BZPEERPapers, people, evidence and research paths
Menu

Discover

SearchFind papers, people, topics, institutions and opportunities from one place.GraphSee how papers, authors, topics and evidence connect.

Research tools

HomeContinue from the papers, people and topics that matter now.CollectionsTurn saved papers into reading lists, evidence maps and shareable context.ResearchReconstruct the path that led you from search to paper to question.CollaborationMove from a paper, topic or expert request into a focused thread.PublishCreate full-text research articles with metadata, formulas and versions.

Network

ExpertsFind specialists whose work and reviews explain why they can help.CommunitiesJoin research groups organized around papers, topics and shared evidence.

Opportunities

ListingsBrowse roles, calls and collaborations connected to real research context.

Account

Log inReturn to your saved papers, graph views and active threads.Create accountStart saving papers, building a research trail and joining teams.
Log inCreate account

Source author record

Minjae Lee

Minjae Lee appears in the imported research catalog. Authorship, coauthor and topic links are available while profile ownership is still unclaimed.

ResearcherUnclaimed source record
math-phmath.MPquant-phComputation and LanguageMachine Learningmath.SPSoundArtificial IntelligenceComputer Visioncond-mat.mes-hallcs.CYeess.ASHuman-Computer InteractionNeural and Evolutionary Computingphysics.app-phphysics.atom-ph

Catalog footprint

What is connected

10works
16topics
4close collaborators

Actions

Connect this record

Log in to claim
Open graphBrowse works

Research graph

See the researcher in context

Open full explorer

Inspect adjacent papers, topics, institutions and collaborators without losing the researcher page.

Building this map preview

BZPEER is loading the nearby papers, people, topics and institutions for this page.

Published work

10 published item(s)

preprint2026arXiv

Going PLACES: Participatory Localized Red Teaming for Text-to-Image Safety in the Global South

Despite the global deployment of text-to-image (T2I) models, their safety frameworks are largely calibrated to a Western-centric default, creating significant vulnerabilities for the rest of the world. To embrace cultural pluralism and bring historically under-represented perspectives in T2I safety, we conduct localised community-centered red teaming studies in the Global South. Our two-fold approach prioritizes localization and participation, by focusing on secondary urban centers in these regions, and conducting community engagement and training workshops to contextualize local norms. As a result, we present PLACES, a dataset comprising over 26,000 examples of T2I model failures collected in partnership with universities in Ghana, Nigeria, and two regions of India (Karnataka and Punjab). Analysis of prompts collected reveals a wide-ranging diversity in socio-cultural and linguistic attributes, when compared to existing geography-agnostic crowdsourced red-teaming data. We observe unique adversarial patterns enabled by local cultural and linguistic nuances, and distinct clusters within region around specific themes, such as religion in India. Moreover, we uncover structural contextual gaps in existing safety frameworks by identifying novel harms showing normative dissonance (e.g., violating religious norms, ignoring local customs, and ominous symbolism). This work argues that expanding T2I safety requires moving beyond mere scale to incorporate deeply localised, participatory methodologies for data collection and contextualization. Content warning: This paper includes examples containing potentially harmful or offensive content.

0 citations0 reviewsNo code linkedOpen access
preprint2026arXiv

Sparse-View 3D Gaussian Splatting in the Wild

We propose a 3D novel sparse-view synthesis framework for unconstrained real-world scenarios that contain distractors. Unlike existing methods that primarily perform novel-view synthesis from a sparse set of constrained images without transient elements or leverage unconstrained dense image collections to enhance 3D representation in real-world scenarios, our method not only effectively tackles sparse unconstrained image collections, but also shows high-quality 3D rendering results. To do this, we introduce reference-guided view refinement with a diffusion model using a transient mask and a reference image to enhance the 3D representation and mitigate artifacts in rendered views. Furthermore, we address sparse regions in the Gaussian field via pseudo-view generation along with a sparsity-aware Gaussian replication strategy to amplify Gaussians in the sparse regions. Extensive experiments on publicly available datasets demonstrate that our methodology consistently outperforms existing methods (e.g., PSNR - 17.2%, SSIM - 10.8%, LPIPS - 4.0%) and provides high-fidelity 3D rendering results. This advancement paves the way for realizing unconstrained real-world scenarios without labor-intensive data acquisition. Our project page is available at $\href{https://robotic-vision-lab.github.io/SaveWildGS/}{here}$

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Metric Learning for Keyword Spotting

The goal of this work is to train effective representations for keyword spotting via metric learning. Most existing works address keyword spotting as a closed-set classification problem, where both target and non-target keywords are predefined. Therefore, prevailing classifier-based keyword spotting systems perform poorly on non-target sounds which are unseen during the training stage, causing high false alarm rates in real-world scenarios. In reality, keyword spotting is a detection problem where predefined target keywords are detected from a variety of unknown sounds. This shares many similarities to metric learning problems in that the unseen and unknown non-target sounds must be clearly differentiated from the target keywords. However, a key difference is that the target keywords are known and predefined. To this end, we propose a new method based on metric learning that maximises the distance between target and non-target keywords, but also learns per-class weights for target keywords à la classification objectives. Experiments on the Google Speech Commands dataset show that our method significantly reduces false alarms to unseen non-target keywords, while maintaining the overall classification accuracy.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Microelectromechanical-System-Based Design of a High-Finesse Fiber Cavity Integrated with an Ion Trap

