#knowledge distillation
topicknowledge distillation
26 papers · 1 filter
cs.IR2026
Score-Only Distillation for Compact Dense Retrieval
Kirill Dubovikov, Martin Takac, Salem Lahlou
The paper proposes a method to compress large dense retrieval models into much smaller ones by distilling only the teacher's score vectors, using a row‑centered score‑vector object…
cs.CV2026
LaGuadia: Language-Guided Adaptive Distillation from Pathology Foundation Models
Gangsu Kim, Won-Ki Jeong
LaGuadia is a framework that creates a compact pathology image encoder by using clinical language to adaptively weight multiple foundation model teachers during knowledge distillat…