Learning Beyond Full Imitation: Task-Preserving Knowledge Distillation

arXiv:2609.39338 · cs.LG · Submitted 2026-09-30 · Read on arXiv

cs.LG

Submitted: 2026-09-30

Updated: 2026-09-30

Code: https://github.com/megvii-research/mdistiller

Terminology

• Distillation — 1× in this paper · explained in 2 episodes
• Knowledge Distillation — 1× in this paper · explained in 12 episodes

Sources

• Supervision Complexity and its Role in Knowledge Distillation
• Distilling the Knowledge in a Neural Network
• Well-Read Students Learn Better: On the Importance of Pre-training Compact Models

Related papers

• Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
• AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
• Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
• Convergence issues in Relational Concept Analysis based on AOC-posets
• Beliefs Beyond Posteriors: The Predictive Cost of ELBO Binding
• Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks