Showing 1–50 of 89 results for author: Lee, J Y

Deep Learning-based Surrogate Modelling of the LOD Method for Multiscale Problems

Authors: Marc Haltmayer, Jaemin Seo, Yuseung Lee, Sungyeop Lee, Jaehoon Jeong, Jae Yong Lee

Abstract: Multiscale problems are notoriously difficult to tackle using traditional numerical methods, as accurately resolving fine-scale features often requires prohibitively fine discretizations. This challenge is particularly pronounced in applications such as materials science, fluid dynamics, climate systems, chemical processes, and complex networks. Recent neural operator models provide a promising da… ▽ More Multiscale problems are notoriously difficult to tackle using traditional numerical methods, as accurately resolving fine-scale features often requires prohibitively fine discretizations. This challenge is particularly pronounced in applications such as materials science, fluid dynamics, climate systems, chemical processes, and complex networks. Recent neural operator models provide a promising data-driven alternative, but frequently struggle to achieve sufficient accuracy in the presence of strongly heterogeneous or oscillatory coefficients. In this work, we focus on the solution of elliptic PDEs with rough and high-contrast inputs. The Localized Orthogonal Decomposition (LOD) method is a well-established numerical approach for such problems, but it comes, however, at a substantial computational cost. We investigate the performance of popular neural operator architectures on these challenging multiscale problems and identify key limitations in their ability to resolve fine-scale structure. To overcome these challenges, we introduce LOD-MSNO (LOD-Multiscale Neural Operator), a hybrid approach that leverages the LOD method as a strong multiscale prior by building on its representation of the solution as a linear combination of problem-adapted basis functions, while addressing its main computational bottlenecks through data-driven operator learning. We further provide theoretical error estimates for the proposed coefficient-learning framework. Lastly, we demonstrate the potential of our proposed method to outperform current neural operator baselines in terms of accuracy for challenging multiscale inputs, while mainly retaining the computational efficiency of neural operator models. △ Less

Submitted 14 July, 2026; originally announced July 2026.

Comments: 56 pages, 4 figures

MSC Class: 65N30; 65M60; 76S05; 65N55; 68T20; 68U07

EHRNote-ChatQA: A Benchmark for Evidence-Grounded Multi-Turn Clinical Question Answering over Longitudinal Discharge Summaries

Authors: Jiyoun Kim, Muhan Yeo, Eunhye Jang, Jeewon Yang, Hangyul Yoon, Su Ji Lee, Hee Jo Han, Hee-Jae Jung, Doyun Kwon, Jun young Lee, Jaehun Lee, Jung-Oh Lee, Sunjun Kweon, Jong Hak Moon, Daseul Kim, Minjae Cho, Edward Choi

Abstract: Discharge summaries are crucial clinical documents containing the context of a patient's overall hospital stay, and are routinely reviewed by medical experts for patient readmission, ongoing care, and diagnostic decision-making. When reviewing them, medical experts often must iteratively synthesize information across multiple summaries while verifying the evidence supporting each answer. Although… ▽ More Discharge summaries are crucial clinical documents containing the context of a patient's overall hospital stay, and are routinely reviewed by medical experts for patient readmission, ongoing care, and diagnostic decision-making. When reviewing them, medical experts often must iteratively synthesize information across multiple summaries while verifying the evidence supporting each answer. Although large language models (LLMs) are increasingly explored for clinical question answering, existing benchmarks do not sufficiently reflect this setting: they often evaluate exam-style medical knowledge or focus on single-turn question answering with limited evidence-grounding evaluation. We introduce EHRNote-ChatQA, the first benchmark for evidence-grounded multi-turn clinical question answering over patients' multiple discharge summaries. Built from de-identified MIMIC-IV discharge summaries, EHRNote-ChatQA contains 967 patient-level multi-turn samples spanning one to five notes and 16,072 medical-expert-verified QA pairs (8,036 content questions, each paired with an evidence-grounding question) across eight clinical categories. The benchmark is constructed through an expert-informed pipeline combining discharge-summary structuring schema, expert-curated multi-turn QA templates, and LLM-based generation, followed by review and revision of every single QA sample by 11 medical experts. Benchmarking 22 open- and closed-source LLMs reveals several challenges, including that LLMs struggle more with evidence grounding than content answering, multi-turn errors compound across turns, and single-turn clinical QA performance does not reliably transfer to this setting. These findings establish EHRNote-ChatQA as a rigorous and practical benchmark for evaluating clinical QA systems. The dataset will be made publicly available through PhysioNet credentialed access. △ Less

Submitted 16 June, 2026; v1 submitted 14 June, 2026; originally announced June 2026.

Unbiased and Second-Order-Free Training for High-Dimensional PDEs

Authors: Jaemin Seo, Surin Lee, Jae Yong Lee

Abstract: Deep learning methods based on backward stochastic differential equations (BSDEs) have emerged as competitive alternatives to physics-informed neural networks (PINNs) for solving high-dimensional partial differential equations (PDEs). By leveraging probabilistic representations, BSDE approaches can avoid the curse of dimensionality and often admit second-order-free training objectives that do not… ▽ More Deep learning methods based on backward stochastic differential equations (BSDEs) have emerged as competitive alternatives to physics-informed neural networks (PINNs) for solving high-dimensional partial differential equations (PDEs). By leveraging probabilistic representations, BSDE approaches can avoid the curse of dimensionality and often admit second-order-free training objectives that do not require explicit Hessian evaluations. It has recently been established that the commonly used Euler-Maruyama (EM) time discretization induces an intrinsic bias in BSDE training losses. While high-order schemes such as Heun can fully eliminate this bias, such schemes re-introduce second-order spatial derivatives and incur substantial computational overhead. In this work, we provide a principled analysis of EM-induced loss bias and propose an unbiased, second-order-free training framework that preserves the computational advantages of BSDE methods. Our code is available at https://github.com/seojaemin22/Un-EM-BSDE. △ Less

Submitted 14 May, 2026; originally announced May 2026.

Comments: Accepted at ICML 2026

MSC Class: 65C30; 68TO7

Journal ref: International Conference on Machine Learning 2026

Discovering Ordinary Differential Equations with LLM-Based Qualitative and Quantitative Evaluation

Authors: Sum Kyun Song, Bong Gyun Shin, Jae Yong Lee

Abstract: Discovering governing differential equations from observational data is a fundamental challenge in scientific machine learning. Existing symbolic regression approaches rely primarily on quantitative metrics; however, real-world differential equation modeling also requires incorporating domain knowledge to ensure physical plausibility. To address this gap, we propose DoLQ, a method for discovering… ▽ More Discovering governing differential equations from observational data is a fundamental challenge in scientific machine learning. Existing symbolic regression approaches rely primarily on quantitative metrics; however, real-world differential equation modeling also requires incorporating domain knowledge to ensure physical plausibility. To address this gap, we propose DoLQ, a method for discovering ordinary differential equations with LLM-based qualitative and quantitative evaluation. DoLQ employs a multi-agent architecture: a Sampler Agent proposes dynamic system candidates, a Parameter Optimizer refines equations for accuracy, and a Scientist Agent leverages an LLM to conduct both qualitative and quantitative evaluations and synthesize their results to iteratively guide the search. Experiments on multi-dimensional ordinary differential equation benchmarks demonstrate that DoLQ achieves superior performance compared to existing methods, not only attaining higher success rates but also more accurately recovering the correct symbolic terms of ground truth equations. Our code is available at https://github.com/Bon99yun/DoLQ. △ Less

Submitted 15 July, 2026; v1 submitted 8 May, 2026; originally announced May 2026.

Comments: Accepted at ICML 2026

MSC Class: 68T01

Journal ref: International Conference on Machine Learning 2026

DiSCo: Diffusion Sequence Copilots for Shared Autonomy

Authors: Andy Wang, Xu Yan, Brandon McMahan, Michael Zhou, Yuyang Yuan, Johannes Y. Lee, Ali Shreif, Matthew Li, Zhenghao Peng, Bolei Zhou, Yuchen Cui, Jonathan C. Kao

Abstract: Shared autonomy combines human user and AI copilot actions to control complex systems such as robotic arms. When a task is challenging, requires high dimensional control, or is subject to corruption, shared autonomy can significantly increase task performance by using a trained copilot to effectively correct user actions in a manner consistent with the user's goals. To significantly improve the pe… ▽ More Shared autonomy combines human user and AI copilot actions to control complex systems such as robotic arms. When a task is challenging, requires high dimensional control, or is subject to corruption, shared autonomy can significantly increase task performance by using a trained copilot to effectively correct user actions in a manner consistent with the user's goals. To significantly improve the performance of shared autonomy, we introduce Diffusion Sequence Copilots (DiSCo): a method of shared autonomy with diffusion policy that plans action sequences consistent with past user actions. DiSCo seeds and inpaints the diffusion process with user-provided actions with hyperparameters to balance conformity to expert actions, alignment with user intent, and perceived responsiveness. We demonstrate that DiSCo substantially improves task performance in simulated driving and robotic arm tasks. Project website: https://sites.google.com/view/disco-shared-autonomy/ △ Less

Submitted 10 August, 2026; v1 submitted 24 March, 2026; originally announced March 2026.

Comments: 10 pages, 5 figures, HRI '26: Proceedings of the 21st ACM/IEEE International Conference on Human-Robot Interaction

GRAFITE: Generative Regression Analysis Framework for Issue Tracking and Evaluation

Authors: Ja Young Lee, Mírian Silva, Mohamed Nasr, Shonda Witherspoon, Enzo Bozzani, Veronique Demers, Radha Ratnaparkhi, Hui Wu, Sara Rosenthal

Abstract: Large language models (LLMs) are largely motivated by their performance on popular topics and benchmarks at the time of their release. However, over time, contamination occurs due to significant exposure of benchmark data during training. This poses a risk of model performance inflation if testing is not carefully executed. To address this challenge, we present GRAFITE, a continuous LLM evaluation… ▽ More Large language models (LLMs) are largely motivated by their performance on popular topics and benchmarks at the time of their release. However, over time, contamination occurs due to significant exposure of benchmark data during training. This poses a risk of model performance inflation if testing is not carefully executed. To address this challenge, we present GRAFITE, a continuous LLM evaluation platform through a comprehensive system for maintaining and evaluating model issues. Our approach enables building a repository of model problems based on user feedback over time and offers a pipeline for assessing LLMs against these issues through quality assurance (QA) tests using LLM-as-a-judge. The platform enables side-by-side comparison of multiple models, facilitating regression detection across different releases. The platform is available at https://github.com/IBM/grafite. The demo video is available at www.youtube.com/watch?v=XFZyoleN56k. △ Less

Submitted 18 March, 2026; originally announced March 2026.

