
Learn to automatically select vector indexes and prompts for document QA using Langchain router chains, with code demos for Streamlit and terminal applications.

Explore cutting-edge advancements in non-interactive secure multi-party computation, including reusable NISC, witness encryption, and overcoming limitations in two-party and multi-party settings.

Explore messaging security, key updates, and encryption debates in this cryptography session, covering UPIBE, moderation challenges, and group signature compilers.

Comprehensive hands-on introduction to Linux: install Ubuntu, manage software, customize settings, use command line, create users, and set up development environments for web, Python, and C++.

Explore information-theoretic approaches to enhance privacy and fairness in collaborative AI systems, focusing on trustworthy machine learning techniques.

Explore information-theoretic approaches to group fairness and predictive multiplicity in machine learning, examining their limitations and implications for trustworthy AI systems.

Explore information-theoretic constraints in decision-making processes, focusing on applications in trustworthy machine learning and their impact on algorithmic outcomes.

Explore information-theoretic methods for trustworthy ML, focusing on fairness, explainability, and legal compliance in critical applications.

Explore variational formulations and distributed convex optimization methods in information-theoretic approaches to trustworthy machine learning.

Explore the training process behind ChatGPT, including generative pretraining, supervised fine-tuning, and reinforcement learning through human feedback. Gain insights into AI language model development.

Explore scientific software packaging using Conda-Forge with Jan Janssen from Los Alamos National Laboratory, focusing on co-design for exascale computing and hackathon applications.

Comprehensive guide to training custom LLMs: from data processing and tokenization to evaluation and deployment, with insights on tools, best practices, and essential skills for LLM engineers.

Explore tool-using language models with long-term memory in this comprehensive overview of AI agents, covering key concepts, challenges, and real-world examples from LangChain's co-creator.

Explore data poisoning's impact on machine learning, its detection methods, and strategies for building robust models against adversarial attacks in this informative talk.

Explore information-theoretic approaches to fair risk minimization in machine learning, focusing on trustworthy AI and ethical considerations in algorithm design.

Explore an asymptotic toy model revealing intriguing aspects of overparameterized learning, with insights into information-theoretic methods for trustworthy machine learning.

Explore advanced gradient quantization techniques for machine learning, focusing on differential methods and their impact on algorithm efficiency and performance.

Explore user-level privacy and communication constraints in distribution estimation, focusing on information-theoretic methods for trustworthy machine learning.

Explore information-constrained optimal transport theory and its applications in trustworthy machine learning with Stanford researcher Ayfer Ozgur.

Learn a systematic approach to troubleshoot deep neural networks, from starting simple to tuning hyperparameters, with practical strategies for implementation, debugging, evaluation, and improvement.

Comprehensive overview of ML infrastructure and tools, covering software engineering, computing, resource management, frameworks, experiment management, and hyperparameter optimization for practitioners.