Hesitation-Aware On-Policy Distillation for Diffusion Language Models
cs.CL, cs.AI
Submitted: 2026-09-27
Updated: 2026-09-27
Terminology
Sources
- LLaDA2.0: Scaling Up Diffusion Language Models to 100B
- SFT Memorizes, RL Generalizes: A Comparative Study of Foundation Model Post-training
- Training Verifiers to Solve Math Word Problems
- dOPSD: On-Policy Self-Distillation for Diffusion Language Models
- Re-evaluating Confidence Remasking in Masked Diffusion Language Models
- DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
- MDPO: Overcoming the Training-Inference Divide of Masked Diffusion Language Models
- Measuring Mathematical Problem Solving With the MATH Dataset
- Distilling the Knowledge in a Neural Network
- INTELLECT-1 Technical Report
- Trace-Based On-Policy Distillation for Masked Diffusion Language Models
- Learn from Your Mistakes: Self-Correcting Masked Diffusion Models
- Deferred Commitment Decoding for Diffusion Language Models
- Dream 7B: Diffusion Large Language Models
- Simple Policy Gradients for Reasoning with Diffusion Language Models
- DiFFPO: Training Diffusion LLMs to Reason Fast and Furious via Reinforcement Learning
- Stabilizing Reinforcement Learning for Diffusion Language Models
Related papers
- Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
- Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
- Subliminal Steering: Stronger Encoding of Hidden Signals
- MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
- The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
- Untangling the Mechanisms of Misleading Context in Medical Question Answering