Comments: 7 pages, 2 figures

Ego-1K -- A Large-Scale Multiview Video Dataset for Egocentric Vision

Authors: Jae Yong Lee, Daniel Scharstein, Akash Bapat, Hao Hu, Andrew Fu, Haoru Zhao, Paul Sammut, Xiang Li, Stephen Jeapes, Anik Gupta, Lior David, Saketh Madhuvarasu, Jay Girish Joshi, Jason Wither

Abstract: We present Ego-1K, a large-scale collection of time-synchronized egocentric multiview videos designed to advance neural 3D video synthesis and dynamic scene understanding. The dataset contains nearly 1,000 short egocentric videos captured with a custom rig with 12 synchronized cameras surrounding a 4-camera VR headset worn by the user. Scene content focuses on hand motions and hand-object interact… ▽ More We present Ego-1K, a large-scale collection of time-synchronized egocentric multiview videos designed to advance neural 3D video synthesis and dynamic scene understanding. The dataset contains nearly 1,000 short egocentric videos captured with a custom rig with 12 synchronized cameras surrounding a 4-camera VR headset worn by the user. Scene content focuses on hand motions and hand-object interactions in different settings. We describe rig design, data processing, and calibration. Our dataset enables new ways to benchmark egocentric scene reconstruction methods, an important research area as smart glasses with multiple cameras become omnipresent. Our experiments demonstrate that our dataset presents unique challenges for existing 3D and 4D novel view synthesis methods due to large disparities and image motion caused by close dynamic objects and rig egomotion. Our dataset supports future research in this challenging domain. It is available at https://huggingface.co/datasets/facebook/ego-1k. △ Less

Submitted 14 March, 2026; originally announced March 2026.

Comments: To appear in CVPR 2026

QMAVIS: Long Video-Audio Understanding using Fusion of Large Multimodal Models

Authors: Zixing Lin, Jiale Wang, Gee Wah Ng, Lee Onn Mak, Chan Zhi Yang Jeriel, Jun Yang Lee, Yaohao Li

Abstract: Large Multimodal Models (LMMs) for video-audio understanding have traditionally been evaluated only on shorter videos of a few minutes long. In this paper, we introduce QMAVIS (Q Team-Multimodal Audio Video Intelligent Sensemaking), a novel long video-audio understanding pipeline built through a late fusion of LMMs, Large Language Models, and speech recognition models. QMAVIS addresses the gap in… ▽ More Large Multimodal Models (LMMs) for video-audio understanding have traditionally been evaluated only on shorter videos of a few minutes long. In this paper, we introduce QMAVIS (Q Team-Multimodal Audio Video Intelligent Sensemaking), a novel long video-audio understanding pipeline built through a late fusion of LMMs, Large Language Models, and speech recognition models. QMAVIS addresses the gap in long-form video analytics, particularly for longer videos of a few minutes to beyond an hour long, opening up new potential applications in sensemaking, video content analysis, embodied AI, etc. Quantitative experiments using QMAVIS demonstrated a 38.75% improvement over state-of-the-art video-audio LMMs like VideoLlaMA2 and InternVL2 on the VideoMME (with subtitles) dataset, which comprises long videos with audio information. Evaluations on other challenging video understanding datasets like PerceptionTest and EgoSchema saw up to 2% improvement, indicating competitive performance. Qualitative experiments also showed that QMAVIS is able to extract the nuances of different scenes in a long video audio content while understanding the overarching narrative. Ablation studies were also conducted to ascertain the impact of each component in the fusion pipeline. △ Less

Submitted 10 January, 2026; originally announced January 2026.

Discontinuous Galerkin finite element operator network for solving non-smooth PDEs

Authors: Kapil Chawla, Youngjoon Hong, Jae Yong Lee, Sanghyun Lee

Abstract: We introduce Discontinuous Galerkin Finite Element Operator Network (DG--FEONet), a data-free operator learning framework that combines the strengths of the discontinuous Galerkin (DG) method with neural networks to solve parametric partial differential equations (PDEs) with discontinuous coefficients and non-smooth solutions. Unlike traditional operator learning models such as DeepONet and Fourie… ▽ More We introduce Discontinuous Galerkin Finite Element Operator Network (DG--FEONet), a data-free operator learning framework that combines the strengths of the discontinuous Galerkin (DG) method with neural networks to solve parametric partial differential equations (PDEs) with discontinuous coefficients and non-smooth solutions. Unlike traditional operator learning models such as DeepONet and Fourier Neural Operator, which require large paired datasets and often struggle near sharp features, our approach minimizes the residual of a DG-based weak formulation using the Symmetric Interior Penalty Galerkin (SIPG) scheme. DG-FEONet predicts element-wise solution coefficients via a neural network, enabling data-free training without the need for precomputed input-output pairs. We provide theoretical justification through convergence analysis and validate the model's performance on a series of one- and two-dimensional PDE problems, demonstrating accurate recovery of discontinuities, strong generalization across parameter space, and reliable convergence rates. Our results highlight the potential of combining local discretization schemes with machine learning to achieve robust, singularity-aware operator approximation in challenging PDE settings. △ Less

Submitted 7 January, 2026; originally announced January 2026.

Comments: 24 pages, 11 figures

MSC Class: 65M60; 65N30; 68T20; 68U07 ACM Class: G.1.8

From Correctness to Collaboration: Toward a Human-Centered Framework for Evaluating AI Agent Behavior in Software Engineering

Authors: Tao Dong, Harini Sampath, Ja Young Lee, Sherry Y. Shi, Andrew Macvean

Abstract: As Large Language Models (LLMs) evolve from code generators into collaborative partners for software engineers, our methods for evaluation are lagging. Current benchmarks, focused on code correctness, fail to capture the nuanced, interactive behaviors essential for successful human-AI partnership. To bridge this evaluation gap, this paper makes two core contributions. First, we present a foundatio… ▽ More As Large Language Models (LLMs) evolve from code generators into collaborative partners for software engineers, our methods for evaluation are lagging. Current benchmarks, focused on code correctness, fail to capture the nuanced, interactive behaviors essential for successful human-AI partnership. To bridge this evaluation gap, this paper makes two core contributions. First, we present a foundational taxonomy of desirable agent behaviors for enterprise software engineering, derived from an analysis of 91 sets of user-defined agent rules. This taxonomy defines four key expectations of agent behavior: Adhere to Standards and Processes, Ensure Code Quality and Reliability, Solving Problems Effectively, and Collaborating with the User. Second, recognizing that these expectations are not static, we introduce the Context-Adaptive Behavior (CAB) Framework. This emerging framework reveals how behavioral expectations shift along two empirically-derived axes: the Time Horizon (from immediate needs to future ideals), established through interviews with 15 expert engineers, and the Type of Work (from enterprise production to rapid prototyping, for example), identified through a prompt analysis of a prototyping agent. Together, these contributions offer a human-centered foundation for designing and evaluating the next generation of AI agents, moving the field's focus from the correctness of generated code toward the dynamics of true collaborative intelligence. △ Less

Submitted 29 December, 2025; originally announced December 2025.

Comparative Evaluation of Generative AI Models for Chest Radiograph Report Generation in the Emergency Department

Authors: Woo Hyeon Lim, Ji Young Lee, Jong Hyuk Lee, Saehoon Kim, Hyungjin Kim

Abstract: Purpose: To benchmark open-source or commercial medical image-specific VLMs against real-world radiologist-written reports. Methods: This retrospective study included adult patients who presented to the emergency department between January 2022 and April 2025 and underwent same-day CXR and CT for febrile or respiratory symptoms. Reports from five VLMs (AIRead, Lingshu, MAIRA-2, MedGemma, and MedVe… ▽ More Purpose: To benchmark open-source or commercial medical image-specific VLMs against real-world radiologist-written reports. Methods: This retrospective study included adult patients who presented to the emergency department between January 2022 and April 2025 and underwent same-day CXR and CT for febrile or respiratory symptoms. Reports from five VLMs (AIRead, Lingshu, MAIRA-2, MedGemma, and MedVersa) and radiologist-written reports were randomly presented and blindly evaluated by three thoracic radiologists using four criteria: RADPEER, clinical acceptability, hallucination, and language clarity. Comparative performance was assessed using generalized linear mixed models, with radiologist-written reports treated as the reference. Finding-level analyses were also performed with CT as the reference. Results: A total of 478 patients (median age, 67 years [interquartile range, 50-78]; 282 men [59.0%]) were included. AIRead demonstrated the lowest RADPEER 3b rate (5.3% [76/1434] vs. radiologists 13.9% [200/1434]; P<.001), whereas other VLMs showed higher disagreement rates (16.8-43.0%; P<.05). Clinical acceptability was the highest with AIRead (84.5% [1212/1434] vs. radiologists 74.3% [1065/1434]; P<.001), while other VLMs performed worse (41.1-71.4%; P<.05). Hallucinations were rare with AIRead, comparable to radiologists (0.3% [4/1425]) vs. 0.1% [1/1425]; P=.21), but frequent with other models (5.4-17.4%; P<.05). Language clarity was higher with AIRead (82.9% [1189/1434]), Lingshu (88.0% [1262/1434]), and MedVersa (88.4% [1268/1434]) compared with radiologists (78.1% [1120/1434]; P<.05). Sensitivity varied substantially across VLMs for the common findings: AIRead, 15.5-86.7%; Lingshu, 2.4-86.7%; MAIRA-2, 6.0-72.0%; MedGemma, 4.8-76.7%; and MedVersa, 20.2-69.3%. Conclusion: Medical VLMs for CXR report generation exhibited variable performance in report quality and diagnostic measures. △ Less

Submitted 28 November, 2025; originally announced December 2025.

