Index

Recent Notes

AVION - Aerial Vision-Language Instruction from Offline Teacher to Prompt-Tuned Network
Sep 18, 2026
Agree to Disagree - Adaptive Ensemble Knowledge Distillation in Gradient Space
Sep 18, 2026
Beyond Soft Label - Dataset Distillation via Orthogonal Gradient Matching
Sep 18, 2026
DUNE - Distilling a Universal Encoder from Heterogeneous 2D and 3D Teachers
Sep 18, 2026
Distillation Scaling Laws
Sep 18, 2026
Domain-Constrained Distillation of DINOv3 into a Lightweight Foundation Model Toward Point-of-Care Ultrasound
Sep 18, 2026
Foundry
Sep 18, 2026
Improving CLIP Fine-tuning Performance
Sep 18, 2026
Knowledge Transfer with Jacobian Matching
Sep 18, 2026
Learning Efficient Vision Transformers via Fine-Grained Manifold Distillation
Sep 18, 2026
Orthogonal Gradient Descent for Continual Learning
Sep 18, 2026
Rethinking Dataset Distillation - Hard Truths about Soft Labels
Sep 18, 2026
Scalable Model Merging with Progressive Layer-wise Distillation (ProDistill)
Sep 18, 2026
Towards Understanding Knowledge Distillation
Sep 18, 2026
Two Mathematical Models of Knowledge Distillation
Sep 18, 2026
Weight Copy and Low-Rank Adaptation for Few-Shot Distillation of Vision Transformers (WeCoLoRA)
Sep 18, 2026
What Mechanisms Does Knowledge Distillation Distill
Sep 18, 2026
What Matters in On-Policy Distillation
Sep 04, 2026
Balancing Frequencies and Pixels in Flow Matching
Sep 02, 2026
CA-OPD
Sep 02, 2026