Academia

Montréal, Canada

Université de Montréal & Mila

Bengio's lab produced the attention mechanism and the generative-adversarial idea — two of the three pillars the current era stands on.

3 key findings1 timeline milestones1 sources to follow

Key findings

  1. 2014

    Neural machine translation by jointly learning to align and translate

    Bahdanau, Cho, Bengio

    Introduced an attention mechanism letting a decoder look back at any encoder state instead of one fixed vector.

    Why it matters here · Attention, three years before Transformers. Every model in the catalog runs a scaled variant of this idea.

  2. 2014

    Generative Adversarial Networks

    Ian Goodfellow et al.

    Two networks in a minimax game: a generator producing samples, a discriminator judging them.

    Why it matters here · Dominated image generation until diffusion took over, and adversarial training still underpins evaluation and red-teaming practice.

    min_G max_D V(D,G)
  3. 2003

    A Neural Probabilistic Language Model

    Bengio, Ducharme, Vincent, Jauvin

    Learned distributed word representations and a language model jointly, beating n-gram baselines.

    Why it matters here · The first neural language model — the direct ancestor of the whole LLM line.

On the history timeline

Milestones on the 1943 → today timeline credited to this institution.

  • 2014Generative Adversarial NetworksIan Goodfellow et al.Deep learning boom

What to follow