LowKeyEMG: Electromyographic typing with a reduced keyset

Authors: Johannes Y. Lee, Derek Xiao, Shreyas Kaasyap, Nima R. Hadidi, John L. Zhou, Jacob Cunningham, Rakshith R. Gore, Deniz O. Eren, Jonathan C. Kao

Abstract: We introduce LowKeyEMG, a real-time human-computer interface that enables efficient text entry using only 7 gesture classes decoded from surface electromyography (sEMG). Prior work has attempted full-alphabet decoding from sEMG, but decoding large character sets remains unreliable, especially for individuals with motor impairments. Instead, LowKeyEMG reduces the English alphabet to 4 gesture keys,… ▽ More We introduce LowKeyEMG, a real-time human-computer interface that enables efficient text entry using only 7 gesture classes decoded from surface electromyography (sEMG). Prior work has attempted full-alphabet decoding from sEMG, but decoding large character sets remains unreliable, especially for individuals with motor impairments. Instead, LowKeyEMG reduces the English alphabet to 4 gesture keys, with 3 more for space and system interaction, to reliably translate simple one-handed gestures into text, leveraging the recurrent transformer-based language model RWKV for efficient computation. In real-time experiments, participants achieved average one-handed keyboardless typing speeds of 23.3 words per minute with LowKeyEMG, and improved gesture efficiency by 17% (relative to typed phrase length). When typing with only 7 keys, LowKeyEMG can achieve 98.2% top-3 word accuracy, demonstrating that this low-key typing paradigm can maintain practical communication rates. Our results have implications for assistive technologies and any interface where input bandwidth is constrained. △ Less

Submitted 25 July, 2025; originally announced July 2025.

Comments: 11+3 pages, 5 main figures, 2 supplementary tables, 4 supplementary figures

DMQ: Dissecting Outliers of Diffusion Models for Post-Training Quantization

Authors: Dongyeun Lee, Jiwan Hur, Hyounguk Shon, Jae Young Lee, Junmo Kim

Abstract: Diffusion models have achieved remarkable success in image generation but come with significant computational costs, posing challenges for deployment in resource-constrained environments. Recent post-training quantization (PTQ) methods have attempted to mitigate this issue by focusing on the iterative nature of diffusion models. However, these approaches often overlook outliers, leading to degrade… ▽ More Diffusion models have achieved remarkable success in image generation but come with significant computational costs, posing challenges for deployment in resource-constrained environments. Recent post-training quantization (PTQ) methods have attempted to mitigate this issue by focusing on the iterative nature of diffusion models. However, these approaches often overlook outliers, leading to degraded performance at low bit-widths. In this paper, we propose a DMQ which combines Learned Equivalent Scaling (LES) and channel-wise Power-of-Two Scaling (PTS) to effectively address these challenges. Learned Equivalent Scaling optimizes channel-wise scaling factors to redistribute quantization difficulty between weights and activations, reducing overall quantization error. Recognizing that early denoising steps, despite having small quantization errors, crucially impact the final output due to error accumulation, we incorporate an adaptive timestep weighting scheme to prioritize these critical steps during learning. Furthermore, identifying that layers such as skip connections exhibit high inter-channel variance, we introduce channel-wise Power-of-Two Scaling for activations. To ensure robust selection of PTS factors even with small calibration set, we introduce a voting algorithm that enhances reliability. Extensive experiments demonstrate that our method significantly outperforms existing works, especially at low bit-widths such as W4A6 (4-bit weight, 6-bit activation) and W4A8, maintaining high image generation quality and model stability. The code is available at https://github.com/LeeDongYeun/dmq. △ Less

Submitted 17 July, 2025; originally announced July 2025.

Comments: Accepted by ICCV 2025

DocTalk: Scalable Graph-based Dialogue Synthesis for Enhancing LLM Conversational Capabilities

Authors: Jing Yang Lee, Hamed Bonab, Nasser Zalmout, Ming Zeng, Sanket Lokegaonkar, Colin Lockard, Binxuan Huang, Ritesh Sarkhel, Haodong Wang

Abstract: Large Language Models (LLMs) are increasingly employed in multi-turn conversational tasks, yet their pre-training data predominantly consists of continuous prose, creating a potential mismatch between required capabilities and training paradigms. We introduce a novel approach to address this discrepancy by synthesizing conversational data from existing text corpora. We present a pipeline that tran… ▽ More Large Language Models (LLMs) are increasingly employed in multi-turn conversational tasks, yet their pre-training data predominantly consists of continuous prose, creating a potential mismatch between required capabilities and training paradigms. We introduce a novel approach to address this discrepancy by synthesizing conversational data from existing text corpora. We present a pipeline that transforms a cluster of multiple related documents into an extended multi-turn, multi-topic information-seeking dialogue. Applying our pipeline to Wikipedia articles, we curate DocTalk, a multi-turn pre-training dialogue corpus consisting of over 730k long conversations. We hypothesize that exposure to such synthesized conversational structures during pre-training can enhance the fundamental multi-turn capabilities of LLMs, such as context memory and understanding. Empirically, we show that incorporating DocTalk during pre-training results in up to 40% gain in context memory and understanding, without compromising base performance. DocTalk is available at https://huggingface.co/datasets/AmazonScience/DocTalk. △ Less

Submitted 8 July, 2025; originally announced July 2025.

Comments: Accepted at SIGDIAL 2025

Modeling the One-to-Many Property in Open-Domain Dialogue with LLMs

Authors: Jing Yang Lee, Kong-Aik Lee, Woon-Seng Gan

Abstract: Open-domain Dialogue (OD) exhibits a one-to-many (o2m) property, whereby multiple appropriate responses exist for a single dialogue context. Despite prior research showing that modeling this property boosts response diversity, most modern LLM-based dialogue agents do not explicitly do so. In this work, we model the o2m property of OD in LLMs by decomposing OD generation into two key tasks: Multi-R… ▽ More Open-domain Dialogue (OD) exhibits a one-to-many (o2m) property, whereby multiple appropriate responses exist for a single dialogue context. Despite prior research showing that modeling this property boosts response diversity, most modern LLM-based dialogue agents do not explicitly do so. In this work, we model the o2m property of OD in LLMs by decomposing OD generation into two key tasks: Multi-Response Generation (MRG) and Preference-based Selection (PS), which entail generating a set of n semantically and lexically diverse high-quality responses for a given dialogue context, followed by selecting a single response based on human preference, respectively. To facilitate MRG and PS, we introduce o2mDial, a dialogue corpus explicitly designed to capture the o2m property by featuring multiple plausible responses for each context. Leveraging o2mDial, we propose new in-context learning and instruction-tuning strategies, as well as novel evaluation metrics for MRG, alongside a model-based approach for PS. Empirical results demonstrate that applying the proposed two-stage framework to smaller LLMs for OD generation enhances overall response diversity while maintaining contextual coherence, improving response quality by up to 90%, bringing them closer to the performance of larger models. △ Less

Submitted 2 January, 2026; v1 submitted 18 June, 2025; originally announced June 2025.

6G communications through sub-Terahertz CMOS power amplifiers: Design challenges and trends

Authors: Jun Yan Lee, Duo Wu, Xuanrui Guo, Jian Ding Tan, Teh Jia Yew, Zi Neng Ng, Mohammad Arif Sobhan Bhuiyan, Mahdi H. Miraz

Abstract: The fifth-generation (5G) network faces limitations in supporting emerging applications, such as artificial intelligence (AI), virtual reality (VR) and digital twins. To overcome these confines, sub-Terahertz (sub-THz) and Terahertz (THz) technologies are considered to be key enablers of effective 6G wireless communications, offering higher transmission speeds, longer range and wider bandwidth. Ac… ▽ More The fifth-generation (5G) network faces limitations in supporting emerging applications, such as artificial intelligence (AI), virtual reality (VR) and digital twins. To overcome these confines, sub-Terahertz (sub-THz) and Terahertz (THz) technologies are considered to be key enablers of effective 6G wireless communications, offering higher transmission speeds, longer range and wider bandwidth. Achieving these capabilities requires careful engineering of 6G transceivers, with a focus on efficient power amplifiers (PAs) in the front-end, which play a critical role in effectively amplifying and transmitting signals over long distances. Complimentary metal-oxidesemiconductor (CMOS) technology-based PA in sub-THz suffers severe parasitic and limited maximum frequency, however, this has eventually been solved by different design architectures and scaling down of CMOS technology to break through the frequency limitations. In this article, we reviewed the potentials and capabilities of CMOS technology for designing 6G hardware, identified the state-of-art PA designs in the sub-THz band and then examined as well as compared the designs to identify the suitable design strategies for better performance. The circuit optimisation techniques, such as coupled-line, passive gain boosting method, zero-degree power splitting, load-pull matching, diode and capacitor linearisation for better gain, saturated output power and power added efficiency, are considered for the PA design architectures at different sub-THz bands. Furthermore, these methods are summarised and discussed with their advantages and disadvantages in lieu with their performances. The PA design trends, challenges and future perspectives are also presented and discussed. Therefore, this comprehensive review article will serve as a comparative study and reference for future PA designs for radio frequency integrated circuits (RFIC). △ Less

Submitted 19 May, 2025; originally announced May 2025.

Journal ref: Heliyon, vol. 11, no. 11, May 2025

FourierSpecNet: Neural Collision Operator Approximation Inspired by the Fourier Spectral Method for Solving the Boltzmann Equation

Authors: Jae Yong Lee, Gwang Jae Jung, Byung Chan Lim, Hyung Ju Hwang

Abstract: The Boltzmann equation, a fundamental model in kinetic theory, describes the evolution of particle distribution functions through a nonlinear, high-dimensional collision operator. However, its numerical solution remains computationally demanding, particularly for inelastic collisions and high-dimensional velocity domains. In this work, we propose the Fourier Neural Spectral Network (FourierSpecNet… ▽ More The Boltzmann equation, a fundamental model in kinetic theory, describes the evolution of particle distribution functions through a nonlinear, high-dimensional collision operator. However, its numerical solution remains computationally demanding, particularly for inelastic collisions and high-dimensional velocity domains. In this work, we propose the Fourier Neural Spectral Network (FourierSpecNet), a hybrid framework that integrates the Fourier spectral method with deep learning to approximate the collision operator in Fourier space efficiently. FourierSpecNet achieves resolution-invariant learning and supports zero-shot super-resolution, enabling accurate predictions at unseen resolutions without retraining. Beyond empirical validation, we establish a consistency result showing that the trained operator converges to the spectral solution as the discretization is refined. We evaluate our method on several benchmark cases, including Maxwellian and hard-sphere molecular models, as well as inelastic collision scenarios. The results demonstrate that FourierSpecNet offers competitive accuracy while significantly reducing computational cost compared to traditional spectral solvers. Our approach provides a robust and scalable alternative for solving the Boltzmann equation across both elastic and inelastic regimes. △ Less

Submitted 6 March, 2026; v1 submitted 29 April, 2025; originally announced April 2025.

