH learners perceive and use emotion data from two collection approaches, self-reported and automatic emotion recognition (AER), in video-based learning. By comparing the use of these technologies between DHH (N=20) and hearing learners (N=20), we identified key differences in their usage and perceptions: 1) DHH learners enhanced their emotional awareness by rewatching the video to self-report their emotions and called for alternative methods for self-reporting emotion, such as using sign language or expressive emoji designs; and 2) while the AER technology could be useful for detecting emotional patterns in learning experiences, DHH learners expressed more concerns about the accuracy and intrusiveness of the AER data. Our findings provide novel design implications for improving the inclusiveness of emotion technologies to support DHH learners, such as leveraging DHH peer learners' emotions to elicit reflections.

cs.HC↗

arXiv2024

The 2nd FutureDial Challenge: Dialog Systems with Retrieval Augmented Generation (FutureDial-RAG)

Recently, increasing research interests have focused on retrieval augmented generation (RAG) to mitigate hallucination for large language models (LLMs). Following this trend, we launch the FutureDial-RAG challenge at SLT 2024, which aims at promoting the study of RAG for dialog systems. The challenge builds upon the MobileCS2 dataset, a real-life customer service datasets with nearly 3000 high-quality dialogs containing annotations for knowledge base query and corresponding results. Over the dataset, we define two tasks, track 1 for knowledge retrieval and track 2 for response generation, which are core research questions in dialog systems with RAG. We build baseline systems for the two tracks and design metrics to measure whether the systems can perform accurate retrieval and generate informative and coherent response. The baseline results show that it is very challenging to perform well on the two tasks, which encourages the participating teams and the community to study how to make better use of RAG for real-life dialog systems.

cs.CL↗

arXiv2024

Towards reliable respiratory disease diagnosis based on cough sounds and vision transformers

Recent advancements in deep learning techniques have sparked performance boosts in various real-world applications including disease diagnosis based on multi-modal medical data. Cough sound data-based respiratory disease (e.g., COVID-19 and Chronic Obstructive Pulmonary Disease) diagnosis has also attracted much attention. However, existing works usually utilise traditional machine learning or deep models of moderate scales. On the other hand, the developed approaches are trained and evaluated on small-scale data due to the difficulty of curating and annotating clinical data on scale. To address these issues in prior works, we create a unified framework to evaluate various deep models from lightweight Convolutional Neural Networks (e.g., ResNet18) to modern vision transformers and compare their performance in respiratory disease classification. Based on the observations from such an extensive empirical study, we propose a novel approach to cough-based disease classification based on both self-supervised and supervised learning on a large-scale cough data set. Experimental results demonstrate our proposed approach outperforms prior arts consistently on two benchmark datasets for COVID-19 diagnosis and a proprietary dataset for COPD/non-COPD classification with an AUROC of 92.5%.

cs.CV↗

arXiv2024

Suppression of Coherent Synchrotron Radiation-Induced Emittance Growth in a Multi-Bend Deflection Line

Preserving beam quality during the transportation of high-brightness electron beams is a significant and widespread challenge in the design of modern accelerators. The importance of this issue stems from the fact that the quality of the beam at the accelerator's output is crucial for various applications, including particle colliders, free-electron lasers, and synchrotron radiation sources. The coherent synchrotron radiation (CSR) effect can degrade beam quality when a bunch is deflected. Therefore, developing a structure that effectively suppresses the CSR effect, especially for the short bunches is critically important. This involves protecting both the transverse emittance and the longitudinal profile to ensure the production of a high-quality beam. In this study, an optimization based on the reverse lattice of the beamline is proposed. This method can simplify the optimization process. Based on this approach, the Quadruple Bend Achromat (QBA) deflection structure has been designed and optimized. Then we have derived a general solution to completely suppress the impact of steady-state CSR on the transverse plane for different topologies of QBA. Furthermore, a general condition is proposed for suppressing displacements caused by CSR in sequence drifts for isochronous structures. Simultaneously, QBA has proven to be the simplest structure that can simultaneously suppress both types of CSR effects. Simulation results for bunches with a peak current of up to $3000A$ show almost no change in transverse emittance for a large angle deflection.

