Institution profile

Korea Advanced Institute of Science and Technology

Academic institutionasia · kr
Official website
Research library2,423linked papers
Opportunities0open roles
Selected work

Representative Papers

Child Sexual Abuse and the Internet—A Systematic Review

Jun 04, 2021Human Arenas

This study addresses the imbalance among technical skill development, social safety, and career advancement within the adolescent Roblox developer community—particularly amid frequent user conflicts and inadequate platform governance. Guided by the PRISMA framework, we systematically reviewed global literature on online child sexual abuse (CSA) published between 2000 and 2020, synthesizing findings across disciplines to propose the first interdisciplinary, multi-dimensional framework for studying CSA in networked digital environments. Through qualitative content analysis and thematic modeling of scholarly and technical reports, we identified 12 distinct patterns of online abuse and seven critical bottlenecks in detection and intervention technologies. Building on this, we introduce a tiered platform accountability assessment model that maps technical capabilities against regulatory responsibilities. The study contributes both a theoretical foundation and actionable design principles for fostering safe, inclusive, and sustainable digital creation ecosystems for adolescents.

31 citationsRead paper

Event-based Video Frame Interpolation with Cross-Modal Asymmetric Bidirectional Motion Fields

Jun 01, 2023Computer Vision and Pattern Recognition

Existing video frame interpolation (VFI) methods struggle to model realistic asymmetric, high-speed, and texture-rich motion in event-camera scenarios. To address this, we propose the first cross-modal asymmetric bidirectional motion field estimation framework for event-driven VFI: leveraging the complementary nature of event streams and intensity frames, it directly regresses asymmetric optical flow. We design EIF-BiOFNet—a novel neural architecture—and an interactive attention-based fusion module; additionally, we introduce ERF-X, the first high-frame-rate (170 FPS) event-based VFI benchmark featuring extreme motion and dynamic textures. Extensive experiments demonstrate that our method significantly outperforms state-of-the-art approaches across multiple datasets, achieving substantial PSNR and SSIM improvements—particularly under high-speed motion and complex texture conditions.

21 citations6 influentialRead paper

Conditional Temporal Neural Processes with Covariance Loss

Apr 01, 2025International Conference on Machine Learning

Neural processes often fail to accurately model dependencies between inputs and targets under noisy observations. To address this, we propose the Covariance Loss—a novel objective that explicitly incorporates second-order statistical dependencies among target variables into the end-to-end training of conditional neural processes for the first time. By regularizing the covariance structure of the predictive distribution, our loss enhances the model’s ability to recover missing or degraded dependencies and improves robustness to observation noise. The method is architecture-agnostic and can be seamlessly integrated into mainstream neural process frameworks. Extensive experiments across multiple real-world time-series and regression benchmarks demonstrate consistent and significant improvements over state-of-the-art methods in three key aspects: predictive accuracy, fidelity of dependency structure recovery, and robustness to observational noise.

15 citationsRead paper

Imitating and Finetuning Model Predictive Control for Robust and Symmetric Quadrupedal Locomotion

Nov 01, 2023IEEE Robotics and Automation Letters

To address the challenge of achieving robust, symmetric, periodic, and energy-efficient gaits for quadrupedal robots on unstructured terrains—including uneven ground, slippery surfaces, and moving conveyor belts—this paper proposes an “Imitation–Fine-tuning” collaborative control framework (IFM). IFM innovatively employs a model predictive controller (MPC) combining differential dynamic programming with Raibert-inspired heuristics as an expert policy, which is first rendered learnable via behavioral cloning and subsequently refined safely using low-exploration-depth PPO or SAC reinforcement learning. Comprehensive simulation and hardware experiments demonstrate that IFM significantly improves gait stability and left–right symmetry, generates more periodic and energy-efficient locomotion patterns, and eliminates the need for intricate reward engineering. The framework achieves a favorable trade-off among safety, environmental adaptability, and deployment efficiency.

15 citationsRead paper

Too Many Frames, not all Useful: Efficient Strategies for Long-Form Video QA

Jun 13, 2024arXiv.org

Long-form video question answering (LVQA) suffers from high visual redundancy and sparse salient information, while existing methods inefficiently process uniformly sampled frames via independent vision-language model (VLM) descriptions, leading to poor semantic utilization. To address this, we propose the Hierarchical Keyframe Selector (HKFS), the first framework to jointly perform question-guided dynamic temporal segment localization and semantic keyframe selection. HKFS integrates multi-granularity temporal modeling, question-driven visual attention, and a lightweight VLM adaptation architecture—LVNet—to substantially reduce visual-language modeling overhead. Our approach achieves state-of-the-art performance on three major LVQA benchmarks—EgoSchema, NExT-QA, and IntentQA—and demonstrates strong generalization on VideoMME. Notably, it supports LVQA over videos up to one hour in length, enabling scalable, efficient, and semantically grounded long-video understanding.

12 citations2 influentialRead paper
Recent publications

Latest Papers