Comments: 37 pages, 17 figures

MSC Class: 68T20; 35Q20; 35B40; 82C40

Toward building next-generation Geocoding systems: a systematic review

Authors: Zhengcong Yin, Daniel W. Goldberg, Binbin Lin, Bing Zhou, Diya Li, Andong Ma, Ziqian Ming, Heng Cai, Zhe Zhang, Shaohua Wang, Shanzhen Gao, Joey Ying Lee, Xiao Li, Da Huo

Abstract: Geocoding systems are widely used in both scientific research for spatial analysis and everyday life through location-based services. The quality of geocoded data significantly impacts subsequent processes and applications, underscoring the need for next-generation systems. In response to this demand, this review first characterizes the technical requirements for next-generation geocoding inputs a… ▽ More Geocoding systems are widely used in both scientific research for spatial analysis and everyday life through location-based services. The quality of geocoded data significantly impacts subsequent processes and applications, underscoring the need for next-generation systems. In response to this demand, this review first characterizes the technical requirements for next-generation geocoding inputs and outputs. We then decompose the geocoding workflow into modular functional units and survey existing implementations. For each component, we identify methodological limitations, articulate domain-specific research questions and hypotheses, and outline evaluation strategies needed. Finally, we identify opportunities to improve next-generation geocoding systems in light of recent technological advances. We envision that this review provides a technical foundation and research agenda for advancing the design, assessment, and deployment of next-generation geocoding systems. △ Less

Submitted 25 December, 2025; v1 submitted 24 March, 2025; originally announced March 2025.

Predictive Prompt Analysis

Authors: Jae Yong Lee, Sungmin Kang, Shin Yoo

Abstract: Large Language Models (LLMs) are machine learning models that have seen widespread adoption due to their capability of handling previously difficult tasks. LLMs, due to their training, are sensitive to how exactly a question is presented, also known as prompting. However, prompting well is challenging, as it has been difficult to uncover principles behind prompting -- generally, trial-and-error is… ▽ More Large Language Models (LLMs) are machine learning models that have seen widespread adoption due to their capability of handling previously difficult tasks. LLMs, due to their training, are sensitive to how exactly a question is presented, also known as prompting. However, prompting well is challenging, as it has been difficult to uncover principles behind prompting -- generally, trial-and-error is the most common way of improving prompts, despite its significant computational cost. In this context, we argue it would be useful to perform `predictive prompt analysis', in which an automated technique would perform a quick analysis of a prompt and predict how the LLM would react to it, relative to a goal provided by the user. As a demonstration of the concept, we present Syntactic Prevalence Analyzer (SPA), a predictive prompt analysis approach based on sparse autoencoders (SAEs). SPA accurately predicted how often an LLM would generate target syntactic structures during code synthesis, with up to 0.994 Pearson correlation between the predicted and actual prevalence of the target structure. At the same time, SPA requires only 0.4\% of the time it takes to run the LLM on a benchmark. As LLMs are increasingly used during and integrated into modern software development, our proposed predictive prompt analysis concept has the potential to significantly ease the use of LLMs for both practitioners and researchers. △ Less

Submitted 13 March, 2025; v1 submitted 30 January, 2025; originally announced January 2025.

Comments: Accepted by FSE 2025, 5 pages, 2 figures

Redefining Proactivity for Information Seeking Dialogue

Authors: Jing Yang Lee, Seokhwan Kim, Kartik Mehta, Jiun-Yu Kao, Yu-Hsiang Lin, Arpit Gupta

Abstract: Information-Seeking Dialogue (ISD) agents aim to provide accurate responses to user queries. While proficient in directly addressing user queries, these agents, as well as LLMs in general, predominantly exhibit reactive behavior, lacking the ability to generate proactive responses that actively engage users in sustained conversations. However, existing definitions of proactive dialogue in this con… ▽ More Information-Seeking Dialogue (ISD) agents aim to provide accurate responses to user queries. While proficient in directly addressing user queries, these agents, as well as LLMs in general, predominantly exhibit reactive behavior, lacking the ability to generate proactive responses that actively engage users in sustained conversations. However, existing definitions of proactive dialogue in this context do not focus on how each response actively engages the user and sustains the conversation. Hence, we present a new definition of proactivity that focuses on enhancing the `proactiveness' of each generated response via the introduction of new information related to the initial query. To this end, we construct a proactive dialogue dataset comprising 2,000 single-turn conversations, and introduce several automatic metrics to evaluate response `proactiveness' which achieved high correlation with human annotation. Additionally, we introduce two innovative Chain-of-Thought (CoT) prompts, the 3-step CoT and the 3-in-1 CoT prompts, which consistently outperform standard prompts by up to 90% in the zero-shot setting. △ Less

Submitted 17 November, 2024; v1 submitted 20 October, 2024; originally announced October 2024.

Development of Image Collection Method Using YOLO and Siamese Network

Authors: Chan Young Shin, Ah Hyun Lee, Jun Young Lee, Ji Min Lee, Soo Jin Park

Abstract: As we enter the era of big data, collecting high-quality data is very important. However, collecting data by humans is not only very time-consuming but also expensive. Therefore, many scientists have devised various methods to collect data using computers. Among them, there is a method called web crawling, but the authors found that the crawling method has a problem in that unintended data is coll… ▽ More As we enter the era of big data, collecting high-quality data is very important. However, collecting data by humans is not only very time-consuming but also expensive. Therefore, many scientists have devised various methods to collect data using computers. Among them, there is a method called web crawling, but the authors found that the crawling method has a problem in that unintended data is collected along with the user. The authors found that this can be filtered using the object recognition model YOLOv10. However, there are cases where data that is not properly filtered remains. Here, image reclassification was performed by additionally utilizing the distance output from the Siamese network, and higher performance was recorded than other classification models. (average \_f1 score YOLO+MobileNet 0.678->YOLO+SiameseNet 0.772)) The user can specify a distance threshold to adjust the balance between data deficiency and noise-robustness. The authors also found that the Siamese network can achieve higher performance with fewer resources because the cropped images are used for object recognition when processing images in the Siamese network. (Class 20 mean-based f1 score, non-crop+Siamese(MobileNetV3-Small) 80.94 -> crop preprocessing+Siamese(MobileNetV3-Small) 82.31) In this way, the image retrieval system that utilizes two consecutive models to reduce errors can save users' time and effort, and build better quality data faster and with fewer resources than before. △ Less

Submitted 16 October, 2024; originally announced October 2024.

Comments: 15 pages, 13 figures, 2 tables

QE-EBM: Using Quality Estimators as Energy Loss for Machine Translation

Authors: Gahyun Yoo, Jay Yoon Lee

Abstract: Reinforcement learning has shown great promise in aligning language models with human preferences in a variety of text generation tasks, including machine translation. For translation tasks, rewards can easily be obtained from quality estimation (QE) models which can generate rewards for unlabeled data. Despite its usefulness, reinforcement learning cannot exploit the gradients with respect to the… ▽ More Reinforcement learning has shown great promise in aligning language models with human preferences in a variety of text generation tasks, including machine translation. For translation tasks, rewards can easily be obtained from quality estimation (QE) models which can generate rewards for unlabeled data. Despite its usefulness, reinforcement learning cannot exploit the gradients with respect to the QE score. We propose QE-EBM, a method of employing quality estimators as trainable loss networks that can directly backpropagate to the NMT model. We examine our method on several low and high resource target languages with English as the source language. QE-EBM outperforms strong baselines such as REINFORCE and proximal policy optimization (PPO) as well as supervised fine-tuning for all target languages, especially low-resource target languages. Most notably, for English-to-Mongolian translation, our method achieves improvements of 2.5 BLEU, 7.1 COMET-KIWI, 5.3 COMET, and 6.4 XCOMET relative to the supervised baseline. △ Less

Submitted 14 October, 2024; originally announced October 2024.

SegINR: Segment-wise Implicit Neural Representation for Sequence Alignment in Neural Text-to-Speech

Authors: Minchan Kim, Myeonghun Jeong, Joun Yeop Lee, Nam Soo Kim

Abstract: We present SegINR, a novel approach to neural Text-to-Speech (TTS) that addresses sequence alignment without relying on an auxiliary duration predictor and complex autoregressive (AR) or non-autoregressive (NAR) frame-level sequence modeling. SegINR simplifies the process by converting text sequences directly into frame-level features. It leverages an optimal text encoder to extract embeddings, tr… ▽ More We present SegINR, a novel approach to neural Text-to-Speech (TTS) that addresses sequence alignment without relying on an auxiliary duration predictor and complex autoregressive (AR) or non-autoregressive (NAR) frame-level sequence modeling. SegINR simplifies the process by converting text sequences directly into frame-level features. It leverages an optimal text encoder to extract embeddings, transforming each into a segment of frame-level features using a conditional implicit neural representation (INR). This method, named segment-wise INR (SegINR), models temporal dynamics within each segment and autonomously defines segment boundaries, reducing computational costs. We integrate SegINR into a two-stage TTS framework, using it for semantic token prediction. Our experiments in zero-shot adaptive TTS scenarios demonstrate that SegINR outperforms conventional methods in speech quality with computational efficiency. △ Less

Submitted 6 October, 2024; originally announced October 2024.

