Michal Sutter is a data science professional with a Master of Science in Data Science from the University of Padova. With a solid foundation in statistical analysis, machine learning, and data ...

In the traditional cascade modeling approach, automatic speech recognition (ASR) first produces a single text string, which is then passed to retrieval. Small transcription errors can change query ...

As AI agents evolve beyond simple chatbots, new design patterns have emerged to make them more capable, adaptable, and intelligent. These agentic design patterns define how agents think, act, and ...

ROMA provides a setup.sh quick start with Docker Setup (Recommended) or Native Setup, plus flags for E2B sandbox integration (--e2b, --test-e2b). The stack lists Backend: Python 3.12+ with ...

ACE positions “context engineering” as a first-class alternative to parameter updates. Instead of compressing instructions into short prompts, ACE accumulates and organizes domain-specific tactics ...

Flow-GRPO (Flow-based Group Refined Policy Optimization) converts long-horizon, sparse-reward optimization into tractable single-turn updates: Benchmarks. The research team evaluates four task types: ...

What if an AI agent could localize a root cause, prove a candidate fix via automated analysis and testing, and proactively rewrite related code to eliminate the entire vulnerability class—then open an ...

Optimizing only for Automatic Speech Recognition (ASR) and Word Error Rate (WER) is insufficient for modern, interactive voice agents. Robust evaluation must measure ...

Most learning-based speech enhancement pipelines depend on paired clean–noisy recordings, which are expensive or impossible to collect at scale in real-world conditions. Unsupervised routes like ...

TUMIX runs a group of heterogeneous agents—text-only Chain-of-Thought, code-executing, web-searching, and guided variants—in parallel, then iterates a small number of refinement rounds where each ...