Jakub Zavrel
where else to find them
no profile links on file
what they talk about
where they keep going back
no series more than once — all 3 in the filters
on a stage with
who talks about the same things
- Fernando Rejon Barrera3 talks
- Naresh Dulam2 talks
- Yuval Belfer2 talks
- Bartek Sadlej3 talks
- Trey Grainger2 talks
- Jeff Vestal5 talks
| title | conference | date |
|---|---|---|
| Unconference: Self-optimizing deep research agents | OpenSearchCon North America 2025 | 2025-09-08 |
Claims that modular, non-differentiable deep research agents can self-optimize using an LLM to critique and rewire prompts and pipelines, evaluated on… | ||
| From Deep Research to Evaluation and Optimization of Advanced AI Age... | AI_dev Europe 2025 | 2025-08-28 |
A modular Deep Research agent is built with planner extractor merger writer stages that call hybrid search (BM25 + vectors + rerankers) and RAG on private… | ||
| Fine-tuning embeddings 4 vector search | OpenSearchCon Europe 2024 | 2024-05-06 |
OpenSearch users fine-tune embeddings for RAG by generating supervised pairs from their documents with the open‑sourced impar toolkit that uses generative… | ||
| RAGElo: An Elo Rating-based Evaluation Toolkit for RAG | OpenSearchCon Europe 2024 | 2024-05-06 |
RAGElo is an open-source toolkit that ranks RAG pipeline variants by running pairwise Elo ranking matches where an LLM judges two answers plus their retrieved… | ||
| nothing matches | ||