newsHacker NewsTrust 52 · CommunityPublished 11d agoLive · 11d ago
Continuous Diffusion Language Models (CDLM's)
108points36comments
Why these links exist
Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.
- PossiblePossibly related (embedding) · 69%piesauce/awesome-dLLM-resources →
- PossiblePossibly related (embedding) · 65%minimal-diffusion-lm →
- PossiblePossibly related (embedding) · 53%Adaptive Block Diffusion: Resolving Training-Inference Mismatch in Diffusion Language Models →
- PossiblePossibly related (embedding) · 52%Understanding Evaluation Illusion in Diffusion Large Language Models →
- PossiblePossibly related (embedding) · 51%Trace-Based On-Policy Distillation for Masked Diffusion Language Models →
- PossiblePossibly related (embedding) · 47%Let It Go or Learn to Self-Correct: Continuous Diffusion for Constrained Discrete Tasks →
Covers
repopiesauce/awesome-dLLM-resourcesrepominimal-diffusion-lmpaperAdaptive Block Diffusion: Resolving Training-Inference Mismatch in Diffusion Language ModelspaperUnderstanding Evaluation Illusion in Diffusion Large Language ModelspaperTrace-Based On-Policy Distillation for Masked Diffusion Language Models
Covers (incoming)
Related across the graph
paperUnderstanding Evaluation Illusion in Diffusion Large Language Modelsrepominimal-diffusion-lmpaperLet It Go or Learn to Self-Correct: Continuous Diffusion for Constrained Discrete TaskspaperAdaptive Block Diffusion: Resolving Training-Inference Mismatch in Diffusion Language Modelsrepopiesauce/awesome-dLLM-resourcespaperTrace-Based On-Policy Distillation for Masked Diffusion Language Models