Destruction is a General Strategy to Learn Generation; Diffusion's Strength is to Take it Seriously; Exploration is the Future
cs.LG, cs.IT, math.IT
Submitted: 2026-05-28
Updated: 2026-05-28
Terminology
Sources
- DiffuCoder: Understanding and Improving Masked Diffusion Models for Code Generation
- Reinforcement Learning and Control as Probabilistic Inference: Tutorial and Review
- Diffusion Language Models are Super Data Learners
- DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
- Fine-Tuning Language Models from Human Preferences
Related papers
- A Physics-Regulated Neural Framework for Learning 3D Grain Growth Dynamics
- FlexMoE: Learning One-for-All Multi-Budget Expert Pruning for Flexible MoE Deployment
- OptiMind: Improving Small Language Models for Optimization Modeling through Formulation Guidance and Multi-Turn Learning
- Staying in the Sweet Spot: Boost Reasoning Evolution via Responsive Rollout Difficulty Manipulation
- Examining the Impact of Data and Training Methods on Emergent and Subliminal Misalignment
- Rethinking Black-Box On-Policy Distillation: A Rubric-based Analysis