Join our in-person meetup to hear talks from experts on cutting-edge topics across AI, ML, and computer vision. View more CV events here.

The presence of AI agents in the tech scene has skyrocketed in 2025, and is continuing to grow in 2026: from Manus to Claude Code, they are making their way to the everyday life of everyone of us.

But what makes a good AI Agent? In this talk we'll try to give an answer to this question, by going through the anatomy of one, exploring topics such as how an agent thinks and acts, how it interacts with the external environment (the filesystem, e.g.), how we can harness it to control its flow and how we can provide the right context to it, avoiding hallucinations.

This talk shows how to build a systematic, interactive map of an entire conference using modern open-source tools. We load all 177 papers from 3DV 2026 (full PDF page images plus metadata) into a FiftyOne grouped dataset. We then run three annotation passes using Qwen3.5-9B on each cover page: topic classification, author affiliation extraction, and project page detection. Document embeddings from Jina v4 are computed across all 3,019 page images, pooled to paper-level vectors, and fed into FiftyOne Brain for UMAP visualization, similarity search, representativeness scoring, and uniqueness scoring.

The result is an interactive dataset you can query, filter, and explore in the FiftyOne App. Sort by uniqueness to find distinctive work, filter by topic and sort by representativeness to understand each research area, and cross-reference with scheduling metadata to build a personal agenda.

I demonstrate the end-to-end pipeline and discuss design decisions regarding grouped datasets, reasoning model output parsing, and embedding pooling strategies.

Artificial intelligence and machine learning are rapidly transforming manufacturing by enabling data-driven optimization across the entire production process. This presentation highlights proven industrial use cases, including automated visual inspection, process parameter optimization, intelligent production plannung, and cognitive robotics, demonstrating measurable gains in quality, uptime, and cost efficiency. It also briefly introduces a methodology to identify and prioritize use cases. The talk ends with exploring emerging technologies such as AI-based simulation or Embodied AI.