LAW bases language modeling entirely on self-conditioning
After TinyGSM training, LAW solves 42.2% of GSM8K at 1024 NFE versus 34.5% for uniform loopholing discrete diffusion.
Stories per day · 30 days
3 RSS
Relateddiffusion-language-models1flow-matching1generative-models1gsm8k1language-modeling1openwebtext1transformers1visual-reasoning1
3 stories, newest first · one card per story
Stories tagged #self-conditioning
Self-Conditioning Enables Deep Sequential Reasoning in Flow Matching
Researchers show self-conditioning lets flow-matching models gain deeper visual reasoning from additional sampling steps.
On the Design Space of Continuous Diffusion Language Models
A study of continuous diffusion language models introduces DoubleCat and SemiCat, matching discrete diffusion on TinyGSM.