3 Matching Annotations
  1. Last 7 days
    1. In pixel-native generation, more inference often means sampling more outputs: generate twenty images, pick the best one, maybe try again. That is useful, but every attempt is mostly a new roll of the dice.

      作者认为当前主流的像素原生生成方法本质上是在'掷骰子',每次尝试都是全新的随机生成。这一观点挑战了当前扩散模型通过增加推理次数提升质量的共识,暗示这种方法效率低下且缺乏系统性改进。

    1. the future of video generation may depend more on language models and agents than on diffusion alone

      大多数人认为扩散模型(diffusion models)是视频生成的核心技术,并将持续主导这一领域,但作者认为未来视频生成的发展将更多地依赖于语言模型和代理技术,而非单纯的扩散方法。这挑战了当前AI生成领域的技术共识,暗示了语言模型可能在视频生成中扮演更重要的角色。

  2. Apr 2026
    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。