Preparing Fineweb - A Finely Cleaned Common Crawl Dataset for Language Models
Explore Common Crawl data processing, comparing datasets like C4 and RefinedWeb. Learn about quality filters, deduplication strategies, and LLM-assisted filtering for creating high-quality datasets like Fineweb Edu.
Improving LLM Accuracy with Monte Carlo Tree Search
Explore Monte Carlo Tree Search to enhance LLM accuracy, focusing on boosting Llama 3 8B performance. Learn implementation, testing, and limitations through code examples and mathematical problem-solving.
RAG with Verified Citations - Advanced Inference Techniques
Explore advanced RAG techniques with verified citations, including BM25 and cosine similarity methods. Learn to implement and leverage one-click document RAG for improved accuracy.
The Magic of Merlin - Shopify's New Machine Learning Platform
Explore Shopify's Merlin ML platform, its open-source stack, architecture, and how it scales ML work using Ray.
Scalable Feature Engineering with Hamilton on Ray
Explore scalable feature engineering using Hamilton and Ray at StitchFix. Learn declarative dataflow, team scaling, and efficient computation for thousands of time-series features.
FastCFE - A Counterfactual Explainer Using Reinforcement Learning
Explore reinforcement learning for real-time counterfactual explanations in machine learning explainability. Learn about FastCFE algorithm, OpenAI Gym, and Ray+RLlib for actionable insights in various applications.
Cruise.data - A New Dataset Processing Pipeline for Cruise ML
Explore Cruise.data, a novel ML data pre-processing framework combining tf.data, PyTorch, and large-scale processing capabilities for efficient and scalable dataset handling in autonomous vehicle development.
A Cross-Platform, Cross-Tool Ray on Kubernetes Deployment
Deploy Ray, Spark, Dask, and Jupyter on mixed-architecture Kubernetes clusters. Learn cross-building containers, handling Ubuntu versions, and glibc versioning for heterogeneous Ray clusters.
Enterprise Vector-based Information Retrieval and Prompt Engineering at Scale Using Open Source on AWS
Build enterprise-scale vector-based information retrieval systems using open source technologies on AWS, addressing challenges in Retrieval Augmented Generation for accurate, hallucination-free results.
Perplexity AI: Building the World's Best LLM-Powered Search Engine in 6 Months
Explore the engineering challenges and opportunities in building Perplexity.ai, an LLM-powered answer engine, with insights from founder Aravind Srinivas on rapid development and resource optimization.
Wandering Through Sequence Space
Explore protein sequence space and its implications for evolution, structure, and function with insights from statistical physics and machine learning.
Inferring Phylogeny and Function from Different Sequence Spaces
Explore phylogeny and function inference using diverse sequence spaces, led by Alessandra Carbone from CNRS and Sorbonne Université.
New Directions in Correlation Clustering and Biclustering
Explore advanced techniques in correlation clustering and biclustering, focusing on novel approaches and applications in data analysis and machine learning.
Interpreting Deep Neural Networks Towards Trustworthiness
Explore methods for interpreting neural networks, including contextual decomposition and adaptive wavelet distillation, to enhance model trustworthiness and performance.
Perception of Visual Art and Topological Data Analysis
Explore topological data analysis applications in visual art perception, comparing eye movements for abstract paintings vs. AI-generated images using algebraic topology methods.
Learning with Missing Values: Theoretical Insights and Application to Health Databases
Explore theoretical insights and practical applications of learning with missing values in health databases, focusing on regression, classification, and neural network solutions.
Weak Signals: Machine Learning Meets Extreme Value Theory
Explore machine learning's intersection with extreme value theory, focusing on angular measure recovery and its applications in classification and anomaly detection.
Pinecone Vector Database - Build Knowledgeable AI
Discover vector databases' advantages, explore Pinecone's innovative features, and watch a live demo on getting started with its powerful search capabilities.
Advanced RAG Scenarios: Building Your Own Database Agents - Developing AI Agents for Natural Language Database Interaction
Develop AI agents for natural language database interactions, enabling efficient data querying and analysis without advanced SQL knowledge.
Persistent Homology of Plant-Pollinator Interactions - The Importance of Flowering Plant Surveys
Explore persistent homology in plant-pollinator interactions, analyzing topological features and the impact of flowering plant surveys on understanding community structures.
The Promise and Challenge of Harnessing Collateral Information from Medical Images Using AI
Explore AI's potential in extracting collateral information from medical images, discussing promises and challenges in this field.