Train Where the Quantized Model Goes: On-Policy Distillation for Low-Bit Reasoning
cs.LG, cs.AI
Submitted: 2026-09-22
Updated: 2026-09-22
Comments: 18 pages, 6 figures
Code: https://github.com/EleutherAI/lm-evaluation-harness
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- Program Synthesis with Large Language Models
- Evaluating Large Language Models Trained on Code
- Training Verifiers to Solve Math Word Problems
- DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
- What Makes Low-Bit Quantization-Aware Training Work for Reasoning LLMs? A Systematic Study
- The Era of 1-bit LLMs: All Large Language Models are in 1.58 Bits
- Qwen3 Technical Report
- DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
- EdgeRazor: A Lightweight Framework for Large Language Models via Mixed-Precision Quantization-Aware 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: Local-Consistency Optimisation for Bayesian Neural Networks
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks