work

recommendation systems, from the model to the machinery.

SANSA / same weights, less waiting ↗

Reuse residual columns and trim sparse computation while keeping the resulting weights unchanged.

My optimization of SANSA execution; draft PR in my fork.

Reuse learned relationships with different views of user history, then rank forty catalogue nodes.

My component was retrieval; Grigory Vyaznikov worked on ranking.

Find an audience through author history, then allocate users across videos under a shared budget.

Team solution; presented with Grigory Vyaznikov.

Keep retrieval evidence separate through two candidate compressors, then explain the fixed ranking.

Team solution under AmazMe; the official entry is listed as vkost.

Keep learner histories causal while combining two boosting models and three neural checkpoints.

My published inference notebook, with Dean as editor; transformer experiments retain teammate credit.