Exploiting Voice Cloning in Adversarial Simulation - Security Testing and Defense Strategies
Explore the security vulnerabilities of voice verification systems through deep learning voice cloning techniques, including practical demonstrations, risk assessment, and defensive countermeasures.
Medical Insight+ - AI Medical Device for Rapid and Accurate Diagnosis of Emergency and Severe Brain Diseases
Discover how Medical Insight+ AI medical device revolutionizes emergency brain disease diagnosis through rapid CT image analysis, supporting healthcare professionals across Korean hospitals for accurate patient care.
X-RAY 영상 AI 모델을 이용한 자동 진단
Discover how AI models can revolutionize medical diagnosis through X-ray image analysis in this innovative presentation from student researchers at the SK TECH SUMMIT 2023.
AI Innovations Through Deep Learning and Generative AI
Explore how deep learning and generative AI innovations transform business models, featuring insights from Moloco CEO and former Google tech lead on AI commercialization and growth strategies.
In2Out - Video Outpainting Using Discriminator Loss Design
Dive into 비디오 outpainting 기술의 혁신적 접근법과 Discriminator Loss 설계 방법론을 통해 AI 영상 처리의 최신 연구 성과를 탐구합니다.
AI Music Recommendation System Based on User Emotions and Context
Discover how FLO's innovative AI system uses multi-modal deep learning to match music playlists with users' moods and situations, creating personalized recommendations through advanced text-audio mapping and 2-stage architecture.
Squash - 딥러닝 서비스 추론 속도 개선기
Discover how Squash technology optimizes deep learning inference speed and reduces hardware costs through innovative model compression techniques for efficient AI service deployment.
물성 예측 마법사 - 화학과 딥러닝의 만남으로 세상을 예측하다
Discover how deep learning and chemistry combine to predict semiconductor material properties, revolutionizing development processes by reducing experimental needs and optimizing efficiency in manufacturing.
Personalized AI Voice Technology: Text-to-Speech Systems and Voice Cloning
Discover SK텔레콤's innovative TTS technology that enables voice generation in anyone's voice, exploring its applications from AI assistants to gaming and human-machine interfaces.
이미지 센서에서의 딥러닝 모델 최적화와 구현 - SK 하이닉스의 On-Sensor AI 여정
Discover how SK Hynix engineers integrate deep learning models into image sensors, exploring AI semiconductor technology for enhanced mobile device functionality and image quality optimization.
Deep Learning Models for Autonomous Driving
Discover the latest autonomous driving deep learning models and innovations from Silicon Valley, featuring insights from a former Tesla Autopilot R&D expert and current Phantom AI CEO.
Parallel Processing for Stable Diffusion Using TPU - Speed Optimization Guide
Master parallel processing in Stable Diffusion using TPUs and JAX/FLAX libraries to generate AI art 8x faster, achieving remarkable speeds of 8 images in just 4 seconds.
Node Classification with Graph Convolutional Networks for Graph Machine Learning
Master Graph Convolutional Networks (GCN) implementation in PyG for node classification, featuring practical coding examples and theoretical foundations of spectral graph convolutions.
JAX vs PyTorch 2 - Converting Stateful to Stateless Operations in Neural Networks
Explore functional programming in JAX through hands-on comparison with PyTorch 2, focusing on neural network implementation and stateless operations for gradient descent.
MusicGen: Understanding Meta AI's Music Generation Model Architecture
Delve into Meta AI's MusicGen architecture, exploring vector quantization, melody conditioning, and interleaving patterns for high-quality AI music generation in just 13 minutes.
Understanding Robotics Transformer 2 (RT-2) - A Deep Dive into DeepMind's Vision-Language-Action Model
Explore DeepMind's RT2 model and discover how it bridges language models with robotics to enable intelligent reasoning and action in autonomous systems.
Machine Learning and the Future of Creative Expression - How AI is Transforming Creativity
Explore how AI and machine learning are revolutionizing creative expression, from text-to-image generation to broader implications for human creativity and artistic innovation.
Audio Data Augmentation: Techniques, Theory, and Implementation
Discover essential audio data augmentation techniques for machine learning, from time shifting to frequency masking, with practical Python implementations and best practices for enhancing audio datasets.
AI for Autonomous Mobile Robots - Computer Vision and Navigation Systems
Explore how AI and computer vision enable autonomous mobile robots to navigate safely alongside humans in logistics, focusing on deep learning, mapping, and advanced navigation algorithms.
Analysis of Sports Scenes Using Computer Vision Models
Explore computer vision applications in sports analysis, from player detection to performance monitoring, using deep neural networks with practical experiments in handball scene analysis.
Towards the Universal Law of Robustness for Deep Neural Networks
Explore fundamental developments in neural network robustness, focusing on overparametrized models and the BLN Conjecture through geometric visualization and practical applications.