AutoMoE - Neural Architecture Search for Efficient Sparsely Activated Transformers
Discover how Neural Architecture Search optimizes Transformer models through sparse activation, achieving 4x FLOP reduction while maintaining performance in machine translation tasks.
Neural Fine-Tuning Search for Few-Shot Learning
Explore advanced neural architecture search techniques for optimizing few-shot learning adaptation strategies, focusing on meta-training and meta-testing trade-offs in multi-domain contexts.
Multi-objective Differentiable Neural Architecture Search
Explore advanced techniques in neural architecture optimization across multiple objectives and hardware devices, focusing on Pareto front profiling and hypernetwork-based solutions.
Mixture-of-Supernets - Improving Weight-Sharing Supernet Training with Architecture-Routed MoE
Explore cutting-edge research on Mixture-of-Supernets architecture that enhances neural architecture search efficiency and improves BERT and MT model performance through innovative weight-sharing techniques.
Searching for Neural Architectures from Fundamental Operations - An Introduction to einspace
Explore neural architecture search through einspace, a novel approach using fundamental operations to discover diverse and competitive network architectures for machine learning tasks.
Prompt Engineering - Steps Towards AI Native Tooling
Explore the evolving landscape of AI-native tooling through prompt engineering, from code generation to creative applications, while understanding its impact on the future of technology and development.
Grand Theft Actions - Abusing Self-Hosted GitHub Runners for Supply Chain Attacks
Dive into critical security vulnerabilities in GitHub Actions, exploring real-world attacks on self-hosted runners and learning how to prevent supply chain compromises in major open-source projects.
Incubated ML Exploits: Backdooring Machine Learning Pipelines with Input Handling Bugs
Explore machine learning pipeline vulnerabilities and learn to identify, exploit, and defend against model backdoors through input handling bugs and systematic security approaches.
PyTorch Tutorial: Deep Learning Framework Fundamentals - Fall 2022
Master PyTorch fundamentals and deep learning concepts, from tensor operations to GPU acceleration, autograd, and data loading - all through hands-on coding examples and practical implementations.
Online Learning for Hierarchical Inference
Explore hierarchical inference optimization through online learning algorithms, focusing on efficient distributed inference between edge devices and cloud servers using confidence metric thresholds.
인공지능 기반 펀드 운용 시스템: AI-Advisor의 개발과 적용
Discover how SK's AI-powered robo-advisor revolutionizes fund management through deep learning and reinforcement learning, offering innovative solutions for financial investment products and market strategies.
There Is No Such Thing as Artificial Intelligence - Understanding AI Myths and Realities
Explore the misconceptions about AI with Luc Julia as he debunks Hollywood myths, examines real technological advances, and discusses the future potential of machine learning and deep learning technologies.
How Deep Learning is Revolutionizing Sports Analytics
Explore how deep learning transforms sports analytics through player tracking, performance analysis, and data-driven decision making to revolutionize team strategies and viewer experiences.
Multi-Task Learning in Transformer-Based Architectures for Natural Language Processing
Explore multi-task learning in transformers, covering adapter techniques, hypernetworks, and efficient solutions for training multiple NLP tasks with shared architectures and reduced computational costs.
RETINA: Exploring Computational Storage with SmartSSD for Key-Value Storage and Deep Learning
Discover how Computational Storage and Samsung SmartSSD accelerate key-value storage engines and deep learning workloads through RETINA's cross-layered approach to near-data processing and performance optimization.
Toward Sustainable Coastal Environments: Coastal Hazards and Machine Learning
Explore innovative machine learning approaches for coastal hazard forecasting, assessment, and risk management, addressing challenges in tsunami and storm surge modeling for sustainable coastal environments.
Machine and Deep Learning Applications in the Permian Basin
Explore innovative ML and DL techniques for 3D lithofacies prediction and fault detection in Permian Basin reservoirs, enhancing accuracy and efficiency in subsurface characterization.
Fast Deep Learning with Categories
Explore GPU-accelerated deep learning using Haskell, ConCat, and Accelerate for high-performance industrial applications.
Comparing Elixir and Python for Simple Neural Networks
Compare Elixir's Nx library with Python's machine learning ecosystem for training neural networks. Explore development experiences and performance differences using MNIST and CIFAR-10 datasets.
Large Language Models for Computational Biology - A Primer
Explore large language models in computational biology, covering transformers, pretraining, and applications in genomics and single-cell analysis.
Characterization of Genomic Structural Variation Using Various Sequencing Technologies
Explore genomic structural variation analysis using diverse sequencing technologies. Learn about copy number variation genotyping and deep learning applications in exome sequencing.