Blurring the Block Boundaries: Overlapping Block Denoising for Efficient Diffusion Language Models
cs.CL, cs.AI
Submitted: 2026-11-10
Updated: 2026-11-10
Code: https://github.com/huggingface/Omni-MATH
Terminology
Sources
- Neither Parallel Nor Sequential: How DiffusionGemma Actually Commits Tokens
- LLaDA2.0: Scaling Up Diffusion Language Models to 100B
- LLaDA2.1: Speeding Up Text Diffusion via Token Editing
- LangFlow: Continuous Diffusion Rivals Discrete in Language Modeling
- SDAR: A Synergistic Diffusion-AutoRegression Paradigm for Scalable Sequence Generation
- Training Verifiers to Solve Math Word Problems
- DiffusionGemma Technical Report
- An Introduction to Flow Matching and Diffusion Models
- Rethinking the Generation Order of Block Diffusion Language Models
- Multi-Block Diffusion Language Models
- Learn from Your Mistakes: Self-Correcting Masked Diffusion Models
- Seed Diffusion: A Large-Scale Diffusion Language Model with High-Speed Inference
- FlowBlock: Wavefront-Parallel Decoding for Self-Correcting Diffusion Language Models
- GeoBlock: Inferring Block Granularity from Dependency Geometry in Diffusion Language Models
- When to Commit? Towards Variable-Size Self-Contained Blocks for Discrete Diffusion Language Models
- Dream 7B: Diffusion Large Language Models
- Sumi: Open Uniform Diffusion Language Model from Scratch
- Instruction-Following Evaluation for Large Language Models
- LLaDA 1.5: Variance-Reduced Preference Optimization for Large Language Diffusion Models
Related papers
- ALARM: Audio-Language Alignment for Reasoning Models
- ThinkSum: Probabilistic reasoning over sets using large language models
- Coherence boosting: When your pretrained language model is not paying enough attention
- From Facts to Insights: A Persona-Driven Dual Memory Framework and Dataset for Role-Playing Agents
- Improving General Role-Playing Agents via Psychology-Grounded Reasoning and Role-Aware Policy Optimization
- The Art of Asking: Multilingual Prompt Optimization for Synthetic Data