physics.acc-ph↗

arXiv2024

FASTTRACK: Fast and Accurate Fact Tracing for LLMs

Fact tracing seeks to identify specific training examples that serve as the knowledge source for a given query. Existing approaches to fact tracing rely on assessing the similarity between each training sample and the query along a certain dimension, such as lexical similarity, gradient, or embedding space. However, these methods fall short of effectively distinguishing between samples that are merely relevant and those that actually provide supportive evidence for the information sought by the query. This limitation often results in suboptimal effectiveness. Moreover, these approaches necessitate the examination of the similarity of individual training points for each query, imposing significant computational demands and creating a substantial barrier for practical applications. This paper introduces FASTTRACK, a novel approach that harnesses the capabilities of Large Language Models (LLMs) to validate supportive evidence for queries and at the same time clusters the training database towards a reduced extent for LLMs to trace facts. Our experiments show that FASTTRACK substantially outperforms existing methods in both accuracy and efficiency, achieving more than 100\% improvement in F1 score over the state-of-the-art methods while being X33 faster than \texttt{TracIn}.

cs.CL↗

arXiv2024

Towards Inclusive Video Commenting: Introducing Signmaku for the Deaf and Hard-of-Hearing

Previous research underscored the potential of danmaku--a text-based commenting feature on videos--in engaging hearing audiences. Yet, for many Deaf and hard-of-hearing (DHH) individuals, American Sign Language (ASL) takes precedence over English. To improve inclusivity, we introduce "Signmaku," a new commenting mechanism that uses ASL, serving as a sign language counterpart to danmaku. Through a need-finding study (N=12) and a within-subject experiment (N=20), we evaluated three design styles: real human faces, cartoon-like figures, and robotic representations. The results showed that cartoon-like signmaku not only entertained but also encouraged participants to create and share ASL comments, with fewer privacy concerns compared to the other designs. Conversely, the robotic representations faced challenges in accurately depicting hand movements and facial expressions, resulting in higher cognitive demands on users. Signmaku featuring real human faces elicited the lowest cognitive load and was the most comprehensible among all three types. Our findings offered novel design implications for leveraging generative AI to create signmaku comments, enriching co-learning experiences for DHH individuals.

cs.HC↗

arXiv2024

CoQuest: Exploring Research Question Co-Creation with an LLM-based Agent

Developing novel research questions (RQs) often requires extensive literature reviews, especially in interdisciplinary fields. To support RQ development through human-AI co-creation, we leveraged Large Language Models (LLMs) to build an LLM-based agent system named CoQuest. We conducted an experiment with 20 HCI researchers to examine the impact of two interaction designs: breadth-first and depth-first RQ generation. The findings revealed that participants perceived the breadth-first approach as more creative and trustworthy upon task completion. Conversely, during the task, participants considered the depth-first generated RQs as more creative. Additionally, we discovered that AI processing delays allowed users to reflect on multiple RQs simultaneously, leading to a higher quantity of generated RQs and an enhanced sense of control. Our work makes both theoretical and practical contributions by proposing and evaluating a mental model for human-AI co-creation of RQs. We also address potential ethical issues, such as biases and over-reliance on AI, advocating for using the system to improve human research creativity rather than automating scientific inquiry.

cs.HC↗

arXiv2024

StaPep: an open-source tool for the structure prediction and feature extraction of hydrocarbon-stapled peptides

