FoCore uses self-contrast on early-converging high-density tokens to boost diffusion LLM quality on reasoning benchmarks while cutting decoding steps by over 2x.
Decoding large language diffusion models with foreseeing movement.arXiv preprint arXiv:2512.04135
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Focus on the Core: Empowering Diffusion Large Language Models by Self-Contrast
FoCore uses self-contrast on early-converging high-density tokens to boost diffusion LLM quality on reasoning benchmarks while cutting decoding steps by over 2x.