Tensor arithmetics in search and ranking for Ecommerce.
Small, domain-specific vision models can dramatically enhance the buyer search experience by delivering more relevant visual understanding. But the real opportunity comes from controllable image embeddings: by fusing base search embeddings with additional control vectors, representing features such as color, shape, and style,
Relevance Feedback Inside the Search Engine
How does searching for new information often look? Loops: query, review results for relevance, rewrite the query, repeat… Until success, or until the user churns / the token budget burns.
This talk introduces a new instrument for search pipeline builders: propagating query-results relevance right inside the search algorithm of a search engine.
Search is Back: Solving the “Context Crisis” for AI Agents
Why do smart agents make dumb mistakes? The culprit is context, an old problem with new solutions. Let’s fast-forward through 20 years of search evolution to fix the missing link in today’s Agentic AI.
We’ll demonstrate how to combine Knowledge Graphs and Vector Search to build reliable, context-aware applications using open-source tools.
Scientific Data Under Threat in Today’s America
A brief look at how scientific data came under political pressure during the presidency of Donald Trump, and how scientists and data repositories in Europe worked to protect public access to evidence-based research, ensuring access for data science in a well-structured way.
Real-Time ML Pipelines: Feature Chaining with Chronon
Modern ML applications demand features computed in near real-time with sub-100ms latencies. This talk dives into Chronon, an OSS feature platform bridging streaming data infrastructure and production ML. Using a two-tower search pipeline example, we’ll show how we can chain embeddings with tabular features while minimizing hot-path computation.
Detecting Hidden Bias in Datasets Before Models Fail
Hidden bias in datasets silently breaks machine learning systems in production. This talk shows how to detect data imbalance, leakage, and coverage gaps early using practical metrics, visualizations, and open-source tools—before misleading offline metrics turn into costly real-world failures.
Sunset for the Wild West: Making ML disciplined by default
Many novel machine learning techniques started as clever hacks that just happened to work, but the demands of building real systems can be at odds with this creative culture. Learn about our open-source stack to improve quality-of-life for ML researchers and infrastructure teams alike — and how their concerns aren’t as different as you might think.
When better retrieval makes agents worse
Agentic systems can break not because information is missing, but because persuasively wrong context gets promoted into action. We examine a recurring pattern: retrieval metrics improve while agent behavior degrades as distractors enter multi-step loops. We show why relevance, reliability, and security are tightly connected in agentic retrieval.
Observability’s Sixth Sense: Detecting Anomalies in Metrics
In this talk, we look at anomaly detection as a complementary way of working with metrics. Instead of relying on predefined limits, anomaly detection focuses on identifying behavior that deviates from what is normally observed over time. The focus is on how developers can interpret these signals, where anomaly detection is useful, where it is not.
The Failures That Don’t Crash: MLOps for AI Agents
This talk takes four reliability patterns from distributed systems and shows what they look like inside an agent architecture. How to shadow-test an agent. Why your circuit breakers need confidence thresholds. What an eval harness looks like when your system is non-deterministic. And why human oversight degrades faster than anyone admits.