Meta AI
Open-Source LLM Entwickler (Llama)
Nougat
docprocessingVisual Transformer OCR (Meta) fuer wissenschaftliche Dokumente (Mathe, Formeln).
WebsiteMeta Llama 4
modelsLlama 4: Scout (10M Kontext!), Maverick, Behemoth. 200 Sprachen. Open Source.
WebsitearXiv:2607.08779v1 Announce Type: cross Abstract: The signed integer alphabet contains one more negative representable ...
arXiv:2604.17502v4 Announce Type: replace Abstract: Misaligned artificial agents might resist shutdown. One proposed so...
arXiv:2507.18043v2 Announce Type: replace Abstract: Inference-time steering methods offer a lightweight alternative to ...
arXiv:2607.09415v1 Announce Type: new Abstract: Long-context processing has become increasingly important for large lan...
arXiv:2607.09287v1 Announce Type: cross Abstract: Large language models (LLMs) remain expensive to fine-tune because fu...
arXiv:2606.28876v2 Announce Type: replace Abstract: We study memory-managed long-context attention: explicit bounded me...
<figure> <img alt="" src="https://platform.theverge.com/wp-content/uploads/sites/2/2026/07/gettyimages-2279420244.jpg?q...
<figure> <img alt="" src="https://platform.theverge.com/wp-content/uploads/sites/2/2026/07/meta-muse-image-instagram-ta...
arXiv:2606.21428v3 Announce Type: replace-cross Abstract: Mixture-of-Experts (MoE) language models are often described ...
arXiv:2607.08027v1 Announce Type: new Abstract: This paper proposes an improved structured pruning method for large lan...