We present a numerical study of a MEMS-based design of a fiber cavity integrated with an ion trap system. Each fiber mirror is supported by a microactuator that controls the mirror's position in three dimensions. The mechanical stability is investigated by a feasibility analysis showing that the actuator offers a stable support of the fiber. The actuators move the fibers' positions continuously with a stroke of more than 10 $μ$m, with mechanical resonance frequencies on the order of kHz. A calculation of the trapping potential shows that a separation between ion and fiber consistent with strong ion-cavity coupling is feasible. Our miniaturized ion-photon interface constitutes a viable approach to integrated hardware for quantum information.

0 citations0 reviewsNo code linkedOpen access
preprint2016arXiv

A Fermi golden rule for quantum graphs

We present a Fermi golden rule giving rates of decay of states obtained by perturbing embedded eigenvalues of a quantum graph. To illustrate the procedure in a notationally simpler setting we also present a Fermi Golden Rule for boundary value problems on surfaces with constant curvature cusps. We also provide a resonance existence result which is uniform on compact sets of energies and metric graphs. The results are illustrated by numerical experiments.

0 citations0 reviewsNo code linkedOpen access
preprint2016arXiv

Dirac cones for point scatterers on a honeycomb lattice

We investigate the spectrum and the dispersion relation of the Schrödinger operator with point scatterers on a triangular lattice and a honeycomb lattice. We prove that the low-level dispersion bands have conic singularities near Dirac points, which are the vertices of the first Brillouin Zone. The existence of such conic dispersion bands plays an important role in various electronic properties of honeycomb-structured materials such as graphene. We then prove that for a honeycomb lattice, the spectra generated by higher-level dispersion relations are all connected so the complete spectrum consists of at most three bands. Numerical simulations for dispersion bands with various parameters are also presented.

0 citations0 reviewsNo code linkedOpen access
preprint2016arXiv

Eigenvalues of Šeba billiards with localization of low-energy eigenfunctions

We study the localization of eigenfunctions produced by a point scatterer on a thin rectangle. We find an explicit set of eigenfunctions localized to part of the rectangle by showing that the one-dimensional Schrödinger operator with a Dirac delta potential asymptotically governs the spectral properties of the two-dimensional point scatterer. We also find the rate of localization in terms of the aspect ratio of the rectangle. In addition, we present numerical results regarding the asymptotic behavior of the localization.

0 citations0 reviewsNo code linkedOpen access
preprint2016arXiv

FPGA-Based Low-Power Speech Recognition with Recurrent Neural Networks

In this paper, a neural network based real-time speech recognition (SR) system is developed using an FPGA for very low-power operation. The implemented system employs two recurrent neural networks (RNNs); one is a speech-to-character RNN for acoustic modeling (AM) and the other is for character-level language modeling (LM). The system also employs a statistical word-level LM to improve the recognition accuracy. The results of the AM, the character-level LM, and the word-level LM are combined using a fairly simple N-best search algorithm instead of the hidden Markov model (HMM) based network. The RNNs are implemented using massively parallel processing elements (PEs) for low latency and high throughput. The weights are quantized to 6 bits to store all of them in the on-chip memory of an FPGA. The proposed algorithm is implemented on a Xilinx XC7Z045, and the system can operate much faster than real-time.

0 citations0 reviewsNo code linkedOpen access
preprint2015arXiv

Localization of low-energy eigenfunctions in Seba billiards

We investigate localization of low-energy modes of the Laplacian with a point scatterer on a rectangular plate. We observe that the point scatterer acts as a barrier confining the low-level modes to one side of the plate while assuming the Dirichlet boundary condition at a point does not induce this type of localization. This low-energy phenomenon extends to higher modes as we increase the eccentricity of the plate.

0 citations0 reviewsNo code linkedOpen access
preprint2015arXiv

Online Keyword Spotting with a Character-Level Recurrent Neural Network

In this paper, we propose a context-aware keyword spotting model employing a character-level recurrent neural network (RNN) for spoken term detection in continuous speech. The RNN is end-to-end trained with connectionist temporal classification (CTC) to generate the probabilities of character and word-boundary labels. There is no need for the phonetic transcription, senone modeling, or system dictionary in training and testing. Also, keywords can easily be added and modified by editing the text based keyword list without retraining the RNN. Moreover, the unidirectional RNN processes an infinitely long input audio streams without pre-segmentation and keywords are detected with low-latency before the utterance is finished. Experimental results show that the proposed keyword spotter significantly outperforms the deep neural network (DNN) and hidden Markov model (HMM) based keyword-filler model even with less computations.

0 citations0 reviewsNo code linkedOpen access