Hypencoder replaces the query vector with a query-generated neural network that scores document vectors, and reports consistent gains over dense retrieval baselines across standard, out-of-domain, and hard retrieval benchmarks.
Mathematische Annalen , year =
3 Pith papers cite this work, alongside 220 external citations. Polarity classification is still indexing.
3
Pith papers citing it
220
external citations · Crossref
representative citing papers
The paper casts apartness tables of convex scenes as a source and develops a differentiable rate-distortion rendering objective that recovers the separoid structure from images at high accuracy.
The winner of the normal partizan domination game is determined for complete split graphs including star forests under arbitrary initial colorings.
citing papers explorer
-
Hypencoder: Hypernetworks for Information Retrieval
Hypencoder replaces the query vector with a query-generated neural network that scores document vectors, and reports consistent gains over dense retrieval baselines across standard, out-of-domain, and hard retrieval benchmarks.
-
Rendering Separoid Information: Rate-Distortion Reconstruction of Convex Apartness Scenes
The paper casts apartness tables of convex scenes as a source and develops a differentiable rate-distortion rendering objective that recovers the separoid structure from images at high accuracy.
-
The Normal Domination Partizan Game in Stars
The winner of the normal partizan domination game is determined for complete split graphs including star forests under arbitrary initial colorings.