Build Wiz AI Show
Episodes
The First Few Tokens Are All You Need: An Efficient and Effective Unsupervised Prefix Fine-Tuning Method for Reasoning Models
06 Mar 2025
Contributed by Lukas
The provided paper introduces Unsupervised Prefix Fine-Tuning (UPFT), a novel method to improve the reasoning abilities of large language models. Thi...
Building Effective LLMs Agents
06 Mar 2025
Contributed by Lukas
Anthropic's article explores building effective AI agents using Large Language Models (LLMs), emphasizing simple and composable patterns over com...
Model Context Protocol (MCP) Explained
05 Mar 2025
Contributed by Lukas
Marco Codes' YouTube video explains the Model Context Protocol (MCP), an initiative by Anthropic (creators of Claude) that allows language models ...
LazyGraphRAG: High-Quality, Low-Cost Graph-Enabled RAG
05 Mar 2025
Contributed by Lukas
Microsoft Research presents LazyGraphRAG, a novel approach to Retrieval-Augmented Generation (RAG) that blends vector and graph-based search methods. ...
Retrieval Augmented Generation Architectures
05 Mar 2025
Contributed by Lukas
Conor Kelly's article explores Retrieval Augmented Generation (RAG) architectures, a technique enhancing large language models (LLMs) by integrati...
Graph RAG: A Query-Focused Summarization Approach
05 Mar 2025
Contributed by Lukas
This research introduces Graph RAG, a novel approach to enhance question answering over large text collections by combining knowledge graphs and retri...
DeepSeek-R1: Reasoning via Reinforcement LearningDeepSeek-R1: Reasoning via Reinforcement Learning
04 Mar 2025
Contributed by Lukas
DeepSeek-AI introduces DeepSeek-R1, a reasoning model developed through reinforcement learning (RL) and distillation techniques. The research explore...
Google Cloud AI Business Trends 2025
04 Mar 2025
Contributed by Lukas
Google's "AI Business Trends 2025" report analyzes key strategic trends expected to reshape businesses. It identifies five major trends...
LLM Post-Training: Reasoning, Reinforcement Learning, and Scaling
04 Mar 2025
Contributed by Lukas
This podcast presents a comprehensive survey of post-training techniques for Large Language Models (LLMs), focusing on methodologies that refine these...