Sparse to Dense: A New Fall Course on Information Retrieval for AI
coallaoh · x · 2026-08-13
The author is teaching a course this autumn on how AI systems acquire knowledge they don't inherently hold: Information Retrieval for AI. The curriculum is structured around two main axes:
- Sparse to dense retrieval methods.
- Parametric to non-parametric knowledge: covering model weights, MoE (Mixture of Experts), indexing within the forward pass, and RAG (Retrieval-Augmented Generation).
More from Research
- Introducing ReactBench: A Frontend Coding Benchmark Beyond Passing Tests — aidenybai · 2026-08-14
- Artificial Analysis Launches Optima for Custom LLM Benchmarking — ArtificialAnlys · 2026-08-13
- Context Compactors Silently Drop 83% of Standing Rules, New COMPINT Suite Reveals — dair_ai · 2026-08-13
- Researcher Disputes ARC-AGI Uniqueness: Most Benchmarks Show Thinking Model Transitions — scaling01 · 2026-08-13
- qeep: A Deep Learning Framework in Go with Tensors, AutoGrad, and CUDA — tom_doerr · 2026-08-13
- Grounding Agents with Markdown Wikis: An Agentic Workflow for Economists — aniketapanjwani · 2026-08-13