Comments: This work has been submitted to the IEEE for possible publication

Plenoptic PNG: Real-Time Neural Radiance Fields in 150 KB

Authors: Jae Yong Lee, Yuqun Wu, Chuhang Zou, Derek Hoiem, Shenlong Wang

Abstract: The goal of this paper is to encode a 3D scene into an extremely compact representation from 2D images and to enable its transmittance, decoding and rendering in real-time across various platforms. Despite the progress in NeRFs and Gaussian Splats, their large model size and specialized renderers make it challenging to distribute free-viewpoint 3D content as easily as images. To address this, we h… ▽ More The goal of this paper is to encode a 3D scene into an extremely compact representation from 2D images and to enable its transmittance, decoding and rendering in real-time across various platforms. Despite the progress in NeRFs and Gaussian Splats, their large model size and specialized renderers make it challenging to distribute free-viewpoint 3D content as easily as images. To address this, we have designed a novel 3D representation that encodes the plenoptic function into sinusoidal function indexed dense volumes. This approach facilitates feature sharing across different locations, improving compactness over traditional spatial voxels. The memory footprint of the dense 3D feature grid can be further reduced using spatial decomposition techniques. This design combines the strengths of spatial hashing functions and voxel decomposition, resulting in a model size as small as 150 KB for each 3D scene. Moreover, PPNG features a lightweight rendering pipeline with only 300 lines of code that decodes its representation into standard GL textures and fragment shaders. This enables real-time rendering using the traditional GL pipeline, ensuring universal compatibility and efficiency across various platforms without additional dependencies. △ Less

Submitted 23 September, 2024; originally announced September 2024.

Hamilton-Jacobi Based Policy-Iteration via Deep Operator Learning

Authors: Jae Yong Lee, Yeoneung Kim

Abstract: The framework of deep operator network (DeepONet) has been widely exploited thanks to its capability of solving high dimensional partial differential equations. In this paper, we incorporate DeepONet with a recently developed policy iteration scheme to numerically solve optimal control problems and the corresponding Hamilton--Jacobi--Bellman (HJB) equations. A notable feature of our approach is th… ▽ More The framework of deep operator network (DeepONet) has been widely exploited thanks to its capability of solving high dimensional partial differential equations. In this paper, we incorporate DeepONet with a recently developed policy iteration scheme to numerically solve optimal control problems and the corresponding Hamilton--Jacobi--Bellman (HJB) equations. A notable feature of our approach is that once the neural network is trained, the solution to the optimal control problem and HJB equations with different terminal functions can be inferred quickly thanks to the unique feature of operator learning. Furthermore, a quantitative analysis of the accuracy of the algorithm is carried out via comparison principles of viscosity solutions. The effectiveness of the method is verified with various examples, including 10-dimensional linear quadratic regulator problems (LQRs). △ Less

Submitted 16 June, 2024; originally announced June 2024.

Comments: 24 pages, 5 figures

MSC Class: 68T20; 68U07; 35F21; 49L12; 49L25

MonoPatchNeRF: Improving Neural Radiance Fields with Patch-based Monocular Guidance

Authors: Yuqun Wu, Jae Yong Lee, Chuhang Zou, Shenlong Wang, Derek Hoiem

Abstract: The latest regularized Neural Radiance Field (NeRF) approaches produce poor geometry and view extrapolation for large scale sparse view scenes, such as ETH3D. Density-based approaches tend to be under-constrained, while surface-based approaches tend to miss details. In this paper, we take a density-based approach, sampling patches instead of individual rays to better incorporate monocular depth an… ▽ More The latest regularized Neural Radiance Field (NeRF) approaches produce poor geometry and view extrapolation for large scale sparse view scenes, such as ETH3D. Density-based approaches tend to be under-constrained, while surface-based approaches tend to miss details. In this paper, we take a density-based approach, sampling patches instead of individual rays to better incorporate monocular depth and normal estimates and patch-based photometric consistency constraints between training views and sampled virtual views. Loosely constraining densities based on estimated depth aligned to sparse points further improves geometric accuracy. While maintaining similar view synthesis quality, our approach significantly improves geometric accuracy on the ETH3D benchmark, e.g. increasing the F1@2cm score by 4x-8x compared to other regularized density-based approaches, with much lower training and inference time than other approaches. △ Less

Submitted 22 August, 2024; v1 submitted 12 April, 2024; originally announced April 2024.

Detectors for Safe and Reliable LLMs: Implementations, Uses, and Limitations

Authors: Swapnaja Achintalwar, Adriana Alvarado Garcia, Ateret Anaby-Tavor, Ioana Baldini, Sara E. Berger, Bishwaranjan Bhattacharjee, Djallel Bouneffouf, Subhajit Chaudhury, Pin-Yu Chen, Lamogha Chiazor, Elizabeth M. Daly, Kirushikesh DB, Rogério Abreu de Paula, Pierre Dognin, Eitan Farchi, Soumya Ghosh, Michael Hind, Raya Horesh, George Kour, Ja Young Lee, Nishtha Madaan, Sameep Mehta, Erik Miehling, Keerthiram Murugesan, Manish Nagireddy , et al. (13 additional authors not shown)

Abstract: Large language models (LLMs) are susceptible to a variety of risks, from non-faithful output to biased and toxic generations. Due to several limiting factors surrounding LLMs (training cost, API access, data availability, etc.), it may not always be feasible to impose direct safety constraints on a deployed model. Therefore, an efficient and reliable alternative is required. To this end, we presen… ▽ More Large language models (LLMs) are susceptible to a variety of risks, from non-faithful output to biased and toxic generations. Due to several limiting factors surrounding LLMs (training cost, API access, data availability, etc.), it may not always be feasible to impose direct safety constraints on a deployed model. Therefore, an efficient and reliable alternative is required. To this end, we present our ongoing efforts to create and deploy a library of detectors: compact and easy-to-build classification models that provide labels for various harms. In addition to the detectors themselves, we discuss a wide range of uses for these detector models - from acting as guardrails to enabling effective AI governance. We also deep dive into inherent challenges in their development and discuss future work aimed at making the detectors more reliable and broadening their scope. △ Less

Submitted 19 August, 2024; v1 submitted 9 March, 2024; originally announced March 2024.

Learning time-dependent PDE via graph neural networks and deep operator network for robust accuracy on irregular grids

Authors: Sung Woong Cho, Jae Yong Lee, Hyung Ju Hwang

Abstract: Scientific computing using deep learning has seen significant advancements in recent years. There has been growing interest in models that learn the operator from the parameters of a partial differential equation (PDE) to the corresponding solutions. Deep Operator Network (DeepONet) and Fourier Neural operator, among other models, have been designed with structures suitable for handling functions… ▽ More Scientific computing using deep learning has seen significant advancements in recent years. There has been growing interest in models that learn the operator from the parameters of a partial differential equation (PDE) to the corresponding solutions. Deep Operator Network (DeepONet) and Fourier Neural operator, among other models, have been designed with structures suitable for handling functions as inputs and outputs, enabling real-time predictions as surrogate models for solution operators. There has also been significant progress in the research on surrogate models based on graph neural networks (GNNs), specifically targeting the dynamics in time-dependent PDEs. In this paper, we propose GraphDeepONet, an autoregressive model based on GNNs, to effectively adapt DeepONet, which is well-known for successful operator learning. GraphDeepONet exhibits robust accuracy in predicting solutions compared to existing GNN-based PDE solver models. It maintains consistent performance even on irregular grids, leveraging the advantages inherited from DeepONet and enabling predictions on arbitrary grids. Additionally, unlike traditional DeepONet and its variants, GraphDeepONet enables time extrapolation for time-dependent PDE solutions. We also provide theoretical analysis of the universal approximation capability of GraphDeepONet in approximating continuous operators across arbitrary time intervals. △ Less

Submitted 12 February, 2024; originally announced February 2024.

Comments: 25 pages, 11 figures

MSC Class: 65D17; 68U07

Region-Based Representations Revisited

Authors: Michal Shlapentokh-Rothman, Ansel Blume, Yao Xiao, Yuqun Wu, Sethuraman T V, Heyi Tao, Jae Yong Lee, Wilfredo Torres, Yu-Xiong Wang, Derek Hoiem

Abstract: We investigate whether region-based representations are effective for recognition. Regions were once a mainstay in recognition approaches, but pixel and patch-based features are now used almost exclusively. We show that recent class-agnostic segmenters like SAM can be effectively combined with strong unsupervised representations like DINOv2 and used for a wide variety of tasks, including semantic… ▽ More We investigate whether region-based representations are effective for recognition. Regions were once a mainstay in recognition approaches, but pixel and patch-based features are now used almost exclusively. We show that recent class-agnostic segmenters like SAM can be effectively combined with strong unsupervised representations like DINOv2 and used for a wide variety of tasks, including semantic segmentation, object-based image retrieval, and multi-image analysis. Once the masks and features are extracted, these representations, even with linear decoders, enable competitive performance, making them well suited to applications that require custom queries. The compactness of the representation also makes it well-suited to video analysis and other problems requiring inference across many images. △ Less

Submitted 9 June, 2024; v1 submitted 4 February, 2024; originally announced February 2024.

Comments: CVPR 2024 Camera Ready; website: https://regionreps.web.illinois.edu/

Stereo-Matching Knowledge Distilled Monocular Depth Estimation Filtered by Multiple Disparity Consistency

Authors: Woonghyun Ka, Jae Young Lee, Jaehyun Choi, Junmo Kim

Abstract: In stereo-matching knowledge distillation methods of the self-supervised monocular depth estimation, the stereo-matching network's knowledge is distilled into a monocular depth network through pseudo-depth maps. In these methods, the learning-based stereo-confidence network is generally utilized to identify errors in the pseudo-depth maps to prevent transferring the errors. However, the learning-b… ▽ More In stereo-matching knowledge distillation methods of the self-supervised monocular depth estimation, the stereo-matching network's knowledge is distilled into a monocular depth network through pseudo-depth maps. In these methods, the learning-based stereo-confidence network is generally utilized to identify errors in the pseudo-depth maps to prevent transferring the errors. However, the learning-based stereo-confidence networks should be trained with ground truth (GT), which is not feasible in a self-supervised setting. In this paper, we propose a method to identify and filter errors in the pseudo-depth map using multiple disparity maps by checking their consistency without the need for GT and a training process. Experimental results show that the proposed method outperforms the previous methods and works well on various configurations by filtering out erroneous areas where the stereo-matching is vulnerable, especially such as textureless regions, occlusion boundaries, and reflective surfaces. △ Less

Submitted 22 January, 2024; v1 submitted 22 January, 2024; originally announced January 2024.

