ODSC West 2024
| title | author | length |
|---|---|---|
| Data infrastructure to build bigger with less | Ryan Boyd | 24m |
Argues that most analytics no longer need clusters by showing concrete results: DuckDB runs in-browser via WebAssembly and on laptops, a 13 billion‑row… | ||
| Building Agentic and Multi-Agent Systems with LangGraph | Chris the Whiz | 01h 59m |
Claims that LangGraph turns LangChain-style flows into graph-based cyclical loops that make adding agents and multi-agent teams simple, and demonstrates… | ||
| Preference Learning from Minimal Human Feedback for Interactive | Ardam Vik | 28m |
Argues robots learn objectives with far less human time by swapping demonstrations for comparisons and comparative language, using Bayesian IRL augmented with… | ||
| Dimensional Data Modeling in the Modern Era | Dustin Dorsey | 34m |
Argues that classic dimensional modeling still pays off by example: an existing one big table SQL pipeline on DBT on Databricks (≈1,000 lines) gets rebuilt… | ||
| Just Do Something with AI”: Bridging the Business Communication Gap for ML Practitioners | Stephanie Kirmer | 34m |
Explains why projects fail from miscommunication and gives a stepwise decision process: ask clarifying questions about the real business problem, align on what… | ||
| Lessons Learned Applying Large Language Models in Healthcare | Dr. David Talby | 33m |
John Snow Labs shows practical results: their medical LLMs top the Hugging Face open medical leaderboard across nine benchmarks, while GPT-4 makes 3× more… | ||
| AI-Powered ETL Pipeline Orchestration: Multi-Agent Systems in the Era of Generative AI | Brij Kishore Pandey | 27m |
Claims a working prototype that ties Apache Airflow, Kubernetes and an LLM-driven stack into agentic DAGs that run extraction, validation, AI-driven cleaning… | ||
| RAG Pipelines Letting You Down? Fitch Group's Solution for Financial Documents | Pablo Vega-Behar | 33m |
Three production RAG applications handle hundreds of thousands of financial reports by combining custom chunking with embeddings stored in Azure AI Search and… | ||
| Introduction to AI Agents | Sheamus McGovern | 02h 08m |
A practical course that shows how to wire LLMs to tools and storage, with working notebooks using LlamaIndex and LangChain demos, OpenAI keys, vector… | ||
| Challenges and Considerations in Language Model Evaluation | Lintang Sutawika | 31m |
Evaluation shows tiny prompt edits can flip scores from near 0% to high values, for example a trailing space or whitespace changes accuracy; few‑shot example… | ||
| Frontiers of Foundation Models for Time Series | Yan Liu | 33m |
Claims a practical path to foundation models for time series by building Temple — a prompt-based generative pretraining Transformer that decomposes inputs into… | ||
| Reinforcement Learning with Human Feedback | Luis Serrano | 29m |
Shows the actual pipeline: collect multiple model outputs per prompt and human-rank them (often 3/2/1), train a value network learns human scores as a reward… | ||
| nothing matches | ||