arXiv subjects

Hyunjae Lee

Publications and source records attributed to Hyunjae Lee.

9 recordsLinked to original sources

arXiv2026

Pinned Boundaries Delay Contraction and Shape Stress Relaxation in Active Gels

Cells dynamically generate, transmit, and dissipate stress. Central to these processes is the actomyosin cortex, an active contractile material that drives cellular mechanical behavior. While prior studies have focused on freely contracting actomyosin systems, the role of mechanical constraints such as adhesion to boundaries remains less explored. To address this, we employ reconstituted actomyosin gels to investigate cellular contractility. We study contraction dynamics under pinned boundary conditions, where the gel is adhered transversely to two opposing surfaces, mimicking supracellular actomyosin networks in tissues and embryos. We find that pinned contraction leads to stress buildup, delaying contraction, producing intermittent dynamics, and generating spatially nonuniform strain fields. Stress is relieved through several pathways, including active-stress-driven symmetric constriction and defect-driven processes such as boundary detachment and internal rupture. We develop a hydrodynamic model incorporating elastic, viscous, and active stress contributions that distinguishes between stress-accumulation and stress-release phases and links variations in active stress to the observed intermittent dynamics. The model predicts distinct energy relaxation rates before and after detachment events, providing insight into stress dissipation. We compare experiments with numerical simulations, which reproduce the observed behavior and reveal how internal energy is generated and dissipated during stress buildup and relaxation. Together, our results demonstrate how boundary conditions and spatial heterogeneity govern the mechanical behavior of contractile active gels. These findings provide insight into stress regulation in cellular and tissue-scale systems and may inform the design of adaptive soft materials and bioinspired robotic systems.

cond-mat.soft↗

arXiv2025

Experimental methods to control pinned and coupled actomyosin contraction events

Actin and myosin drive many instances of force generation, deformation, and shape change in cells, tissues, and organisms. In particular, cytoskeletal actomyosin is remarkable in its adaptive architecture, responding to a host of actin-binding proteins. Equally important, however, is actomyosin's interaction with its mechanical environment. Actomyosin contractility and environmental properties, such as geometry and stiffness, are inherently coupled. To understand this coupling, novel experimental techniques are needed. Here we describe methods to spatially control the anchoring of reconstituted contractile actomyosin networks to two, opposing surfaces ("transverse anchoring"). The two surfaces can be either rigid ("pinned contraction"), or one of the surfaces may be compliant ("coupled contraction"). We introduce compliance by manufacturing flexure hinges, and describe their calibration. Calibration permits a direct measurement of the contractile force and mechanical work that actomyosin exerts on the environment. The methods described here provide an avenue toward a more complete characterization of actomyosin's role as an actuator, an essential property in its context of driving deformation and shape change in living systems.

cond-mat.soft↗

arXiv2025

SGuard-v1: Safety Guardrail for Large Language Models

We present SGuard-v1, a lightweight safety guardrail for Large Language Models (LLMs), which comprises two specialized models to detect harmful content and screen adversarial prompts in human-AI conversational settings. The first component, ContentFilter, is trained to identify safety risks in LLM prompts and responses in accordance with the MLCommons hazard taxonomy, a comprehensive framework for trust and safety assessment of AI. The second component, JailbreakFilter, is trained with a carefully designed curriculum over integrated datasets and findings from prior work on adversarial prompting, covering 60 major attack types while mitigating false-unsafe classification. SGuard-v1 is built on the 2B-parameter Granite-3.3-2B-Instruct model that supports 12 languages. We curate approximately 1.4 million training instances from both collected and synthesized data and perform instruction tuning on the base model, distributing the curated data across the two component according to their designated functions. Through extensive evaluation on public and proprietary safety benchmarks, SGuard-v1 achieves state-of-the-art safety performance while remaining lightweight, thereby reducing deployment overhead. SGuard-v1 also improves interpretability for downstream use by providing multi-class safety predictions and their binary confidence scores. We release the SGuard-v1 under the Apache-2.0 License to enable further research and practical deployment in AI safety.

cs.CL↗

arXiv2024

Adaptive Accelerated Failure Time modeling with a Semiparametric Skewed Error Distribution

The accelerated failure time (AFT) model is widely used to analyze relationships between variables in the presence of censored observations. However, this model relies on some assumptions such as the error distribution, which can lead to biased or inefficient estimates if these assumptions are violated. In order to overcome this challenge, we propose a novel approach that incorporates a semiparametric skew-normal scale mixture distribution for the error term in the AFT model. By allowing for more flexibility and robustness, this approach reduces the risk of misspecification and improves the accuracy of parameter estimation. We investigate the identifiability and consistency of the proposed model and develop a practical estimation algorithm. To evaluate the performance of our approach, we conduct extensive simulation studies and real data analyses. The results demonstrate the effectiveness of our method in providing robust and accurate estimates in various scenarios.

stat.ME↗

arXiv2023

Is Cross-modal Information Retrieval Possible without Training?

