Educational Cards

Learn from video content, text, and interactive tasks

Filters
Clear
Masking bugs and leakage

Two mask families appear in almost every codebase. Padding masks zero out attention to padded...

Advanced Machine learning
Efficient attention approximations (concept map)

Full softmax attention costs O(n^2) per layer in sequence length. When n reaches tens of thousands,...

Advanced Machine learning
Parametric memory is distributed, not a tidy file cabinet

When a model answers "Paris is the capital of France," where did that fact live? Not in a single...

Advanced Machine learning
MLP neurons as key-value-ish nonlinear transforms

Transformer MLP blocks widen activations, apply a smooth gate (GeLU, SiLU), then project back to...

Advanced Machine learning
Catastrophic forgetting and continual learning pain

Fine-tuning updates weights to fit new data. Those same weights encoded prior abilities;...

Advanced Machine learning
Sparse autoencoders and feature directions

Sparse autoencoders (SAEs) train on internal activations to reconstruct them from a larger sparse...

Advanced Machine learning
Retrieval-augmented generation and tool use

Parametric weights cannot stay current with the live web. Retrieval-augmented generation (RAG)...

Advanced Machine learning
Knowledge editing and limits of surgical updates

Can you patch one fact without retraining? Methods like ROME and MEMIT attempt localized weight...

Advanced Machine learning
Diffusion intuition: destroy, then learn to undo

Diffusion models run a forward process that gradually adds noise until data looks almost Gaussian,...

Intermediate Machine learning
Video is harder than still images (temporal coherence)

Independent per-frame generation produces flicker : object identity, lighting, and texture jump...

Intermediate Machine learning
Engineering trade-offs: steps, guidance, distillation

Interactive systems cannot run 1000 denoising steps per click. Knowledge distillation trains a...

Intermediate Machine learning
Safety stacks beyond the loss function

Minimizing denoising loss does not prevent misuse. Production stacks layer refusal policies ,...

Intermediate Machine learning