Progressive Multi-Ancestor Bit-Depth Distillation

arXiv:2610.04100 · cs.LG · Submitted 2026-10-02 · Read on arXiv

cs.LG

Submitted: 2026-10-02

Updated: 2026-10-02

Code: https://github.com/adil-mubashir-ch/PMABD

Terminology

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

Sources

• HPM-KD: Hierarchical Progressive Multi-Teacher Framework for Knowledge Distillation and Efficient Model Compression
• Unifying Block-wise PTQ and Distillation-based QAT for Progressive Quantization toward 2-bit Instruction-Tuned LLMs
• QKD: Quantization-aware Knowledge Distillation
• Paying More Attention to Attention: Improving the Performance of Convolutional Neural Networks via Attention Transfer
• Data-Augmented Quantization-Aware Knowledge Distillation
• Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computation
• Channel Distillation: Channel-Wise Attention for Knowledge Distillation

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