PulseAugur
中
实时 01:16:54
English(EN) TESSERA v2: Scaling Pixel-wise Earth Foundation Models

TESSERA v2 研究揭示地球观测模型的最佳扩展方法

研究人员对像素级地球观测基础模型进行了大规模扩展研究,在 1,024 个 NVIDIA GH200 超级芯片上进行了 395 次训练运行。研究发现,预训练损失是下游性能的糟糕预测指标,这表明将计算资源集中在更大的编码器和更多数据上,而不是更大的投影仪上,更为有效。该团队训练了一系列模型,包括拥有 2100 万个参数的 TESSERA v2-1B-M,其性能优于更大规模的开源和专有模型,并通过 Matryoshka 表示法实现了高效服务。 AI

影响 为高效扩展地球观测基础模型提供了数据驱动的方案,有可能加速部署并提高性能。

排序理由 该集群描述了一篇研究论文,详细介绍了关于扩展地球观测基础模型的大规模实证研究。

在 Hugging Face Daily Papers 阅读 →

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

TESSERA v2 研究揭示地球观测模型的最佳扩展方法

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
Research
该集群描述了一篇研究论文,详细介绍了关于扩展地球观测基础模型的大规模实证研究。
Source corroboration
2 independent sources
Multiple independent publishers reporting the same story raises confidence that it's real and newsworthy.
Topics
paper, 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
100 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. arXiv cs.LG TIER_1 English(EN) · Zhengpeng Feng, Sadiq Jaffer, Ira Shokar, Jovana Knezevic, Mark Elvers, Clement Atzberger, Robin Young, Aneesh Naik, Niall Robinson, Andrew Blake, David Coomes, Anil Madhavapeddy, Srinivasan Keshav ·

    TESSERA v2:像素级地球基础模型的扩展

    arXiv:2607.03949v1 Announce Type: cross Abstract: Pixel-wise Earth-observation (EO) foundation models are now achieving state-of-the-art performance via generated spatial embeddings. However, how these models scale and how best to spend a pretraining budget remain poorly understo…

  2. Hugging Face Daily Papers TIER_1 English(EN) ·

    TESSERA v2:像素级地球基础模型的扩展

    Large-scale controlled experiments reveal optimal scaling strategies for Earth-observation foundation models, enabling efficient training and deployment through encoder growth, downstream performance selection, and model distillation.