Comments: ICASSP 2024. The first two authors are equally contributed

Modeling Stereo-Confidence Out of the End-to-End Stereo-Matching Network via Disparity Plane Sweep

Authors: Jae Young Lee, Woonghyun Ka, Jaehyun Choi, Junmo Kim

Abstract: We propose a novel stereo-confidence that can be measured externally to various stereo-matching networks, offering an alternative input modality choice of the cost volume for learning-based approaches, especially in safety-critical systems. Grounded in the foundational concepts of disparity definition and the disparity plane sweep, the proposed stereo-confidence method is built upon the idea that… ▽ More We propose a novel stereo-confidence that can be measured externally to various stereo-matching networks, offering an alternative input modality choice of the cost volume for learning-based approaches, especially in safety-critical systems. Grounded in the foundational concepts of disparity definition and the disparity plane sweep, the proposed stereo-confidence method is built upon the idea that any shift in a stereo-image pair should be updated in a corresponding amount shift in the disparity map. Based on this idea, the proposed stereo-confidence method can be summarized in three folds. 1) Using the disparity plane sweep, multiple disparity maps can be obtained and treated as a 3-D volume (predicted disparity volume), like the cost volume is constructed. 2) One of these disparity maps serves as an anchor, allowing us to define a desirable (or ideal) disparity profile at every spatial point. 3) By comparing the desirable and predicted disparity profiles, we can quantify the level of matching ambiguity between left and right images for confidence measurement. Extensive experimental results using various stereo-matching networks and datasets demonstrate that the proposed stereo-confidence method not only shows competitive performance on its own but also consistent performance improvements when it is used as an input modality for learning-based stereo-confidence methods. △ Less

Submitted 22 January, 2024; v1 submitted 22 January, 2024; originally announced January 2024.

Comments: AAAI 2024. The first two authors contributed equally

Utilizing Neural Transducers for Two-Stage Text-to-Speech via Semantic Token Prediction

Authors: Minchan Kim, Myeonghun Jeong, Byoung Jin Choi, Semin Kim, Joun Yeop Lee, Nam Soo Kim

Abstract: We propose a novel text-to-speech (TTS) framework centered around a neural transducer. Our approach divides the whole TTS pipeline into semantic-level sequence-to-sequence (seq2seq) modeling and fine-grained acoustic modeling stages, utilizing discrete semantic tokens obtained from wav2vec2.0 embeddings. For a robust and efficient alignment modeling, we employ a neural transducer named token trans… ▽ More We propose a novel text-to-speech (TTS) framework centered around a neural transducer. Our approach divides the whole TTS pipeline into semantic-level sequence-to-sequence (seq2seq) modeling and fine-grained acoustic modeling stages, utilizing discrete semantic tokens obtained from wav2vec2.0 embeddings. For a robust and efficient alignment modeling, we employ a neural transducer named token transducer for the semantic token prediction, benefiting from its hard monotonic alignment constraints. Subsequently, a non-autoregressive (NAR) speech generator efficiently synthesizes waveforms from these semantic tokens. Additionally, a reference speech controls temporal dynamics and acoustic conditions at each stage. This decoupled framework reduces the training complexity of TTS while allowing each stage to focus on semantic and acoustic modeling. Our experimental results on zero-shot adaptive TTS demonstrate that our model surpasses the baseline in terms of speech quality and speaker similarity, both objectively and subjectively. We also delve into the inference speed and prosody control capabilities of our approach, highlighting the potential of neural transducers in TTS frameworks. △ Less

Submitted 2 January, 2024; originally announced January 2024.

Comments: This work has been submitted to the IEEE for possible publication

Efficient Parallel Audio Generation using Group Masked Language Modeling

Authors: Myeonghun Jeong, Minchan Kim, Joun Yeop Lee, Nam Soo Kim

Abstract: We present a fast and high-quality codec language model for parallel audio generation. While SoundStorm, a state-of-the-art parallel audio generation model, accelerates inference speed compared to autoregressive models, it still suffers from slow inference due to iterative sampling. To resolve this problem, we propose Group-Masked Language Modeling~(G-MLM) and Group Iterative Parallel Decoding~(G-… ▽ More We present a fast and high-quality codec language model for parallel audio generation. While SoundStorm, a state-of-the-art parallel audio generation model, accelerates inference speed compared to autoregressive models, it still suffers from slow inference due to iterative sampling. To resolve this problem, we propose Group-Masked Language Modeling~(G-MLM) and Group Iterative Parallel Decoding~(G-IPD) for efficient parallel audio generation. Both the training and sampling schemes enable the model to synthesize high-quality audio with a small number of iterations by effectively modeling the group-wise conditional dependencies. In addition, our model employs a cross-attention-based architecture to capture the speaker style of the prompt voice and improves computational efficiency. Experimental results demonstrate that our proposed model outperforms the baselines in prompt-based audio generation. △ Less

Submitted 2 January, 2024; originally announced January 2024.

Comments: This work has been submitted to the IEEE for possible publication

HyperDeepONet: learning operator with complex target function space using the limited resources via hypernetwork

Authors: Jae Yong Lee, Sung Woong Cho, Hyung Ju Hwang

Abstract: Fast and accurate predictions for complex physical dynamics are a significant challenge across various applications. Real-time prediction on resource-constrained hardware is even more crucial in real-world problems. The deep operator network (DeepONet) has recently been proposed as a framework for learning nonlinear mappings between function spaces. However, the DeepONet requires many parameters a… ▽ More Fast and accurate predictions for complex physical dynamics are a significant challenge across various applications. Real-time prediction on resource-constrained hardware is even more crucial in real-world problems. The deep operator network (DeepONet) has recently been proposed as a framework for learning nonlinear mappings between function spaces. However, the DeepONet requires many parameters and has a high computational cost when learning operators, particularly those with complex (discontinuous or non-smooth) target functions. This study proposes HyperDeepONet, which uses the expressive power of the hypernetwork to enable the learning of a complex operator with a smaller set of parameters. The DeepONet and its variant models can be thought of as a method of injecting the input function information into the target function. From this perspective, these models can be viewed as a particular case of HyperDeepONet. We analyze the complexity of DeepONet and conclude that HyperDeepONet needs relatively lower complexity to obtain the desired accuracy for operator learning. HyperDeepONet successfully learned various operators with fewer computational resources compared to other benchmarks. △ Less

Submitted 26 December, 2023; originally announced December 2023.

Comments: 26 pages, 13 figures. Published as a conference paper at Eleventh International Conference on Learning Representations (ICLR 2023)

MSC Class: 65D17; 68U07

Regional profile of questionable publishing

Authors: Taekho You, Jinseo Park, June Young Lee, Jinhyuk Yun

Abstract: Countries and authors in the academic periphery occasionally have been criticized for contributing to the expansion of questionable publishing because they share a major fraction of papers in questionable journals. On the other side, topics preferred by mainstream journals sometimes necessitate large-scale investigation, which is impossible for developing countries. Thus, local journals, commonly… ▽ More Countries and authors in the academic periphery occasionally have been criticized for contributing to the expansion of questionable publishing because they share a major fraction of papers in questionable journals. On the other side, topics preferred by mainstream journals sometimes necessitate large-scale investigation, which is impossible for developing countries. Thus, local journals, commonly low-impacted, are essential to sustain the regional academia for such countries. In this study, we perform an in-depth analysis of the distribution of questionable publications and journals with their interplay with countries quantifying the influence of questionable publications regarding academia's inequality. We find that low-impact journals play a vital role in the regional academic environment, whereas questionable journals with equivalent impact publish papers from all over the world, both geographically and academically. The business model of questionable journals differs from that of regional journals, and may thus be detrimental to the broader academic community. △ Less

Submitted 2 February, 2025; v1 submitted 12 December, 2023; originally announced December 2023.

Comments: 13 pages, 4 figures, supplementary information with 8 SI figures

Few-Shot Anomaly Detection with Adversarial Loss for Robust Feature Representations

Authors: Jae Young Lee, Wonjun Lee, Jaehyun Choi, Yongkwi Lee, Young Seog Yoon

Abstract: Anomaly detection is a critical and challenging task that aims to identify data points deviating from normal patterns and distributions within a dataset. Various methods have been proposed using a one-class-one-model approach, but these techniques often face practical problems such as memory inefficiency and the requirement of sufficient data for training. In particular, few-shot anomaly detection… ▽ More Anomaly detection is a critical and challenging task that aims to identify data points deviating from normal patterns and distributions within a dataset. Various methods have been proposed using a one-class-one-model approach, but these techniques often face practical problems such as memory inefficiency and the requirement of sufficient data for training. In particular, few-shot anomaly detection presents significant challenges in industrial applications, where limited samples are available before mass production. In this paper, we propose a few-shot anomaly detection method that integrates adversarial training loss to obtain more robust and generalized feature representations. We utilize the adversarial loss previously employed in domain adaptation to align feature distributions between source and target domains, to enhance feature robustness and generalization in few-shot anomaly detection tasks. We hypothesize that adversarial loss is effective when applied to features that should have similar characteristics, such as those from the same layer in a Siamese network's parallel branches or input-output pairs of reconstruction-based methods. Experimental results demonstrate that the proposed method generally achieves better performance when utilizing the adversarial loss. △ Less

Submitted 4 December, 2023; originally announced December 2023.

