Simplex Relaxation for Discrete Diffusion
- 类型:arxiv
- 标识:2608.10615
- 链接:https://arxiv.org/abs/2608.10615
- 主分类:multimodal
- 形态:method
- 被引:0
- 被引来源:Semantic Scholar
- S2被引:0
- 影响力被引:0
- TLDR:Simplax is introduced, an exact Dirichlet--categorical augmentation that couples each corrupted categorical state with an auxiliary simplex-valued variable while preserving the original uniform diffusion process as its categorical marginal.
- 待LLM分类:否
- 标题中文:离散扩散的单纯形松弛
- TLDR中文:本文提出 Simplax,一种精确的 Dirichlet-类别增强方法,将每个被破坏的类别状态与一个辅助的 simplex 值变量耦合,同时保留原始均匀扩散过程作为其类别边缘分布。
- 来源文件:
- /inbox/tom/_candidates/2026-08-13-agent-rag-longcontext-candidates.json
- [S2 enrich]