List your company

Infilling on ROCStories

25.4ROUGE-1DiffuLLaMA + P2-self
7.09611.84816.621.352Feb 5, 2025May 1, 2025Jul 25, 2025Oct 19, 2025Jan 12, 2026Apr 7, 2026Jul 2, 2026

Evaluation results

MethodLinks
DiffuLLaMA + P2-selfModel=DiffuLLaMA, Parameters=7B, Sampling Strategy=P2-self2025.0225.47.123.4——
DiffuLlamaSize=7B, Type=DD2026.0123.35.521.2——
MDLMSize=130M, Tokens=157B2026.0722.22.315.2—72.6
DiffuLLaMAModel=DiffuLLaMA, Parameters=7B, Sampling Strategy=ancestral sampling2025.0220.32.818.2——
A3Size=8B, Type=A32026.0119.24.618.6——
DiffuGPT-MModel=DiffuGPT-M, Parameters=355M2025.0218.72.717——
AR TransformerSize=130M, Tokens=157B2026.0718.31.313.1—158.4
SW-SetDLM S ≤ 32Size=110M, Tokens=157B2026.0718.11.313.2—123.1
ASSDSize=110M, Tokens=45B2026.07181.413.2——
DiffuGPT-SSize=127M, Tokens=n/a2026.0716.4214.2——
SEDD-SSize=170M, Tokens=210B2026.0716.21.312.2——
BD3LM S = 16Size=110M, Tokens=157B2026.0715.80.811.1—114.2
DiffuGPT-SModel=DiffuGPT-S, Parameters=127M2025.0213.71.412.6——
GPT2-SSize=127M, Tokens=n/a2026.0713.50.610.2——
SEDD-MModel=SEDD-M, Parameters=424M2025.0213.11.412.2——
PlaidSize=1B, Type=CD2026.0112.11.111.2——
Plaid1BModel=Plaid1B, Parameters=1.3B2025.0212.11.111.2——
SEDD-SModel=SEDD-S, Parameters=170M2025.0211.90.710.9——
A3Size=1B, Type=A32026.0111.81.711.1——
Llama-3.1Size=8B, Type=AR2026.0111.72.310.5——
DreamSize=7B, Type=DD2026.0111.72.310.5——
LLaMA2Model=LLaMA2, Parameters=7B2025.0211.62.110.5——
A3Size=3B, Type=A32026.0111.32.310.2——
GPT2-MModel=GPT2-M, Parameters=355M2025.028.60.98.2——
GPT2-SModel=GPT2-S, Parameters=127M2025.027.80.87.4——
BaseCPT=Base, SFT=None2026.05———6.94—
BaseCPT=Base, SFT=Base2026.05———9.87—
Base-GaussianCPT=Base, SFT=Gaussian2026.05———9.48—
GaussianCPT=Gaussian, SFT=None2026.05———7.31—
Gaussian-BaseCPT=Gaussian, SFT=Base2026.05———12.18—
Gaussian-GaussianCPT=Gaussian, SFT=Gaussian2026.05———12.62—