Comments: BMVC 2023

An Empirical Bayes Framework for Open-Domain Dialogue Generation

Authors: Jing Yang Lee, Kong Aik Lee, Woon-Seng Gan

Abstract: To engage human users in meaningful conversation, open-domain dialogue agents are required to generate diverse and contextually coherent dialogue. Despite recent advancements, which can be attributed to the usage of pretrained language models, the generation of diverse and coherent dialogue remains an open research problem. A popular approach to address this issue involves the adaptation of variat… ▽ More To engage human users in meaningful conversation, open-domain dialogue agents are required to generate diverse and contextually coherent dialogue. Despite recent advancements, which can be attributed to the usage of pretrained language models, the generation of diverse and coherent dialogue remains an open research problem. A popular approach to address this issue involves the adaptation of variational frameworks. However, while these approaches successfully improve diversity, they tend to compromise on contextual coherence. Hence, we propose the Bayesian Open-domain Dialogue with Empirical Bayes (BODEB) framework, an empirical bayes framework for constructing an Bayesian open-domain dialogue agent by leveraging pretrained parameters to inform the prior and posterior parameter distributions. Empirical results show that BODEB achieves better results in terms of both diversity and coherence compared to variational frameworks. △ Less

Submitted 17 November, 2023; originally announced November 2023.

Partially Randomizing Transformer Weights for Dialogue Response Diversity

Authors: Jing Yang Lee, Kong Aik Lee, Woon-Seng Gan

Abstract: Despite recent progress in generative open-domain dialogue, the issue of low response diversity persists. Prior works have addressed this issue via either novel objective functions, alternative learning approaches such as variational frameworks, or architectural extensions such as the Randomized Link (RL) Transformer. However, these approaches typically entail either additional difficulties during… ▽ More Despite recent progress in generative open-domain dialogue, the issue of low response diversity persists. Prior works have addressed this issue via either novel objective functions, alternative learning approaches such as variational frameworks, or architectural extensions such as the Randomized Link (RL) Transformer. However, these approaches typically entail either additional difficulties during training/inference, or a significant increase in model size and complexity. Hence, we propose the \underline{Pa}rtially \underline{Ra}ndomized trans\underline{Former} (PaRaFormer), a simple extension of the transformer which involves freezing the weights of selected layers after random initialization. Experimental results reveal that the performance of the PaRaformer is comparable to that of the aforementioned approaches, despite not entailing any additional training difficulty or increase in model complexity. △ Less

Submitted 17 November, 2023; originally announced November 2023.

Label Space Partition Selection for Multi-Object Tracking Using Two-Layer Partitioning

Authors: Ji Youn Lee, Changbeom Shim, Hoa Van Nguyen, Tran Thien Dat Nguyen, Hyunjin Choi, Youngho Kim

Abstract: Estimating the trajectories of multi-objects poses a significant challenge due to data association ambiguity, which leads to a substantial increase in computational requirements. To address such problems, a divide-and-conquer manner has been employed with parallel computation. In this strategy, distinguished objects that have unique labels are grouped based on their statistical dependencies, the i… ▽ More Estimating the trajectories of multi-objects poses a significant challenge due to data association ambiguity, which leads to a substantial increase in computational requirements. To address such problems, a divide-and-conquer manner has been employed with parallel computation. In this strategy, distinguished objects that have unique labels are grouped based on their statistical dependencies, the intersection of predicted measurements. Several geometry approaches have been used for label grouping since finding all intersected label pairs is clearly infeasible for large-scale tracking problems. This paper proposes an efficient implementation of label grouping for label-partitioned generalized labeled multi-Bernoulli filter framework using a secondary partitioning technique. This allows for parallel computation in the label graph indexing step, avoiding generating and eliminating duplicate comparisons. Additionally, we compare the performance of the proposed technique with several efficient spatial searching algorithms. The results demonstrate the superior performance of the proposed approach on large-scale data sets, enabling scalable trajectory estimation. △ Less

Submitted 22 October, 2023; originally announced October 2023.

Comments: 6 pages, 4 figures

The GitHub Recent Bugs Dataset for Evaluating LLM-based Debugging Applications

Authors: Jae Yong Lee, Sungmin Kang, Juyeon Yoon, Shin Yoo

Abstract: Large Language Models (LLMs) have demonstrated strong natural language processing and code synthesis capabilities, which has led to their rapid adoption in software engineering applications. However, details about LLM training data are often not made public, which has caused concern as to whether existing bug benchmarks are included. In lieu of the training data for the popular GPT models, we exam… ▽ More Large Language Models (LLMs) have demonstrated strong natural language processing and code synthesis capabilities, which has led to their rapid adoption in software engineering applications. However, details about LLM training data are often not made public, which has caused concern as to whether existing bug benchmarks are included. In lieu of the training data for the popular GPT models, we examine the training data of the open-source LLM StarCoder, and find it likely that data from the widely used Defects4J benchmark was included, raising the possibility of its inclusion in GPT training data as well. This makes it difficult to tell how well LLM-based results on Defects4J would generalize, as for any results it would be unclear whether a technique's performance is due to LLM generalization or memorization. To remedy this issue and facilitate continued research on LLM-based SE, we present the GitHub Recent Bugs (GHRB) dataset, which includes 76 real-world Java bugs that were gathered after the OpenAI data cut-off point. △ Less

Submitted 1 November, 2023; v1 submitted 19 October, 2023; originally announced October 2023.

Finite Element Operator Network for Solving Elliptic-type parametric PDEs

Authors: Jae Yong Lee, Seungchan Ko, Youngjoon Hong

Abstract: Partial differential equations (PDEs) underlie our understanding and prediction of natural phenomena across numerous fields, including physics, engineering, and finance. However, solving parametric PDEs is a complex task that necessitates efficient numerical methods. In this paper, we propose a novel approach for solving parametric PDEs using a Finite Element Operator Network (FEONet). Our propose… ▽ More Partial differential equations (PDEs) underlie our understanding and prediction of natural phenomena across numerous fields, including physics, engineering, and finance. However, solving parametric PDEs is a complex task that necessitates efficient numerical methods. In this paper, we propose a novel approach for solving parametric PDEs using a Finite Element Operator Network (FEONet). Our proposed method leverages the power of deep learning in conjunction with traditional numerical methods, specifically the finite element method, to solve parametric PDEs in the absence of any paired input-output training data. We performed various experiments on several benchmark problems and confirmed that our approach has demonstrated excellent performance across various settings and environments, proving its versatility in terms of accuracy, generalization, and computational flexibility. While our method is not meshless, the FEONet framework shows potential for application in various fields where PDEs play a crucial role in modeling complex domains with diverse boundary conditions and singular behavior. Furthermore, we provide theoretical convergence analysis to support our approach, utilizing finite element approximation in numerical analysis. △ Less

Submitted 19 February, 2025; v1 submitted 8 August, 2023; originally announced August 2023.

Comments: 28 pages, 11 figures

MSC Class: 65M60; 65N30; 68T20; 68U07 ACM Class: G.1.8

Journal ref: SIAM Journal on Scientific Computing (SISC), 2025

SimCol3D -- 3D Reconstruction during Colonoscopy Challenge

Authors: Anita Rau, Sophia Bano, Yueming Jin, Pablo Azagra, Javier Morlana, Rawen Kader, Edward Sanderson, Bogdan J. Matuszewski, Jae Young Lee, Dong-Jae Lee, Erez Posner, Netanel Frank, Varshini Elangovan, Sista Raviteja, Zhengwen Li, Jiquan Liu, Seenivasan Lalithkumar, Mobarakol Islam, Hongliang Ren, Laurence B. Lovat, José M. M. Montiel, Danail Stoyanov

Abstract: Colorectal cancer is one of the most common cancers in the world. While colonoscopy is an effective screening technique, navigating an endoscope through the colon to detect polyps is challenging. A 3D map of the observed surfaces could enhance the identification of unscreened colon tissue and serve as a training platform. However, reconstructing the colon from video footage remains difficult. Lear… ▽ More Colorectal cancer is one of the most common cancers in the world. While colonoscopy is an effective screening technique, navigating an endoscope through the colon to detect polyps is challenging. A 3D map of the observed surfaces could enhance the identification of unscreened colon tissue and serve as a training platform. However, reconstructing the colon from video footage remains difficult. Learning-based approaches hold promise as robust alternatives, but necessitate extensive datasets. Establishing a benchmark dataset, the 2022 EndoVis sub-challenge SimCol3D aimed to facilitate data-driven depth and pose prediction during colonoscopy. The challenge was hosted as part of MICCAI 2022 in Singapore. Six teams from around the world and representatives from academia and industry participated in the three sub-challenges: synthetic depth prediction, synthetic pose prediction, and real pose prediction. This paper describes the challenge, the submitted methods, and their results. We show that depth prediction from synthetic colonoscopy images is robustly solvable, while pose estimation remains an open research question. △ Less

Submitted 2 July, 2024; v1 submitted 20 July, 2023; originally announced July 2023.

MSC Class: I.4.5

Journal ref: Medical Image Analysis 96 (2024): 103195

Lightweight Monocular Depth Estimation via Token-Sharing Transformer

Authors: Dong-Jae Lee, Jae Young Lee, Hyounguk Shon, Eojindl Yi, Yeong-Hun Park, Sung-Sik Cho, Junmo Kim

Abstract: Depth estimation is an important task in various robotics systems and applications. In mobile robotics systems, monocular depth estimation is desirable since a single RGB camera can be deployable at a low cost and compact size. Due to its significant and growing needs, many lightweight monocular depth estimation networks have been proposed for mobile robotics systems. While most lightweight monocu… ▽ More Depth estimation is an important task in various robotics systems and applications. In mobile robotics systems, monocular depth estimation is desirable since a single RGB camera can be deployable at a low cost and compact size. Due to its significant and growing needs, many lightweight monocular depth estimation networks have been proposed for mobile robotics systems. While most lightweight monocular depth estimation methods have been developed using convolution neural networks, the Transformer has been gradually utilized in monocular depth estimation recently. However, massive parameters and large computational costs in the Transformer disturb the deployment to embedded devices. In this paper, we present a Token-Sharing Transformer (TST), an architecture using the Transformer for monocular depth estimation, optimized especially in embedded devices. The proposed TST utilizes global token sharing, which enables the model to obtain an accurate depth prediction with high throughput in embedded devices. Experimental results show that TST outperforms the existing lightweight monocular depth estimation methods. On the NYU Depth v2 dataset, TST can deliver depth maps up to 63.4 FPS in NVIDIA Jetson nano and 142.6 FPS in NVIDIA Jetson TX2, with lower errors than the existing methods. Furthermore, TST achieves real-time depth estimation of high-resolution images on Jetson TX2 with competitive results. △ Less

Submitted 9 June, 2023; originally announced June 2023.

