arxiv
PublishedJune 2, 2026 at 4:00 AM
Balancing Knowledge Distillation for Imbalance Learning with Bilevel Optimization
Publisher summary· verbatim
arXiv:2605.17839v3 Announce Type: replace-cross Abstract: Knowledge distillation transfers knowledge from a high capacity teacher to a compact student using a mixture of hard and soft losses. On imbalanced data, a fixed weighting between hard and soft losses becomes brittle the learning process. Rec
Stay posted· Newsletter
A 5-min weekly brief — top movers, price watch, story of the week.
Discussion
No replies yet. Be first.
Related coverage
More from ARXIV
arxivFrom Noise to Control: Parameterized Diffusion Policies3harxivOn Wednesdays, We Ask Questions: Optimizing "Active Listening" in Automated Legal Triage and Referral3harxivMesh Field Theory: Port-Hamiltonian Formulation of Mesh-Based Physics3harxivCoupling Language Models with Physics-based Simulation for Synthesis of Inorganic Materials3hThe Bubble Brief
WEEKLYRead AI insights every Tuesday — top movers, new releases, story of the week.
Originally published on arxiv ↗