PulseAugur
中
实时 08:48:11
English(EN) Darwin-180B-RSI: VIDRAFT's Recursive Self-Improvement MoE Model Claims Five Leaderboard Tops

VIDRAFT的Darwin-180B-RSI模型在7个Hugging Face排行榜上名列前茅

作者 PulseAugur 编辑部 · [2 个来源] ·

VIDRAFT发布了Darwin-180B-RSI，这是一个拥有1800亿参数的推理模型，采用了递归自改进（RSI）框架。该模型在七个Hugging Face排行榜上均取得了最高排名，包括法律推理基准LEXam和LEXam-hard，尽管它并未在法律数据上进行训练。RSI方法涉及模型解决问题，通过自动化检查验证正确性，然后对成功的推理路径进行再训练，从而使能力泛化到新领域。该模型可在Hugging Face上公开访问和验证。 AI

影响 在法律推理基准上设定了新的SOTA（State-of-the-Art），展示了通过自改进实现的跨领域泛化。

排序理由 Frontier-lab模型发布，附带系统卡。[lever_c 从 frontier_release 降级：ic=2 ai=1.0]

在 dev.to — LLM tag 阅读 →

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

VIDRAFT的Darwin-180B-RSI模型在7个Hugging Face排行榜上名列前茅

本文如何被排名

Signal score
0 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Significant
Frontier-lab模型发布，附带系统卡。[lever_c 从 frontier_release 降级：ic=2 ai=1.0]
Source corroboration
2 independent sources
Multiple independent publishers reporting the same story raises confidence that it's real and newsworthy.
Topics
model release, product
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
46 days old
Aged out of breaking-news scoring windows; ranking reflects the durable signal from the full source set.

完整方法见我们的编辑标准。

报道来源 [2]

  1. dev.to — LLM tag TIER_1 English(EN) · AI OpenFree ·

    Darwin-180B-RSI：VIDRAFT 的递归自改进模型如何在没有法律培训数据的情况下登上 7 个 Hugging Face 排行榜榜首

    <h1> Darwin-180B-RSI: How VIDRAFT's Recursive Self-Improvement Model Topped 7 Hugging Face Leaderboards — Without Legal Training Data </h1> <blockquote> <p><strong>TL;DR:</strong> VIDRAFT's <code>Darwin-180B-RSI</code> is a 180-billion-parameter reasoning model trained via a Recu…

  2. dev.to — LLM tag TIER_1 English(EN) · AI OpenFree ·

    Darwin-180B-RSI：VIDRAFT 的递归自改进 MoE 模型声称在五个排行榜上名列前茅

    <h1> Darwin-180B-RSI: VIDRAFT's Recursive Self-Improvement MoE Model Claims Five Leaderboard Tops </h1> <blockquote> <p><strong>TL;DR:</strong> VIDRAFT, a Korean Pre-AGI AI startup, has released Darwin-180B-RSI — a 180-billion-parameter mixture-of-experts reasoning model built on…

相关实体

相关话题