PulseAugur
实时 01:57:54
English(EN) Can a self-supervised model learn good visual representations without ever reconstructing pixels? JEPA, the program from FAIR now continued at AMI Labs, says ye

Yann LeCun 驳斥 LLM 是通往 AGI 的道路,力挺 JEPA

Yann LeCun 认为,当前的大型语言模型(LLMs)由于缺乏预测后果或执行基于搜索的推理的能力,并非通往人类水平智能的道路。他提倡他的联合嵌入预测架构(JEPA)方法,该方法侧重于世界模型的自监督学习。JEPA 旨在通过预测缺失的数据嵌入来学习表征,他认为这种方法在实现通用智能方面更有前景。 AI

影响 Yann LeCun 对 LLM 的批评以及对 JEPA 的推广表明,人工智能研究的重点可能会从纯粹的语言模型转向基于世界模型的 AGI 实现方法。

排序理由 Yann LeCun 在一次播客访谈中表达了他对 LLM 局限性的看法,并推广了他的替代方法(JEPA)。

在 Mastodon — fosstodon.org 阅读 →

AI 生成摘要 · Google Gemini · 来自 2 个来源。 我们如何撰写摘要 →

报道来源 [2]

  1. Mastodon — fosstodon.org TIER_1 English(EN) · [email protected] ·

    Are LLMs a path to human-level intelligence? Yann LeCun's answer on the Unsupervised Learning podcast is no: they can't predict the consequences of their action

    Are LLMs a path to human-level intelligence? Yann LeCun's answer on the Unsupervised Learning podcast is no: they can't predict the consequences of their actions or plan by search, and only work where language is the substrate of reasoning. The architecture he's scaling at AMI La…

  2. Mastodon — fosstodon.org TIER_1 English(EN) · [email protected] ·

    Can a self-supervised model learn good visual representations without ever reconstructing pixels? JEPA, the program from FAIR now continued at AMI Labs, says ye

    Can a self-supervised model learn good visual representations without ever reconstructing pixels? JEPA, the program from FAIR now continued at AMI Labs, says yes by training the model to predict embeddings of missing data instead. This primer walks you through where JEPA came fro…