English(EN) Perplexity and NVIDIA Made a Model Teach Itself, and It Matched RL With 6.5x Fewer Tokens

Perplexity 和 Nvidia 使用 JOLT 开发了自学习 AI 模型

作者 PulseAugur 编辑部 · [1 个来源] · 2026-10-25 21:01

Perplexity 和 Nvidia 开发了一种名为 JOLT 的新型 AI 训练方法，该方法使单个模型能够同时充当教师和学生。这种方法涉及模型根据学生组件的学习效果来评估自身的表现。该方法已被证明能够在使用显著更少 Token 的情况下，达到与强化学习相当的结果。 AI

影响这种自学习方法可能导致更高效、更有效的 AI 模型训练，从而可能降低计算成本。

排序理由详细介绍新 AI 训练方法的 ist 研究论文。[lever_c_demoted from research: ic=1 ai=1.0]

AI 生成摘要 · Google Gemini · 来自 1 个来源。我们如何撰写摘要 →

本文如何被排名

Signal score: 46 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 详细介绍新 AI 训练方法的 ist 研究论文。[lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration: Single-source cluster; Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics: model release, infra; Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance: High; Clearly on-topic for AI-industry coverage.
Story freshness: Breaking (< 6h); Fresh story with cross-source coverage still developing. Ranking may shift as more sources report.

完整方法见我们的编辑标准。

Towards AI TIER_1 English(EN) · Aya Mahmoud · 2026-10-25 21:01

Perplexity and NVIDIA Made a Model Teach Itself, and It Matched RL With 6.5x Fewer Tokens

<div class="medium-feed-item"><p class="medium-feed-image"><a href="https://pub.towardsai.net/perplexity-and-nvidia-made-a-model-teach-itself-and-it-matched-rl-with-6-5x-fewer-tokens-c6cd54df1880?source=rss----98111c9905da---4"><img src="https://cdn-images-1.medium.com/max/1672/1…