--- id: "/foundation-models-labs/advanced/page/22/" title: "Foundation models & labs for advanced learners · page 22" url: "https://skillissue.dev/foundation-models-labs/advanced/page/22/" --- # Foundation models & labs for advanced learners [Beginner](/foundation-models-labs/beginner/index.md) [Intermediate](/foundation-models-labs/intermediate/index.md) [Advanced](/foundation-models-labs/advanced/index.md) [Expert](/foundation-models-labs/expert/index.md) 684 resources · page 22 of 22 - ### [Samrómur Milljón: An ASR Corpus of One Million Verified Read Prompts in Icelandic](/lab-practices/other-labs/reykjavik-language-and-voice-lab-papers/index.md) by [Carlos Daniel Hernández Mena et al. (Reykjavik University Language and Voice Lab)](https://lvl.ru.is/) LREC-COLING 2024 paper presenting Samrómur Milljón, an Icelandic ASR corpus of one million validated read prompts. Advanced–Expert learning_resource paper Iceland en - ### [Sakana blog](/lab-practices/other-labs/sakana-blog/index.md) by [Sakana AI](https://sakana.ai/) Sakana AI blog with research posts on evolutionary model merging, agents and its Fugu models, partly in Japanese. Advanced learning_resource blog JP en - ### [ReLiK: Retrieve and LinK, Fast and Accurate Entity Linking and Relation Extraction on an Academic Budget](/lab-practices/other-labs/sapienza-nlp-relik-paper/index.md) by [Riccardo Orlando et al. (Sapienza University of Rome)](https://www.uniroma1.it) arXiv paper (2024) introducing ReLiK, fast entity linking and relation extraction by Sapienza NLP. Advanced–Expert learning_resource paper Italy en - ### [SEQUOR: A Multi-Turn Benchmark for Realistic Constraint Following](/lab-practices/other-labs/sardine-sequor-paper/index.md) by [Beatriz Canaverde et al. (Instituto de Telecomunicações)](https://www.it.pt/) arXiv paper (2026) introducing SEQUOR, a multi-turn benchmark for realistic constraint following. Advanced–Expert learning_resource paper Portugal en - ### [SmolLM3 model card](/lab-practices/other-labs/smollm3-model-card/index.md) by [Hugging Face Smol Models Research](https://huggingface.co/HuggingFaceTB) Hugging Face model card for SmolLM3-3B with architecture, training details and evaluation results. Advanced learning_resource docs US; France; international en - ### [Bielik v3 Small: Technical Report](/lab-practices/other-labs/speakleash-bielik-v3-small-paper/index.md) by [Krzysztof Ociepa et al. (SpeakLeash)](https://speakleash.org/) arXiv paper (2025) Bielik v3 Small technical report on SpeakLeash's small Polish language models. Advanced–Expert learning_resource paper Poland en - ### [Apertus: Democratizing Open and Compliant LLMs for Global Language Environments](/lab-practices/other-labs/swiss-ai-initiative-papers/index.md) by [Project Apertus (Swiss AI Initiative)](https://www.swiss-ai.org/) arXiv paper (2025) introducing Apertus, the Swiss AI Initiative's open and compliant multilingual LLMs. Advanced–Expert learning_resource paper Switzerland en - ### [T-Pro 2.1 instruction-following and tool-calling report](/lab-practices/other-labs/t-pro-2-1-instruction-following-and-tool-calling-report/index.md) by [T-Bank](https://www.tbank.ru/) T-Bank Habr article in Russian on T-Pro 2.1 improvements to instruction following and tool calling. Advanced learning_resource paper Russia ru - ### [Connectionism (Thinking Machines Lab)](/lab-practices/other-labs/thinking-machines-blog/index.md) by [Thinking Machines Lab](https://thinkingmachines.ai/) Thinking Machines Lab blog Connectionism, with research posts on training, numerics and infrastructure experiments. Advanced learning_resource blog West en - ### [Pretraining Finnish ModernBERTs](/lab-practices/other-labs/turkunlp-papers/index.md) by [Akseli Reunamo et al. (University of Turku)](https://www.utu.fi) arXiv paper (2025) by TurkuNLP on pretraining Finnish ModernBERT encoder models. Advanced–Expert learning_resource paper Finland en - ### [UK AISI work](/lab-practices/other-labs/uk-aisi-work/index.md) by [UK AI Security Institute](https://www.aisi.gov.uk/) UK AI Security Institute work page listing its research, evaluations and blog posts. Advanced learning_resource docs UK en - ### [Vikhr: The Family of Open-Source Instruction-Tuned Large Language Models for Russian](/lab-practices/other-labs/vikhr-research-paper-v-model-documentation/index.md) by [Aleksandr Nikolich et al. (ITMO University)](https://en.itmo.ru/) arXiv paper (2024) introducing Vikhr, a family of open instruction-tuned Russian language models. Advanced–Expert learning_resource paper CN/RU en [Previous page](/foundation-models-labs/advanced/page/21/index.md) [Plain-text Markdown copy](/foundation-models-labs/advanced/page/22/index.md)