Diffusion Language Models

#dllm #diffusion

• Session 1 | Diffusion Language Models beat AR in data constrained regime - YouTube

• Diffusion Language Models: The Next Big Shift in GenAI - YouTube

• Text diffusion: A new paradigm for LLMs - YouTube

• Transformers & Diffusion LLMs: What’s the connection? - YouTube

• [2508.10875] A Survey on Diffusion Language Models

• [2505.22618] Fast-dLLM: Training-free Acceleration of Diffusion LLM by Enabling KV Cache and Parallel Decoding

• [2510.03270v1] CoDA: Coding LM via Diffusion Adaptation

  • GitHub - SalesforceAIResearch/CoDA: Salesforce AI Research’s open diffusion language model

• [2510.03280] Training Optimal Large Diffusion Language Models

• [2510.06303] SDAR: A Synergistic Diffusion-AutoRegression Paradigm for Scalable Sequence Generation

• d1: Scaling Reasoning in Diffusion Large Language Models via Reinforcement Learning

• GitHub - JinjieNi/dlms-are-super-data-learners: The official github repo for “Diffusion Language Models are Super Data Learners”.

• GitHub - JinjieNi/OpenMoE2: The official repo for “OpenMoE 2: Sparse Diffusion Language Models”.

• GitHub - pengzhangzhi/Open-dLLM: The most open diffusion language model for code generation — releasing pretraining, evaluation, inference, and checkpoints.

  • Notion

• GitHub - NVlabs/Fast-dLLM: Official implementation of “Fast-dLLM: Training-free Acceleration of Diffusion LLM by Enabling KV Cache and Parallel Decoding”

• GitHub - planned-diffusion/planned-diffusion

• GitHub - ZHZisZZ/dllm: dLLM: Simple Diffusion Language Modeling

• GitHub - yjyddq/EOSER-ASS-RL: Official Repository of “Taming Masked Diffusion Language Models via Consistency Trajectory Reinforcement Learning with Fewer Decoding Step”

• inclusionAI/LLaDA2.0-flash-preview · Hugging Face

• [2511.08923] TiDAR: Think in Diffusion, Talk in Autoregression

• MMaDA-Parallel: Multimodal Large Diffusion Language Models <br> for Thinking-Aware Editing and Generation

• GitHub - inclusionAI/dFactory: Easy and Efficient dLLM Fine-Tuning

• inclusionAI/LLaDA2.0-flash · Hugging Face

• Notion

• DEER: Draft with Diffusion, Verify with Autoregressive Models

• [2512.06776] From Next-Token to Next-Block: A Principled Adaptation Path for Diffusion LLMs