Many tools exist for extracting structural and physiochemical descriptors from linear peptides to predict their properties, but similar tools for hydrocarbon-stapled peptides are lacking.Here, we present StaPep, a Python-based toolkit designed for generating 2D/3D structures and calculating 21 distinct features for hydrocarbon-stapled peptides.The current version supports hydrocarbon-stapled peptides containing 2 non-standard amino acids (norleucine and 2-aminoisobutyric acid) and 6 nonnatural anchoring residues (S3, S5, S8, R3, R5 and R8).Then we established a hand-curated dataset of 201 hydrocarbon-stapled peptides and 384 linear peptides with sequence information and experimental membrane permeability, to showcase StaPep's application in artificial intelligence projects.A machine learning-based predictor utilizing above calculated features was developed with AUC of 0.85, for identifying cell-penetrating hydrocarbon-stapled peptides.StaPep's pipeline spans data retrieval, cleaning, structure generation, molecular feature calculation, and machine learning model construction for hydrocarbon-stapled peptides.The source codes and dataset are freely available on Github: https://github.com/dahuilangda/stapep_package.

q-bio.BM↗

arXiv2023

High-Order Structure Based Middle-Feature Learning for Visible-Infrared Person Re-Identification

Visible-infrared person re-identification (VI-ReID) aims to retrieve images of the same persons captured by visible (VIS) and infrared (IR) cameras. Existing VI-ReID methods ignore high-order structure information of features while being relatively difficult to learn a reasonable common feature space due to the large modality discrepancy between VIS and IR images. To address the above problems, we propose a novel high-order structure based middle-feature learning network (HOS-Net) for effective VI-ReID. Specifically, we first leverage a short- and long-range feature extraction (SLE) module to effectively exploit both short-range and long-range features. Then, we propose a high-order structure learning (HSL) module to successfully model the high-order relationship across different local features of each person image based on a whitened hypergraph network.This greatly alleviates model collapse and enhances feature representations. Finally, we develop a common feature space learning (CFL) module to learn a discriminative and reasonable common feature space based on middle features generated by aligning features from different modalities and ranges. In particular, a modality-range identity-center contrastive (MRIC) loss is proposed to reduce the distances between the VIS, IR, and middle features, smoothing the training process. Extensive experiments on the SYSU-MM01, RegDB, and LLCM datasets show that our HOS-Net achieves superior state-of-the-art performance. Our code is available at \url{https://github.com/Jaulaucoeng/HOS-Net}.

cs.CV↗

arXiv2023

Delivery of nanosecond laser pulses by multimode anti-resonant hollow core fiber at 1 um wavelength

In this paper we explore the application of low-loss multimode anti-resonant hollow-core fiber (MM-AR-HCF) in the delivery of nanosecond laser pulses at 1 um wavelength. MM-AR-HCF of large core offers a rich content of low-loss higher-order modes which plays a key role in the efficient coupling and transmission of high-power laser of degraded beam quality. In the experiment, laser pulses of an average pulse energy of 21.8 mJ with 14.6 ns pulse width (corresponding a peak power of 1.49 MW) are transmitted through MM-AR-HCF of 9.8 m length without damaging. Up to 94 % coupling efficiency is achieved where the incident laser beam suffers a degraded beam quality with and of 2.18 and 1.99 respectively. Laser-induced damage threshold (LIDT) of MM-AR-HCF measures 22.6 mJ for 94 % coupling efficiency, which is 7 times higher than that for multimode silica optical fiber with a core diameter of 200 um.

physics.optics↗

arXiv2023

Learning to Rank for Active Learning via Multi-Task Bilevel Optimization

Active learning is a promising paradigm to reduce the labeling cost by strategically requesting labels to improve model performance. However, existing active learning methods often rely on expensive acquisition function to compute, extensive modeling retraining and multiple rounds of interaction with annotators. To address these limitations, we propose a novel approach for active learning, which aims to select batches of unlabeled instances through a learned surrogate model for data acquisition. A key challenge in this approach is developing an acquisition function that generalizes well, as the history of data, which forms part of the utility function's input, grows over time. Our novel algorithmic contribution is a bilevel multi-task bilevel optimization framework that predicts the relative utility -- measured by the validation accuracy -- of different training sets, and ensures the learned acquisition function generalizes effectively. For cases where validation accuracy is expensive to evaluate, we introduce efficient interpolation-based surrogate models to estimate the utility function, reducing the evaluation cost. We demonstrate the performance of our approach through extensive experiments on standard active classification benchmarks. By employing our learned utility function, we show significant improvements over traditional techniques, paving the way for more efficient and effective utility maximization in active learning applications.

