1 Matching Annotations
  1. Last 7 days
    1. I-DLM-8B is the first DLM to match the quality of its same-scale AR counterpart, outperforming LLaDA-2.1-mini (16B) by +26 on AIME-24 and +15 on LiveCodeBench-v6 with half the parameters

      令人惊讶的是:I-DLM-8B模型仅用80亿参数就超过了160亿参数的LLaDA-2.1-mini模型,在AIME-24和LiveCodeBench-v6测试中分别高出26和15分。这表明扩散模型首次达到了与自回归模型相当的质量水平,同时参数减半,打破了人们对扩散模型质量不如自回归模型的普遍认知。