Encoded representations from a pretrained deep learning model (e.g., BERT text embeddings, penultimate CNN layer activations of an image) convey a rich set of features beneficial for information retrieval. Embeddings for a particular modality of data occupy a high-dimensional space of its own, but it can be semantically aligned to another by a simple mapping without training a deep neural net. In this paper, we take a simple mapping computed from the least squares and singular value decomposition (SVD) for a solution to the Procrustes problem to serve a means to cross-modal information retrieval. That is, given information in one modality such as text, the mapping helps us locate a semantically equivalent data item in another modality such as image. Using off-the-shelf pretrained deep learning models, we have experimented the aforementioned simple cross-modal mappings in tasks of text-to-image and image-to-text retrieval. Despite simplicity, our mappings perform reasonably well reaching the highest accuracy of 77% on recall@10, which is comparable to those requiring costly neural net training and fine-tuning. We have improved the simple mappings by contrastive learning on the pretrained models. Contrastive learning can be thought as properly biasing the pretrained encoders to enhance the cross-modal mapping quality. We have further improved the performance by multilayer perceptron with gating (gMLP), a simple neural architecture.

cs.LG↗

arXiv2023

D2CSE: Difference-aware Deep continuous prompts for Contrastive Sentence Embeddings

This paper describes Difference-aware Deep continuous prompt for Contrastive Sentence Embeddings (D2CSE) that learns sentence embeddings. Compared to state-of-the-art approaches, D2CSE computes sentence vectors that are exceptional to distinguish a subtle difference in similar sentences by employing a simple neural architecture for continuous prompts. Unlike existing architectures that require multiple pretrained language models (PLMs) to process a pair of the original and corrupted (subtly modified) sentences, D2CSE avoids cumbersome fine-tuning of multiple PLMs by only optimizing continuous prompts by performing multiple tasks -- i.e., contrastive learning and conditional replaced token detection all done in a self-guided manner. D2CSE overloads a single PLM on continuous prompts and greatly saves memory consumption as a result. The number of training parameters in D2CSE is reduced to about 1\% of existing approaches while substantially improving the quality of sentence embeddings. We evaluate D2CSE on seven Semantic Textual Similarity (STS) benchmarks, using three different metrics, namely, Spearman's rank correlation, recall@K for a retrieval task, and the anisotropy of an embedding space measured in alignment and uniformity. Our empirical results suggest that shallow (not too meticulously devised) continuous prompts can be honed effectively for multiple NLP tasks and lead to improvements upon existing state-of-the-art approaches.

cs.CL↗

arXiv2022

Enhancing Semantic Understanding with Self-supervised Methods for Abstractive Dialogue Summarization

Contextualized word embeddings can lead to state-of-the-art performances in natural language understanding. Recently, a pre-trained deep contextualized text encoder such as BERT has shown its potential in improving natural language tasks including abstractive summarization. Existing approaches in dialogue summarization focus on incorporating a large language model into summarization task trained on large-scale corpora consisting of news articles rather than dialogues of multiple speakers. In this paper, we introduce self-supervised methods to compensate shortcomings to train a dialogue summarization model. Our principle is to detect incoherent information flows using pretext dialogue text to enhance BERT's ability to contextualize the dialogue text representations. We build and fine-tune an abstractive dialogue summarization model on a shared encoder-decoder architecture using the enhanced BERT. We empirically evaluate our abstractive dialogue summarizer with the SAMSum corpus, a recently introduced dataset with abstractive dialogue summaries. All of our methods have contributed improvements to abstractive summary measured in ROUGE scores. Through an extensive ablation study, we also present a sensitivity analysis to critical model hyperparameters, probabilities of switching utterances and masking interlocutors.

cs.CL↗

arXiv2021

KoreALBERT: Pretraining a Lite BERT Model for Korean Language Understanding

A Lite BERT (ALBERT) has been introduced to scale up deep bidirectional representation learning for natural languages. Due to the lack of pretrained ALBERT models for Korean language, the best available practice is the multilingual model or resorting back to the any other BERT-based model. In this paper, we develop and pretrain KoreALBERT, a monolingual ALBERT model specifically for Korean language understanding. We introduce a new training objective, namely Word Order Prediction (WOP), and use alongside the existing MLM and SOP criteria to the same architecture and model parameters. Despite having significantly fewer model parameters (thus, quicker to train), our pretrained KoreALBERT outperforms its BERT counterpart on 6 different NLU tasks. Consistent with the empirical results in English by Lan et al., KoreALBERT seems to improve downstream task performance involving multi-sentence encoding for Korean language. The pretrained KoreALBERT is publicly available to encourage research and application development for Korean NLP.

cs.CL↗

arXiv2019

Clear the Fog: Combat Value Assessment in Incomplete Information Games with Convolutional Encoder-Decoders

StarCraft, one of the most popular real-time strategy games, is a compelling environment for artificial intelligence research for both micro-level unit control and macro-level strategic decision making. In this study, we address an eminent problem concerning macro-level decision making, known as the 'fog-of-war', which rises naturally from the fact that information regarding the opponent's state is always provided in the incomplete form. For intelligent agents to play like human players, it is obvious that making accurate predictions of the opponent's status under incomplete information will increase its chance of winning. To reflect this fact, we propose a convolutional encoder-decoder architecture that predicts potential counts and locations of the opponent's units based on only partially visible and noisy information. To evaluate the performance of our proposed method, we train an additional classifier on the encoder-decoder output to predict the game outcome (win or lose). Finally, we designed an agent incorporating the proposed method and conducted simulation games against rule-based agents to demonstrate both effectiveness and practicality. All experiments were conducted on actual game replay data acquired from professional players.

cs.AI↗