Michael Banf
where else to find them
linkedin:michaelbanf
what they talk about
where they keep going back
no series more than once — all 2 in the filters
on a stage with
- Liliya Imashevaonce
who talks about the same things
nobody close enough yet
| title | conference | date |
|---|---|---|
| Validation Pipeline for Summary Evaluation | Conf42 Large Language Models (LLMs) 2026 | 2026-06-18 |
Built a reproducible LLM-as-judge pipeline that scores summaries on five expert-defined Likert dimensions, binarizes them (1–3 = bad, 4–5 = good), and reports… | ||
| Building Evolving AI Agents Via Dynamic Memory Representations Using Temporal Knowledge Graphs | NODES 2025 | 2025-11-06 |
Claims a practical memory architecture that layers Neo4j + LangGraph + Graphiti to store evolving agent memory, extracts entities with Pydantic entity schemas… | ||
| nothing matches | ||