Blog & Notes

• 🛡️ AI Safety & Security: A Primer for the Agentic Era

  Safety and security: two seventy-year-old problems that agents finally fuse. A primer on where AI safety meets AI security — and why that seam is the story of the next few years.

  May 27, 2026 · AI Safety · AI Security · Agentic AI · Alignment · Guardrails

• 🧠 The Context We Can't Afford to Lose: Neural Networks from First Principles

  The artificial neuron is from 1943. The learning rule, 1958. Backprop, 1986. A primer that builds the foundations of neural networks from first principles — and previews the lineage all the way to today's LLMs and agentic systems.

  May 17, 2026 · nn-timeline · Neural Networks · Deep Learning · First Principles · Backpropagation · Transformer · LLMs · History of AI

• 🌐 Isometric MT: Neural Machine Translation for Automatic Dubbing

  Teaching a transformer to translate within ±10% of the source length directly — no N-best generation, no re-ranking — for length-matched automatic dubbing.

  May 22, 2022 · NMT · Automatic Dubbing · Length Control · Transformer

• 📄 Transfer Learning in Multilingual Neural Machine Translation with Dynamic Vocabulary

  A shared dynamic vocabulary lets an NMT model grow to new language pairs by transferring parameters — up to +13.63 BLEU while training in a fraction of the steps.

  Nov 01, 2018 · NMT · Transfer Learning · Multilingual · Low-Resource

• 📝 Paper Review: Phrase-Based & Neural Unsupervised Machine Translation

  Work investigates how to learn to translate when having access to only monolingual corpora in each language.

  Oct 24, 2018 · NMT · Unsupervised · Zero-Shot · Low-Resource

• ✍️ Neural Machine Translation into Language Varieties

  Training neural machine translation to produce specific language varieties and dialects, across pairs like Brazilian/European Portuguese and Croatian/Serbian.

  Oct 20, 2018 · NMT · Language Varieties · Multilingual

• 📄 A Comparison of Transformer and Recurrent Neural Networks on Multilingual Neural Machine Translation

  A comparative analysis of Transformer vs. recurrent architectures across bilingual, multilingual, and zero-shot translation — using professional post-edits and error categories, not just BLEU.

  Aug 25, 2018 · NMT · Transformer · RNN · Multilingual

• 🏆 Best Paper Award at IWSLT 2017

  Our paper “Improving Zero-Shot Translation of Low-Resource Languages” received the Best Paper Award at IWSLT 2017 in Tokyo.

  Dec 18, 2017 · Award · NMT · Zero-Shot · Low-Resource

• 📄 Improving Zero-Shot Translation of Low-Resource Languages

  An iterative self-training procedure that improves zero-shot translation for low-resource languages — without any parallel data for the target direction.

  Dec 17, 2017 · NMT · Zero-Shot · Low-Resource · Multilingual