HackerNews中文版

现在大家都在谈论非自回归架构，它能以 JSON Schema 进行闪电般的概率预测。我早在 2025 年 3 月就着手研究这个课题，发表了一篇 arXiv 论文，并将模型、PyPI 包和训练数据集都发布到了 Hugging Face。一年后，一家前沿实验室提出了同样的想法，声称是突破性的创新，但没有技术论文、开放权重和开放数据集。在此告知大家，主要的指导模型是强化学习（RL），而不是嵌入模型或大型语言模型（LLM）。论文：https://arxiv.org/abs/2503.23303 模型：https://huggingface.co/DeepMostInnovations/sales-conversion-model-reinf-learning 数据集：https://huggingface.co/datasets/DeepMostInnovations/saas-sales-conversations 此外，我在 2025 年 9 月发表的第二项工作与 Jev 现在提出的完全相同。论文：https://arxiv.org/abs/2510.01237 我的模型使用 PPO 在序列嵌入上输出逐回合的转化轨迹（概率从 0.0 到 1.0）。 Jev 使用并行采样（通过 RLCD 训练）来输出置信度分布和 Schema 选择。令人沮丧的是，你耗费数月辛勤工作、汗水和不眠之夜才完成的东西，在架构上与某个垂直应用场景相似，却得不到应有的支持，因为前沿实验室构建了更具普适性的东西。总的来说，开源的生态故事……

查看原文

Everyone now talks about the architecture that's not auto regressive and does lightning fast probability prediction with a json schema. I worked on this literally one year back in March 2025, published an arxiv paper, pushed the model to huggingface along with the pypi package and training dataset. And then one year later, a frontier lab came, proposing the same idea like literal breakthrough without technical papers, open weights and no open dataset. For anyones information the main guiding model is RL not embedding model or LLMPaper: https://arxiv.org/abs/2503.23303Model: https://huggingface.co/DeepMostInnovations/sales-conversion-model-reinf-learningDataset: https://huggingface.co/datasets/DeepMostInnovations/saas-sales-conversationsAlso the second work published in September 2025 was exactly the same one jev proposed nowPaper: https://arxiv.org/abs/2510.01237My model uses PPO over sequence embeddings to output turn-by-turn conversion trajectories (probabilities from 0.0 to 1.0).Jev uses parallel sampling (trained via RLCD) to output confidence distributions and schema choices.It's incredibly frustrating that the thing that you made with months of hard work, sweat and sleepless night is architecturally similar with the vertical use case and don't get the support you deserve because frontier lab build something horizontal. The open-source story in general

去年开源了 JEV 架构，包含模型、论文和数据集。