This paper introduces XDLM, a single model that blends two popular diffusion styles (masked and uniform) so it both understands and generates text and images well.

#XDLM#discrete diffusion#stationary noise kernel

BatCoder: Self-Supervised Bidirectional Code-Documentation Learning via Back-Translation

Intermediate

Jingwen Xu, Yiyang Lu et al.Jan 30arXiv

BatCoder teaches a code model to write both code and its documentation by doing a round trip: from code to docs and back to code.

#back-translation#self-supervised learning#reinforcement learning for code

Stable-DiffCoder: Pushing the Frontier of Code Diffusion Large Language Model

Intermediate

Chenghao Fan, Wen Heng et al.Jan 22arXiv

Stable-DiffCoder is a code-focused diffusion language model that learns to write and edit programs by filling in masked pieces, not just predicting the next token.

#diffusion language model#block diffusion#code generation