Adaptive Weighting in Knowledge Distillation: An Axiomatic Framework for Multi-Scale Teacher Ensemble Optimization
Paper
• 2601.17910 • Published
SparseTech Research
The official Hugging Face repository for SparseTech's publications.
-
-
Hallucinations Live in Variance
Paper • 2601.07058 • Published -
Recursive Meta-Distillation: An Axiomatic Framework for Iterative Knowledge Refinement
Paper • 2601.13100 • Published -
Multi-Teacher Ensemble Distillation: A Mathematical Framework for Probability-Domain Knowledge Aggregation
Paper • 2601.09165 • Published -
Sparse Knowledge Distillation: A Mathematical Framework for Probability-Domain Temperature Scaling and Multi-Stage Compression
Paper • 2601.03195 • Published -
Post-Training Probability Manifold Correction via Structured SVD Pruning and Self-Referential Distillation
Paper • 2602.00372 • Published