Oriol Vinyals
VERIFIED TECHNICAL DOSSIERSources checked

Oriol Vinyals

VP of Research & Deep Learning Lead, Google DeepMind | Co-Creator of AlphaStar & Gemini

2 Verified ArtifactsSource Checked & Attributed

Verified Proof of Work Artifacts

2 items cataloged

Each artifact below represents an authenticated research publication, production code repository, or technical architectural framework directly authored or co-created by Oriol Vinyals. Every entry undergoes editorial source verification.

#1
RESEARCH Checked Sep 23, 2026

Show and Tell: A Neural Image Caption Generator

Pioneered the integration of deep convolutional neural networks (CNNs) for vision encoding with recurrent language models (RNNs) for text generation, producing the first end-to-end neural image captioning pipeline.

Model & Execution Context:GoogLeNet CNN feature extractor combined with LSTM language decoder on MSCOCO dataset.
Scope & Limitations

Susceptible to hallucinating objects based on strong linguistic prior frequencies rather than verified visual presence.

#2
RESEARCH Checked Sep 23, 2026

Grandmaster Level in StarCraft II using Multi-Agent Reinforcement Learning (AlphaStar)

Led the AlphaStar research team combining imitation learning, multi-agent league training, and deep transformer-based recurrent policies to master StarCraft II—operating under imperfect information, long-horizon real-time strategy, and high-dimensional action spaces.

Model & Execution Context:Multi-agent league self-play across 35 days of TPU v3 training per agent with human-like action rate limits.
Scope & Limitations

League diversity must be actively curated with dedicated exploiters to prevent cyclic policy stagnation.