cs.LG↗

arXiv2023

Heralded three-photon entanglement from a single-photon source on a photonic chip

In the quest to build general-purpose photonic quantum computers, fusion-based quantum computation has risen to prominence as a promising strategy. This model allows a ballistic construction of large cluster states which are universal for quantum computation, in a scalable and loss-tolerant way without feed-forward, by fusing many small n-photon entangled resource states. However, a key obstacle to this architecture lies in efficiently generating the required essential resource states on photonic chips. One such critical seed state that has not yet been achieved is the heralded three-photon Greenberger-Horne-Zeilinger (3-GHZ) state. Here, we address this elementary resource gap, by reporting the first experimental realization of a heralded dual-rail encoded 3-GHZ state. Our implementation employs a low-loss and fully programmable photonic chip that manipulates six indistinguishable single photons of wavelengths in the telecommunication regime. Conditional on the heralding detection, we obtain the desired 3-GHZ state with a fidelity 0.573+-0.024. Our work marks an important step for the future fault-tolerant photonic quantum computing, leading to the acceleration of building a large-scale optical quantum computer.

quant-ph↗

arXiv2023

Multi-Scenario Ranking with Adaptive Feature Learning

Recently, Multi-Scenario Learning (MSL) is widely used in recommendation and retrieval systems in the industry because it facilitates transfer learning from different scenarios, mitigating data sparsity and reducing maintenance cost. These efforts produce different MSL paradigms by searching more optimal network structure, such as Auxiliary Network, Expert Network, and Multi-Tower Network. It is intuitive that different scenarios could hold their specific characteristics, activating the user's intents quite differently. In other words, different kinds of auxiliary features would bear varying importance under different scenarios. With more discriminative feature representations refined in a scenario-aware manner, better ranking performance could be easily obtained without expensive search for the optimal network structure. Unfortunately, this simple idea is mainly overlooked but much desired in real-world systems.Further analysis also validates the rationality of adaptive feature learning under a multi-scenario scheme. Moreover, our A/B test results on the Alibaba search advertising platform also demonstrate that Maria is superior in production environments.

cs.IR↗

arXiv2023

Turning a Curse into a Blessing: Enabling In-Distribution-Data-Free Backdoor Removal via Stabilized Model Inversion

Many backdoor removal techniques in machine learning models require clean in-distribution data, which may not always be available due to proprietary datasets. Model inversion techniques, often considered privacy threats, can reconstruct realistic training samples, potentially eliminating the need for in-distribution data. Prior attempts to combine backdoor removal and model inversion yielded limited results. Our work is the first to provide a thorough understanding of leveraging model inversion for effective backdoor removal by addressing key questions about reconstructed samples' properties, perceptual similarity, and the potential presence of backdoor triggers. We establish that relying solely on perceptual similarity is insufficient for robust defenses, and the stability of model predictions in response to input and parameter perturbations is also crucial. To tackle this, we introduce a novel bi-level optimization-based framework for model inversion, promoting stability and visual quality. Interestingly, we discover that reconstructed samples from a pre-trained generator's latent space are backdoor-free, even when utilizing signals from a backdoored model. We provide a theoretical analysis to support this finding. Our evaluation demonstrates that our stabilized model inversion technique achieves state-of-the-art backdoor removal performance without clean in-distribution data, matching or surpassing performance using the same amount of clean samples.

cs.CV↗

arXiv2023

Rationalizing the influence of tunable energy levels on quantum efficiency to design optimal non-fullerene acceptor-based ternary organic solar cells

