Wei Guo

@weiguo01

ML PhD, Georgia Tech; Research Intern, NVIDIA; math undergrad, PKU: Generative AI / Diffusion / LLM / MCMC Sampling / Agent-assisted Theoretical Research

following
followers

Sigma introduced as a continuous diffusion language model in 3B and 8B sizes

The authors report competitive math and coding results, but high-step decoding remains slower than optimized autoregressive baselines.

8 Sources, 14d ago, updated 14d ago

Featured in

Sigma introduced as a continuous diffusion language model in 3B and 8B sizes

Featured in

Sigma introduced as a continuous diffusion language model in 3B and 8B sizes