Comments: ICRA 2023

Fix the Noise: Disentangling Source Feature for Controllable Domain Translation

Authors: Dongyeun Lee, Jae Young Lee, Doyeon Kim, Jaehyun Choi, Jaejun Yoo, Junmo Kim

Abstract: Recent studies show strong generative performance in domain translation especially by using transfer learning techniques on the unconditional generator. However, the control between different domain features using a single model is still challenging. Existing methods often require additional models, which is computationally demanding and leads to unsatisfactory visual quality. In addition, they ha… ▽ More Recent studies show strong generative performance in domain translation especially by using transfer learning techniques on the unconditional generator. However, the control between different domain features using a single model is still challenging. Existing methods often require additional models, which is computationally demanding and leads to unsatisfactory visual quality. In addition, they have restricted control steps, which prevents a smooth transition. In this paper, we propose a new approach for high-quality domain translation with better controllability. The key idea is to preserve source features within a disentangled subspace of a target feature space. This allows our method to smoothly control the degree to which it preserves source features while generating images from an entirely new domain using only a single model. Our extensive experiments show that the proposed method can produce more consistent and realistic images than previous works and maintain precise controllability over different levels of transformation. The code is available at https://github.com/LeeDongYeun/FixNoise. △ Less

Submitted 20 March, 2023; originally announced March 2023.

Comments: Accepted by CVPR 2023. The code is available at https://github.com/LeeDongYeun/FixNoise. Extended from arXiv:2204.14079 (AICC workshop at CVPR 2022)

Rapid Development of Compositional AI

Authors: Lee Martie, Jessie Rosenberg, Veronique Demers, Gaoyuan Zhang, Onkar Bhardwaj, John Henning, Aditya Prasad, Matt Stallone, Ja Young Lee, Lucy Yip, Damilola Adesina, Elahe Paikari, Oscar Resendiz, Sarah Shaw, David Cox

Abstract: Compositional AI systems, which combine multiple artificial intelligence components together with other application components to solve a larger problem, have no known pattern of development and are often approached in a bespoke and ad hoc style. This makes development slower and harder to reuse for future applications. To support the full rapid development cycle of compositional AI applications,… ▽ More Compositional AI systems, which combine multiple artificial intelligence components together with other application components to solve a larger problem, have no known pattern of development and are often approached in a bespoke and ad hoc style. This makes development slower and harder to reuse for future applications. To support the full rapid development cycle of compositional AI applications, we have developed a novel framework called (Bee)* (written as a regular expression and pronounced as "beestar"). We illustrate how (Bee)* supports building integrated, scalable, and interactive compositional AI applications with a simplified developer experience. △ Less

Submitted 12 February, 2023; originally announced February 2023.

Comments: Accepted to ICSE 2023, NIER track

Journal ref: 2023 IEEE/ACM 45th International Conference on Software Engineering: New Ideas and Emerging Technologies Results Track (ICSE-NIER), Melbourne, Australia, 2023, pp. (forthcoming)

I See-Through You: A Framework for Removing Foreground Occlusion in Both Sparse and Dense Light Field Images

Authors: Jiwan Hur, Jae Young Lee, Jaehyun Choi, Junmo Kim

Abstract: Light field (LF) camera captures rich information from a scene. Using the information, the LF de-occlusion (LF-DeOcc) task aims to reconstruct the occlusion-free center view image. Existing LF-DeOcc studies mainly focus on the sparsely sampled (sparse) LF images where most of the occluded regions are visible in other views due to the large disparity. In this paper, we expand LF-DeOcc in more chall… ▽ More Light field (LF) camera captures rich information from a scene. Using the information, the LF de-occlusion (LF-DeOcc) task aims to reconstruct the occlusion-free center view image. Existing LF-DeOcc studies mainly focus on the sparsely sampled (sparse) LF images where most of the occluded regions are visible in other views due to the large disparity. In this paper, we expand LF-DeOcc in more challenging datasets, densely sampled (dense) LF images, which are taken by a micro-lens-based portable LF camera. Due to the small disparity ranges of dense LF images, most of the background regions are invisible in any view. To apply LF-DeOcc in both LF datasets, we propose a framework, ISTY, which is defined and divided into three roles: (1) extract LF features, (2) define the occlusion, and (3) inpaint occluded regions. By dividing the framework into three specialized components according to the roles, the development and analysis can be easier. Furthermore, an explainable intermediate representation, an occlusion mask, can be obtained in the proposed framework. The occlusion mask is useful for comprehensive analysis of the model and other applications by manipulating the mask. In experiments, qualitative and quantitative results show that the proposed framework outperforms state-of-the-art LF-DeOcc methods in both sparse and dense LF datasets. △ Less

Submitted 16 January, 2023; originally announced January 2023.

Comments: WACV 2023

Auditing citation polarization during the early COVID-19 pandemic

Authors: Taekho You, Jinseo Park, June Young Lee, Jinhyuk Yun

Abstract: The recent pandemic stimulated scientists to publish a significant amount of research that created a surge of citations of COVID-19-related publications in a short time, leading to an abrupt inflation of the journal impact factor (IF). By auditing the complete set of COVID-19-related publications in the Web of Science, we reveal here that COVID-19-related research worsened the polarization of acad… ▽ More The recent pandemic stimulated scientists to publish a significant amount of research that created a surge of citations of COVID-19-related publications in a short time, leading to an abrupt inflation of the journal impact factor (IF). By auditing the complete set of COVID-19-related publications in the Web of Science, we reveal here that COVID-19-related research worsened the polarization of academic journals: the IF before the pandemic was proportional to the increment of IF, which had the effect of increasing inequality while retaining the journal rankings. We also found that the most highly cited studies related to COVID-19 were published in prestigious journals at the onset of the epidemic. Through the present quantitative investigation, our findings caution against the belief that quantitative metrics, particularly IF, can indicate the significance of individual papers. Rather, such metrics reflect the social attention given to a particular study. △ Less

Submitted 24 May, 2024; v1 submitted 5 January, 2023; originally announced January 2023.

Comments: 31 pages of main text including 4 figures + 13 pages of supplementary information including 2 supplementary tables and 10 supplementary figures

Sparse SPN: Depth Completion from Sparse Keypoints

Authors: Yuqun Wu, Jae Yong Lee, Derek Hoiem

Abstract: Our long term goal is to use image-based depth completion to quickly create 3D models from sparse point clouds, e.g. from SfM or SLAM. Much progress has been made in depth completion. However, most current works assume well distributed samples of known depth, e.g. Lidar or random uniform sampling, and perform poorly on uneven samples, such as from keypoints, due to the large unsampled regions. To… ▽ More Our long term goal is to use image-based depth completion to quickly create 3D models from sparse point clouds, e.g. from SfM or SLAM. Much progress has been made in depth completion. However, most current works assume well distributed samples of known depth, e.g. Lidar or random uniform sampling, and perform poorly on uneven samples, such as from keypoints, due to the large unsampled regions. To address this problem, we extend CSPN with multiscale prediction and a dilated kernel, leading to much better completion of keypoint-sampled depth. We also show that a model trained on NYUv2 creates surprisingly good point clouds on ETH3D by completing sparse SfM points. △ Less

Submitted 2 December, 2022; originally announced December 2022.

QFF: Quantized Fourier Features for Neural Field Representations

Authors: Jae Yong Lee, Yuqun Wu, Chuhang Zou, Shenlong Wang, Derek Hoiem

Abstract: Multilayer perceptrons (MLPs) learn high frequencies slowly. Recent approaches encode features in spatial bins to improve speed of learning details, but at the cost of larger model size and loss of continuity. Instead, we propose to encode features in bins of Fourier features that are commonly used for positional encoding. We call these Quantized Fourier Features (QFF). As a naturally multiresolut… ▽ More Multilayer perceptrons (MLPs) learn high frequencies slowly. Recent approaches encode features in spatial bins to improve speed of learning details, but at the cost of larger model size and loss of continuity. Instead, we propose to encode features in bins of Fourier features that are commonly used for positional encoding. We call these Quantized Fourier Features (QFF). As a naturally multiresolution and periodic representation, our experiments show that using QFF can result in smaller model size, faster training, and better quality outputs for several applications, including Neural Image Representations (NIR), Neural Radiance Field (NeRF) and Signed Distance Function (SDF) modeling. QFF are easy to code, fast to compute, and serve as a simple drop-in addition to many neural field representations. △ Less

Submitted 1 December, 2022; originally announced December 2022.

SNAC: Speaker-normalized affine coupling layer in flow-based architecture for zero-shot multi-speaker text-to-speech

Authors: Byoung Jin Choi, Myeonghun Jeong, Joun Yeop Lee, Nam Soo Kim

Abstract: Zero-shot multi-speaker text-to-speech (ZSM-TTS) models aim to generate a speech sample with the voice characteristic of an unseen speaker. The main challenge of ZSM-TTS is to increase the overall speaker similarity for unseen speakers. One of the most successful speaker conditioning methods for flow-based multi-speaker text-to-speech (TTS) models is to utilize the functions which predict the scal… ▽ More Zero-shot multi-speaker text-to-speech (ZSM-TTS) models aim to generate a speech sample with the voice characteristic of an unseen speaker. The main challenge of ZSM-TTS is to increase the overall speaker similarity for unseen speakers. One of the most successful speaker conditioning methods for flow-based multi-speaker text-to-speech (TTS) models is to utilize the functions which predict the scale and bias parameters of the affine coupling layers according to the given speaker embedding vector. In this letter, we improve on the previous speaker conditioning method by introducing a speaker-normalized affine coupling (SNAC) layer which allows for unseen speaker speech synthesis in a zero-shot manner leveraging a normalization-based conditioning technique. The newly designed coupling layer explicitly normalizes the input by the parameters predicted from a speaker embedding vector while training, enabling an inverse process of denormalizing for a new speaker embedding at inference. The proposed conditioning scheme yields the state-of-the-art performance in terms of the speech quality and speaker similarity in a ZSM-TTS setting. △ Less

Submitted 30 November, 2022; originally announced November 2022.

Comments: Accepted to IEEE Signal Processing Letters