Non-fullerene acceptor (NFA)-based ternary bulk heterojunction solar cells (TSC) are the most efficient organic solar cells (OSCs) today due to their broader absorption and quantum efficiencies (QE) often surpassing those of corresponding binary blends. We study how the energetics driving charge transfer at the electron donor:electron acceptor (D/A) interfaces impact the QE in blends of PBDB-T-2F donor with several pairs of lower bandgap NFAs. As in binary blends, the ionization energy offset between donor and acceptor (ΔIE) controls the QE and maximizes for ΔIE > 0.5 eV. However, ΔIE is not controlled by the individual NFAs IEs but by their average, weighted for their blending ratio. Using this property, we improved the QE of a PBDB-T-2F:IEICO binary blend that had an insufficient ΔIE for charge generation by adding a deep IE third component: IT-4F. Combining two NFAs enables to optimize the D/A energy alignment and cells' QE without molecular engineering.

physics.app-ph↗

arXiv2022

ModelPred: A Framework for Predicting Trained Model from Training Data

In this work, we propose ModelPred, a framework that helps to understand the impact of changes in training data on a trained model. This is critical for building trust in various stages of a machine learning pipeline: from cleaning poor-quality samples and tracking important ones to be collected during data preparation, to calibrating uncertainty of model prediction, to interpreting why certain behaviors of a model emerge during deployment. Specifically, ModelPred learns a parameterized function that takes a dataset $S$ as the input and predicts the model obtained by training on $S$. Our work differs from the recent work of Datamodels [1] as we aim for predicting the trained model parameters directly instead of the trained model behaviors. We demonstrate that a neural network-based set function class is capable of learning the complex relationships between the training data and model parameters. We introduce novel global and local regularization techniques to prevent overfitting and we rigorously characterize the expressive power of neural networks (NN) in approximating the end-to-end training process. Through extensive empirical investigations, we show that ModelPred enables a variety of applications that boost the interpretability and accountability of machine learning (ML), such as data valuation, data selection, memorization quantification, and model calibration.

cs.LG↗

arXiv2022

Just Fine-tune Twice: Selective Differential Privacy for Large Language Models

Protecting large language models from privacy leakage is becoming increasingly crucial with their wide adoption in real-world products. Yet applying differential privacy (DP), a canonical notion with provable privacy guarantees for machine learning models, to those models remains challenging due to the trade-off between model utility and privacy loss. Utilizing the fact that sensitive information in language data tends to be sparse, Shi et al. (2021) formalized a DP notion extension called Selective Differential Privacy (SDP) to protect only the sensitive tokens defined by a policy function. However, their algorithm only works for RNN-based models. In this paper, we develop a novel framework, Just Fine-tune Twice (JFT), that achieves SDP for state-of-the-art large transformer-based models. Our method is easy to implement: it first fine-tunes the model with redacted in-domain data, and then fine-tunes it again with the original in-domain data using a private training mechanism. Furthermore, we study the scenario of imperfect implementation of policy functions that misses sensitive tokens and develop systematic methods to handle it. Experiments show that our method achieves strong utility compared to previous baselines. We also analyze the SDP privacy guarantee empirically with the canary insertion attack.

cs.CL↗

arXiv2022

Quantitative elemental imaging in eukaryotic algae

All organisms, fundamentally, are made from the same raw material, namely the elements of the periodic table. Biochemical diversity is achieved with how these elements are utilized, for what purpose and in which physical location. Determining elemental distributions, especially those of trace elements that facilitate metabolism as cofactors in the active centers of essential enzymes, can determine the state of metabolism, the nutritional status or the developmental stage of an organism. Photosynthetic eukaryotes, especially algae, are excellent subjects for quantitative analysis of elemental distribution. These microbes utilize unique metabolic pathways that require various trace nutrients at their core to enable its operation. Photosynthetic microbes also have important environmental roles as primary producers in habitats with limited nutrient supply or toxin contaminations. Accordingly, photosynthetic eukaryotes are of great interest for biotechnological exploitation, carbon sequestration and bioremediation, with many of the applications involving various trace elements and consequently affecting their quota and intracellular distribution. A number of diverse applications were developed for elemental imaging allowing subcellular resolution, with X-ray fluorescence microscopy (XFM) being at the forefront, enabling quantitative descriptions of intact cells in a non-destructive method. This Tutorial Review summarizes the workflow of a quantitative, single-cell elemental distribution analysis of a eukaryotic alga using XFM.

q-bio.SC↗